hermes-agent/tests/agent
Teknium e5bce320db
fix(auxiliary): evict cached client on timeout/connection error (#23482)
A Codex auxiliary timeout closes the underlying OpenAI client (so the
streaming hang doesn't sit until the user kills the session), but the
cached wrapper kept pointing at the now-dead transport. Subsequent
auxiliary calls (compression retry, memory flush, background review,
title generation routed via provider: main) reused that closed client
and failed fast with 'Connection error' until the gateway restarted —
even though the main agent route was healthy the whole time.

Sync `_get_cached_client` had no liveness check (async did, via loop
identity), and the connection-error fallback in `call_llm` only fired
on the auto provider path, so an explicit provider — including the
common `auxiliary.compression.provider: main` shape — never evicted.

Three fixes:

* New `_evict_cached_client_instance(target)` helper that drops the
  cache entry whose stored client is target (or wraps it via
  `_real_client`, for `CodexAuxiliaryClient`).
* `_CodexCompletionsAdapter._close_client_on_timeout` evicts the
  wrapper after closing the inner OpenAI client.
* `call_llm` and `async_call_llm` evict on `_is_connection_error`
  before re-raising, regardless of whether the provider is auto.

Net effect: one timeout costs one summary attempt + the existing 30s
compressor cooldown; the next compaction rebuilds the client and
works. Non-connection errors (4xx/5xx) do not evict, so cache hits
stay stable.

Closes #23432
2026-05-10 18:55:05 -07:00
..
transports fix(xai): omit reasoning.effort for grok models that reject it (#23435) 2026-05-10 15:21:30 -07:00
__init__.py
test_anthropic_adapter.py fix: avoid unsupported anthropic context beta by default 2026-05-07 05:43:20 -07:00
test_anthropic_keychain.py
test_arcee_trinity_overrides.py test(arcee): cover Trinity Large Thinking temperature + compression overrides 2026-05-05 17:23:45 -07:00
test_auxiliary_client.py fix(auxiliary): evict cached client on timeout/connection error (#23482) 2026-05-10 18:55:05 -07:00
test_auxiliary_client_anthropic_custom.py
test_auxiliary_config_bridge.py fix(tests): pin UTF-8 encoding when reading source files on Windows 2026-05-09 02:47:28 -07:00
test_auxiliary_main_first.py fix(copilot): send vision header for Copilot vision requests 2026-04-27 08:35:50 -07:00
test_auxiliary_named_custom_providers.py fix(fallback): let custom_providers shadow built-in aliases 2026-04-30 20:18:44 -07:00
test_auxiliary_transport_autodetect.py fix(auxiliary): auto-detect Anthropic Messages transport for all aux clients (#17027) 2026-04-28 06:50:14 -07:00
test_bedrock_1m_context.py test: remove 50 stale/broken tests to unblock CI (#22098) 2026-05-08 14:55:40 -07:00
test_bedrock_adapter.py fix(bedrock): preserve reasoningContent across converse normalization 2026-05-07 05:17:16 -07:00
test_bedrock_integration.py
test_codex_cloudflare_headers.py fix(aux): remove hardcoded Codex fallback model, drop Codex from auto chain (#17765) 2026-04-29 23:23:50 -07:00
test_compress_focus.py
test_compressor_image_tokens.py feat(image-input): native multimodal routing based on model vision capability (#16506) 2026-04-27 06:27:59 -07:00
test_context_compressor.py fix(context_compressor): treat streaming premature-close as transient error 2026-05-09 17:52:51 -07:00
test_context_compressor_summary_continuity.py fix(compression): preserve iterative summary continuity 2026-05-05 04:42:44 -07:00
test_context_engine.py
test_context_references.py
test_copilot_acp_client.py fix(ci): recover 38 failing tests on main (#17642) 2026-04-29 20:05:32 -07:00
test_credential_pool.py fix(auth): shorten credential 401 cooldown 2026-05-07 06:15:33 -07:00
test_credential_pool_routing.py
test_crossloop_client_cache.py
test_curator.py fix(skills): keep manual skills out of curator 2026-05-04 02:19:28 -07:00
test_curator_activity.py fix: use skill activity in curator status 2026-04-30 10:31:47 -07:00
test_curator_backup.py fix(curator): authoritative absorbed_into on delete + restore cron skill links on rollback (#18671) (#18731) 2026-05-02 01:29:57 -07:00
test_curator_classification.py feat(curator): hint at hermes curator pin in the rename block (#23212) 2026-05-10 06:44:53 -07:00
test_curator_reports.py fix(curator): rewrite cron job skill refs after consolidation (#18253) 2026-04-30 23:04:50 -07:00
test_deepseek_anthropic_thinking.py test(anthropic): regression guard for DeepSeek /anthropic thinking replay 2026-04-29 08:10:29 -07:00
test_direct_provider_url_detection.py
test_display.py fix(cli): honor positive tool preview length 2026-05-07 05:26:28 -07:00
test_display_emoji.py
test_error_classifier.py fix(error_classifier): classify generic-typed timeout messages as transient (carve-out of #22664) 2026-05-09 17:54:07 -07:00
test_external_skills.py
test_external_skills_dirs_cache.py perf(cli): cut ~19s from 'hermes' cold start (skills cache + lazy Feishu + no Nous HTTP) (#22138) 2026-05-08 16:39:32 -07:00
test_gemini_cloudcode.py
test_gemini_fast_fallback.py Prefer fallback for Gemini CloudCode rate limits 2026-05-05 10:14:48 -07:00
test_gemini_free_tier_gate.py
test_gemini_native_adapter.py
test_gemini_schema.py
test_i18n.py feat(i18n): localize all gateway commands + web dashboard, add 8 new locales (16 total) (#22914) 2026-05-10 07:14:14 -07:00
test_image_gen_registry.py
test_image_routing.py fix(image-routing): sniff magic bytes for image MIME, ignore misleading suffix 2026-05-07 05:58:11 -07:00
test_insights.py
test_kimi_coding_anthropic_thinking.py fix(anthropic): broaden Kimi thinking-suppression to custom endpoints (#17455) 2026-04-29 06:35:42 -07:00
test_local_stream_timeout.py
test_memory_provider.py
test_memory_session_switch.py feat(hindsight): probe API for update_mode='append' support, dedupe across processes 2026-05-05 15:09:59 -07:00
test_memory_user_id.py
test_minimax_auxiliary_url.py
test_minimax_provider.py feat: provider modules — ProviderProfile ABC, 33 providers, fetch_models, transport single-path 2026-05-05 13:40:01 -07:00
test_model_metadata.py fix(model-metadata): set codex-spark fallback context to 128k 2026-05-09 23:17:25 -07:00
test_model_metadata_local_ctx.py fix(tui): show correct context length 2026-04-28 12:27:36 -07:00
test_model_metadata_ssl.py
test_models_dev.py perf(models_dev): cache-first lookup, skip network when disk cache is fresh (#22808) 2026-05-09 13:32:38 -07:00
test_moonshot_schema.py fix(moonshot): also strip nullable/enum after anyOf collapse 2026-04-30 23:14:31 -07:00
test_nous_rate_guard.py fix(nous): don't trip cross-session rate breaker on upstream-capacity 429s (#15898) 2026-04-26 04:53:42 -07:00
test_onboarding.py docs(onboarding): lead OpenClaw residue banner with migrate, warn that cleanup breaks OpenClaw (#17507) 2026-04-29 08:08:36 -07:00
test_openrouter_response_cache.py fix(openrouter): use canonical X-Title attribution header 2026-05-05 10:13:34 -07:00
test_plugin_llm.py feat(plugins): run any LLM call from inside a plugin via ctx.llm (#23194) 2026-05-10 07:09:28 -07:00
test_prompt_builder.py fix(webui): add platform hint for MEDIA rendering 2026-05-09 02:22:40 -07:00
test_prompt_caching.py
test_proxy_and_url_validation.py
test_rate_limit_tracker.py
test_redact.py
test_shell_hooks.py
test_shell_hooks_consent.py fix(shell_hooks): parse hooks_auto_accept as strict bool/string, not bool() (#16322) 2026-04-26 20:48:35 -07:00
test_skill_commands.py test(skills): cover additional rescan paths in skill_commands cache (#14536) 2026-05-07 04:59:43 -07:00
test_skill_commands_reload.py refactor(reload-skills): queue note for next turn, drop cache invalidation + agent tool 2026-04-29 21:07:47 -07:00
test_skill_utils.py test(skill_utils): add regression tests for non-dict metadata in extract_skill_conditions 2026-04-30 20:37:15 -07:00
test_streaming_context_scrubber.py style: trim verbose comment blocks added by previous commit 2026-04-27 12:37:33 -07:00
test_subagent_progress.py
test_subagent_stop_hook.py
test_subdirectory_hints.py
test_think_scrubber.py fix(agent): stateful streaming scrubber for reasoning-block leaks (#17924) (#20184) 2026-05-05 04:33:38 -07:00
test_title_generator.py fix: improve telegram topic mode setup 2026-05-04 12:07:17 -07:00
test_tool_guardrails.py fix(agent): make tool loop guardrails warning-first 2026-04-30 20:43:15 -07:00
test_unsupported_parameter_retry.py test: remove 50 stale/broken tests to unblock CI (#22098) 2026-05-08 14:55:40 -07:00
test_unsupported_temperature_retry.py refactor(memory): remove flush_memories entirely (#15696) 2026-04-25 08:21:14 -07:00
test_usage_pricing.py
test_vision_resolved_args.py fix(vision): preserve explicit provider auth with custom base_url 2026-05-04 05:05:43 -07:00