hermes-agent/tests
Teknium 775c0e22cf
perf(models_dev): cache-first lookup, skip network when disk cache is fresh (#22808)
`fetch_models_dev()` is on the hot path of every `AIAgent.__init__`
(via `context_compressor → get_model_context_length`). The previous
policy was "always try network first, only fall back to disk if
network fails," so every fresh `hermes chat` / `hermes gateway` /
batch / cron process paid 250-500 ms re-fetching a 2 MB JSON registry
that was already on disk from earlier runs.

Add a stage 2 between in-mem and network: if
`models_dev_cache.json` exists and its mtime is younger than the
existing `_MODELS_DEV_CACHE_TTL` (1 hour, same TTL the in-mem cache
already uses), load from disk and skip the network call.

The in-mem TTL is anchored to the disk file's age, so a 50-min-old
cache stays in-memory for only 10 more minutes — no surprise
extension of staleness window.

Invariants preserved:
- `force_refresh=True` still always hits the network and only falls
  back to disk on failure (`hermes config refresh` semantics).
- Missing disk cache → fall through to network (first-ever run).
- Stale disk cache (mtime > TTL) → fall through to network.
- Negative file age (clock skew) → fall through to network.
- Network failure → existing stage-4 stale-disk fallback unchanged.

Measured impact (3-run medians, 9950X3D, fresh process per run):
  fetch_models_dev cold:  256 → 17 ms  (-93%)
  hermes chat -q wall:   4.00 → 3.73 s (-7% median)
                         3.99 → 3.60 s (-10% min)

The chat-end-to-end win is bounded below by API latency variance, but
the fetch_models_dev microbenchmark is the cleanest signal: 239 ms
shaved off every fresh-process agent construction.

Win compounds with the previous perf PRs:
  #22681 google_chat lazy-load
  #22766 doctor parallel + IMDS off
  #22790 gateway.platforms PEP 562

Tests: all 30 `tests/agent/test_models_dev.py` pass (added 4 new ones
covering the new disk-cache-first path, force_refresh override, stale
disk fallback, and missing-disk-cache fall-through). Full `tests/agent/`
suite: 2560 passed, 0 failed.
2026-05-09 13:32:38 -07:00
..
acp fix(acp): preserve assistant reasoning metadata in session persistence 2026-05-05 10:18:28 -07:00
acp_adapter feat(acp): pass image file attachments through as image_url parts 2026-05-07 09:24:32 -07:00
agent perf(models_dev): cache-first lookup, skip network when disk cache is fresh (#22808) 2026-05-09 13:32:38 -07:00
cli fix(cli): make Ctrl+Enter insert newline on WSL/SSH/Windows Terminal (#22777) 2026-05-09 12:48:14 -07:00
cron fix(cron): avoid github skill false positives in scanner 2026-05-09 11:11:45 -07:00
e2e fix(gateway): move quick-command dispatch before built-in handlers 2026-05-04 01:39:23 -07:00
environments/benchmarks
fakes
gateway fix(api-server): emit length/error finish_reason for truncation/failure (#22775) 2026-05-09 12:48:08 -07:00
hermes_cli fix(tools): install cua-driver when Computer Use is enabled via 'hermes tools' (#22765) 2026-05-09 13:02:25 -07:00
hermes_state
honcho_plugin
integration
openviking_plugin fix(openviking): pre-check fs/stat to route file URIs before hitting directory-only endpoints 2026-04-30 02:35:29 -07:00
plugins test(xai-image): regression-guard literal '1k'/'2k' resolution payload 2026-05-09 13:07:46 -07:00
providers feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
run_agent fix(fallback): skip chain entries matching current provider/model/base_url (#22780) 2026-05-09 12:48:19 -07:00
skills fix(google-workspace): restore required_credential_files in SKILL.md (#16452) 2026-05-04 12:43:14 -07:00
stress fix(kanban): gate claim + unblock on parent completion 2026-05-09 11:07:37 -07:00
tools fix: move pytest.importorskip below pytest import in skip-guarded tests 2026-05-09 11:12:03 -07:00
tui_gateway fix(tui): close slash parity gaps with CLI (#20339) 2026-05-05 15:42:39 -05:00
website docs(skills): explain restoring bundled skills 2026-05-05 13:46:20 -07:00
__init__.py
conftest.py fix(tests): avoid asyncio DeprecationWarning in event loop fixture on 3.12+ 2026-05-07 07:05:05 -07:00
run_interrupt_test.py
test_account_usage.py
test_atomic_replace_symlinks.py refactor: consolidate symlink-safe atomic replace into shared helper 2026-04-28 04:58:22 -07:00
test_base_url_hostname.py
test_batch_runner_checkpoint.py
test_cli_file_drop.py
test_cli_manual_compress.py test(cli): regression test for manual /compress system_message 2026-04-28 05:21:49 -07:00
test_cli_skin_integration.py fix(ci): stabilize main test suite regressions (#17660) 2026-04-29 23:18:55 -07:00
test_ctx_halving_fix.py
test_empty_model_fallback.py
test_evidence_store.py
test_get_tool_definitions_cache_isolation.py fix(tools): isolate get_tool_definitions quiet_mode cache + dedup LCM injection (#17335) 2026-04-30 04:32:06 -07:00
test_hermes_bootstrap.py fix(entry-points): guard hermes_bootstrap import so partial updates don't brick hermes (#22091) 2026-05-08 14:43:13 -07:00
test_hermes_constants.py test(hermes_constants): cover parse_reasoning_effort() 2026-05-07 09:59:07 -07:00
test_hermes_home_profile_warning.py fix(constants): warn once when get_hermes_home() falls back under an active profile (#18746) 2026-05-02 01:49:55 -07:00
test_hermes_logging.py
test_hermes_state.py fix(telegram): polish topic mode — CASCADE, General-topic handling, rename guard, debounce 2026-05-04 12:07:17 -07:00
test_hermes_state_wal_fallback.py fix(sqlite): fall back to journal_mode=DELETE on NFS/SMB/FUSE (#22043) 2026-05-09 02:09:35 -07:00
test_honcho_client_config.py
test_install_sh_pythonpath_sanitization.py fix: harden install.sh against inherited Python env leakage 2026-05-06 04:02:02 -07:00
test_install_sh_setup_wizard_tty_probe.py fix(install): widen /dev/tty open-probe to sibling gates (#16746) 2026-04-28 06:45:55 -07:00
test_install_sh_termux_network_prereqs.py fix: strengthen termux install network prerequisites 2026-05-07 13:04:08 -07:00
test_ipv4_preference.py
test_lazy_session_regressions.py fix: resolve lazy session creation regressions (#18370 fallout) (#20363) 2026-05-06 01:11:49 +05:30
test_lint_config.py lint: enable PLW1514 as a blocking ruff rule 2026-05-08 14:27:40 -07:00
test_mcp_serve.py fix(mcp): unwrap platforms key in channels_list 2026-05-07 13:41:16 -07:00
test_mini_swe_runner.py
test_minimax_model_validation.py
test_minimax_oauth.py test(cli): cover minimax-oauth resolution, refresh, menu wiring 2026-04-29 09:53:42 -07:00
test_minisweagent_path.py
test_model_picker_scroll.py
test_model_tools.py fix(plugins): stop firing pre_tool_call hook twice per tool execution (#17611) 2026-04-29 12:43:39 -07:00
test_model_tools_async_bridge.py fix(model_tools): cancel coroutine on timeout so worker thread exits + log full traceback 2026-04-29 05:00:40 -07:00
test_ollama_num_ctx.py
test_packaging_metadata.py
test_plugin_skills.py fix(skills): support category-qualified local skill names 2026-05-05 10:15:31 -07:00
test_process_loop_event_loop_warning.py fix(cli): replace get_event_loop() with get_running_loop() to silence RuntimeWarning in process_loop thread (#19285) 2026-05-07 06:35:54 -07:00
test_project_metadata.py
test_retry_utils.py
test_sql_injection.py
test_subprocess_home_isolation.py
test_termux_all_extra_compat.py fix: add termux-all install profile and safe fallbacks 2026-05-07 13:04:08 -07:00
test_timezone.py
test_toolset_distributions.py
test_toolsets.py fix: merge plugin tools into builtin toolsets 2026-05-05 10:14:17 -07:00
test_trajectory_compressor.py
test_trajectory_compressor_async.py
test_transform_llm_output_hook.py test+docs: cover transform_llm_output hook + release author map 2026-05-07 05:46:05 -07:00
test_transform_tool_result_hook.py
test_tui_gateway_server.py Merge pull request #20942 from NousResearch/austin/fix/personality 2026-05-07 18:54:29 -04:00
test_utils_truthy_values.py
test_yuanbao_integration.py
test_yuanbao_markdown.py
test_yuanbao_pipeline.py
test_yuanbao_proto.py