mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-30 06:41:51 +00:00
c3a09f7835
## Summary The background skill/memory-review fork constructed a child `AIAgent` without propagating `enabled_toolsets` / `disabled_toolsets` from the parent. When the parent narrowed its toolset (via `hermes tools disable` or `config.yaml`), the fork's default `enabled_toolsets=None` expanded to "all registered tools" — and the fork's outbound request body sent a wider `tools[]` array than the parent's main-turn request. Anthropic's prompt-cache key includes the `tools[]` array byte-for-byte, so this divergence forked the cache lineage on every nudge and forced a full prefix rewrite. On a captured ~4 hour Claude-via-Hermes session this cost roughly 4.3 M cache-write tokens — about half of those attributable to the per-nudge alternation between the main turn's narrowed `tools[]` and the review fork's wider `tools[]`. ## Goal Extend the byte-stability invariant established by PR #17276 (which fixed `system`) to the `tools[]` slot of the request body, so the review fork's outbound request hits the parent's warmed Anthropic prefix cache regardless of how the parent's toolset is configured. ## Implementation Two-line change in `agent/background_review.py`: pass `enabled_toolsets=getattr(agent, "enabled_toolsets", None)` and the matching `disabled_toolsets` kwarg into the `AIAgent(...)` call inside `_spawn_background_review`. Adds an explanatory block comment that calls out the cache-key dependency and the relationship to PR #17276. The post-construction runtime whitelist (`set_thread_tool_whitelist({memory, skills})`) is untouched — it still gates which tools the model is allowed to *dispatch*. This change aligns only what the request body *transmits*, not what the review is allowed to do, so the safety contract from issue #15204 remains intact. ## Testing - `tests/run_agent/test_background_review_cache_parity.py`: new `test_review_fork_inherits_parent_toolset_config` asserts the parent's `enabled_toolsets` and `disabled_toolsets` reach the review-fork constructor as kwargs. - `tests/run_agent/test_background_review_toolset_restriction.py`: the existing `test_background_review_does_not_narrow_toolset_schema` was inverted (its old "must NOT pass enabled_toolsets" rule was built on the assumption that the parent always ran with the registry default — wrong in practice when the parent is narrowed). Renamed to `test_background_review_matches_parent_toolset_config` and updated to assert the parent's value propagates verbatim. - Verified the new positive test fails without the fix and passes with it. - Full suite for `test_background_review*`: ``` $ python -m pytest tests/run_agent/test_background_review.py \ tests/run_agent/test_background_review_summary.py \ tests/run_agent/test_background_review_toolset_restriction.py \ tests/run_agent/test_background_review_cache_parity.py -q 18 passed in 1.85s ``` ## Scope - `agent/background_review.py`: 2 added kwargs + explanatory comment. - Two test files: one new positive test, one inverted existing test. - No production code paths outside the review fork; no schema changes; no public-API changes. Refs: ziliangpeng/hermes-agent#1 (root-cause analysis with wire-level cache-write measurements). Extends PR #17276's `system`-bytes invariant to the `tools[]` slot. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| conftest.py | ||
| test_413_compression.py | ||
| test_860_dedup.py | ||
| test_1630_context_overflow_loop.py | ||
| test_agent_guardrails.py | ||
| test_anthropic_prompt_cache_policy.py | ||
| test_anthropic_third_party_oauth_guard.py | ||
| test_anthropic_truncation_continuation.py | ||
| test_api_max_retries_config.py | ||
| test_async_httpx_del_neuter.py | ||
| test_background_review.py | ||
| test_background_review_cache_parity.py | ||
| test_background_review_summary.py | ||
| test_background_review_toolset_restriction.py | ||
| test_callable_api_key.py | ||
| test_codex_app_server_integration.py | ||
| test_codex_multimodal_tool_result.py | ||
| test_codex_xai_oauth_recovery.py | ||
| test_commit_memory_session_context_engine.py | ||
| test_compress_focus_plugin_fallback.py | ||
| test_compression_boundary.py | ||
| test_compression_boundary_hook.py | ||
| test_compression_feasibility.py | ||
| test_compression_persistence.py | ||
| test_compression_trigger_excludes_reasoning.py | ||
| test_compressor_fallback_update.py | ||
| test_concurrent_interrupt.py | ||
| test_context_token_tracking.py | ||
| test_copilot_native_vision_headers.py | ||
| test_create_openai_client_kwargs_isolation.py | ||
| test_create_openai_client_proxy_env.py | ||
| test_create_openai_client_reuse.py | ||
| test_deepseek_reasoning_content_echo.py | ||
| test_deepseek_v4_thinking_live.py | ||
| test_dict_tool_call_args.py | ||
| test_empty_response_recovery_persistence.py | ||
| test_exit_cleanup_interrupt.py | ||
| test_file_mutation_verifier.py | ||
| test_image_rejection_fallback.py | ||
| test_image_shrink_recovery.py | ||
| test_init_fallback_on_exhausted_pool.py | ||
| test_interactive_interrupt.py | ||
| test_interrupt_propagation.py | ||
| test_invalid_context_length_warning.py | ||
| test_iteration_budget_race.py | ||
| test_jsondecodeerror_retryable.py | ||
| test_last_reasoning_per_turn.py | ||
| test_long_context_tier_429.py | ||
| test_materialize_data_url_cleanup.py | ||
| test_memory_nudge_counter_hydration.py | ||
| test_memory_provider_init.py | ||
| test_memory_sync_interrupted.py | ||
| test_message_sequence_repair.py | ||
| test_openai_client_lifecycle.py | ||
| test_percentage_clamp.py | ||
| test_plugin_context_engine_init.py | ||
| test_primary_runtime_restore.py | ||
| test_provider_attribution_headers.py | ||
| test_provider_fallback.py | ||
| test_provider_parity.py | ||
| test_real_interrupt_subagent.py | ||
| test_redirect_stdout_issue.py | ||
| test_repair_tool_call_arguments.py | ||
| test_repair_tool_call_name.py | ||
| test_review_prompt_class_first.py | ||
| test_run_agent.py | ||
| test_run_agent_codex_responses.py | ||
| test_run_agent_multimodal_prologue.py | ||
| test_sequential_chats_live.py | ||
| test_session_id_env.py | ||
| test_session_meta_filtering.py | ||
| test_session_reset_fix.py | ||
| test_steer.py | ||
| test_stream_drop_logging.py | ||
| test_stream_interrupt_retry.py | ||
| test_streaming.py | ||
| test_streaming_tool_call_repair.py | ||
| test_strict_api_validation.py | ||
| test_strip_reasoning_tags_cli.py | ||
| test_switch_model_context.py | ||
| test_switch_model_fallback_prune.py | ||
| test_thinking_only_sanitizer.py | ||
| test_token_persistence_non_cli.py | ||
| test_tool_arg_coercion.py | ||
| test_tool_call_args_sanitizer.py | ||
| test_tool_call_guardrail_runtime.py | ||
| test_tool_executor_contextvar_propagation.py | ||
| test_tool_name_db_persistence.py | ||
| test_unicode_ascii_codec.py | ||
| test_vision_aware_preprocessing.py | ||