hermes-agent/tests/run_agent
Teknium 6391b46779
fix: bound auxiliary client cache to prevent fd exhaustion in long-running gateways (#10200) (#10470)
The _client_cache used event loop id() as part of the cache key, so
every new worker-thread event loop created a new entry for the same
provider config.  In long-running gateways where threads are recycled
frequently, this caused unbounded cache growth — each stale entry
held an unclosed AsyncOpenAI client with its httpx connection pool,
eventually exhausting file descriptors.

Fix: remove loop_id from the cache key and instead validate on each
async cache hit that the cached loop is the current, open loop.  If
the loop changed or was closed, the stale entry is replaced in-place
rather than creating an additional entry.  This bounds cache growth
to at most one entry per unique provider config.

Also adds a _CLIENT_CACHE_MAX_SIZE (64) safety belt with FIFO
eviction as defense-in-depth against any remaining unbounded growth.

Cross-loop safety is preserved: different event loops still get
different client instances (validated by existing test suite).

Closes #10200
2026-04-15 13:16:28 -07:00
..
__init__.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_413_compression.py fix: clear conversation_history after mid-loop compression to prevent empty sessions (#7001) 2026-04-10 00:14:59 -07:00
test_860_dedup.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_1630_context_overflow_loop.py fix(gateway): break compression-exhaustion infinite loop and auto-reset session (#9893) 2026-04-14 21:18:17 -07:00
test_agent_guardrails.py fix(delegate): make max_concurrent_children configurable + error on excess 2026-04-10 13:38:14 -07:00
test_agent_loop.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_agent_loop_tool_calling.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_agent_loop_vllm.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_anthropic_error_handling.py fix(tests): fix 78 CI test failures and remove dead test (#9036) 2026-04-13 10:50:24 -07:00
test_async_httpx_del_neuter.py fix: bound auxiliary client cache to prevent fd exhaustion in long-running gateways (#10200) (#10470) 2026-04-15 13:16:28 -07:00
test_compression_boundary.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_compression_feasibility.py test: add tests for compression config_context_length passthrough 2026-04-12 17:52:34 -07:00
test_compression_persistence.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_compressor_fallback_update.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_context_pressure.py fix(agent): tiered context pressure warnings + gateway dedup (#6411) 2026-04-08 21:31:44 -07:00
test_context_token_tracking.py fix(tests): fix 78 CI test failures and remove dead test (#9036) 2026-04-13 10:50:24 -07:00
test_dict_tool_call_args.py fix(tests): fix 78 CI test failures and remove dead test (#9036) 2026-04-13 10:50:24 -07:00
test_exit_cleanup_interrupt.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_fallback_model.py fix(model): normalize direct provider ids in auxiliary routing 2026-04-10 05:52:45 -07:00
test_flush_memories_codex.py fix(agent): respect config timeout for flush_memories instead of hardcoded 30s 2026-04-08 18:55:33 -07:00
test_interactive_interrupt.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_interrupt_propagation.py fix: scope tool interrupt signal per-thread to prevent cross-session leaks (#7930) 2026-04-11 14:02:58 -07:00
test_invalid_context_length_warning.py fix: warn on invalid context_length format in config.yaml (#10067) 2026-04-14 22:14:27 -07:00
test_long_context_tier_429.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_openai_client_lifecycle.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_percentage_clamp.py fix: update 6 test files broken by dead code removal 2026-04-10 03:44:43 -07:00
test_plugin_context_engine_init.py test: add coverage for plugin context engine init (#9071) 2026-04-13 15:00:57 -07:00
test_primary_runtime_restore.py fix(run_agent): recover primary client on openai transport errors 2026-04-10 03:21:24 -07:00
test_provider_fallback.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_provider_parity.py fix(tests): fix 78 CI test failures and remove dead test (#9036) 2026-04-13 10:50:24 -07:00
test_real_interrupt_subagent.py fix(tests): fix 78 CI test failures and remove dead test (#9036) 2026-04-13 10:50:24 -07:00
test_redirect_stdout_issue.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_run_agent.py feat(plugins): let pre_tool_call hooks block tool execution 2026-04-13 22:01:49 -07:00
test_run_agent_codex_responses.py fix: strip reasoning item IDs from Responses API input when store=False (#10217) 2026-04-15 03:19:43 -07:00
test_session_meta_filtering.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_session_reset_fix.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_streaming.py fix(run_agent): refresh activity during streaming responses 2026-04-13 10:55:51 -07:00
test_strict_api_validation.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_switch_model_context.py fix: pass config_context_length to switch_model context compressor 2026-04-10 05:52:45 -07:00
test_token_persistence_non_cli.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_tool_arg_coercion.py refactor(tests): re-architect tests + fix CI failures (#5946) 2026-04-07 17:19:07 -07:00
test_unicode_ascii_codec.py fix: sync client.api_key during UnicodeEncodeError ASCII recovery (#10090) 2026-04-14 22:37:45 -07:00