hermes-agent/tests
teknium1 4a3f13b47b perf(prompt-cache): date-only timestamp + loud gateway-DB roundtrip logging
The system prompt's 'Conversation started:' line carried minute precision
(%I:%M %p), making it byte-unstable across every rebuild path. Within a
CLI session the in-memory cache held, but on the gateway path (fresh
AIAgent per turn → restore from session DB), any silent failure in the
read or write path dropped the cache stem and forced a full re-prefill
on every subsequent turn. Local prefix-caching backends (llama.cpp /
vLLM) saw this as KV-cache invalidation; remote prefix-caching providers
saw it as an Anthropic-style cache miss.

Three changes:

1. Date-only timestamp ('Sunday, May 17, 2026' instead of '... 03:42 PM').
   System prompt now byte-stable for the full day. The model can still
   query exact time via tools when it actually needs it. Credit:
   @iamfoz (PR #20451).

2. Loud logging on session DB write failures. The update_system_prompt
   call used to log at DEBUG, hiding disk-full / locked-database / schema
   drift behind a silent fall-through that forced fresh rebuilds on
   every subsequent turn. Now WARN with the session id and exception so
   persistent issues show up in agent.log without verbose mode.

3. Three-way stored-state distinction on read. The previous
   'session_row.get("system_prompt") or None' collapsed three states
   into one (missing row / null column / empty string). Now we tell them
   apart and WARN when a continuing session lands on null/empty (which
   means the previous turn's write never persisted — every subsequent
   turn rebuilds and the prefix cache misses every time).

The restore block is extracted into _restore_or_build_system_prompt()
so the prefix-cache path can be unit-tested in isolation.

E2E proof: fresh AIAgent constructed for turn 2 across a minute-boundary
sleep restores byte-identical bytes from the session DB. NULL stored
prompt fires the new warning. Date-only timestamp survives the rebuild
path. All on real SessionDB, no mocks.

Tests:
  - tests/agent/test_system_prompt_restore.py (10 new tests)
  - tests/run_agent/test_run_agent.py::TestBuildSystemPrompt::
        test_datetime_is_date_only_not_minute_precision

Closes #20451 (date-only), #18547 (prefix stabilization),
#8689 (stabilize timestamp across compression), #15866 (timestamp
caching question), #8687 (compression timestamp), #27339
(claim #3: live timestamp in cached system prompt).

Co-authored-by: Martyn Forryan <9133432+iamfoz@users.noreply.github.com>
2026-05-17 23:20:37 -07:00
..
acp fix ACP start events for polished tools 2026-05-17 02:31:18 -07:00
acp_adapter fix: make session search initialize session db 2026-05-09 14:36:58 -07:00
agent perf(prompt-cache): date-only timestamp + loud gateway-DB roundtrip logging 2026-05-17 23:20:37 -07:00
cli chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
cron chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
e2e test(e2e): fix Discord mock exception surface 2026-05-14 19:08:38 -07:00
fakes
gateway test(gateway): include direct_messages_topic_id in telegram DM metadata assertions 2026-05-17 12:44:48 -07:00
hermes_cli fix(auth) fix a few cases where refresh tokens were not rotated. 2026-05-17 16:56:37 -07:00
hermes_state
honcho_plugin chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
integration
openviking_plugin
plugins fix(browser): self-review pass — dead-import, log levels, future-proofing 2026-05-17 04:04:15 -07:00
providers feat(nvidia): add NIM billing origin header 2026-05-15 14:06:51 -07:00
run_agent perf(prompt-cache): date-only timestamp + loud gateway-DB roundtrip logging 2026-05-17 23:20:37 -07:00
scripts feat(acp-registry): switch to uvx distribution, drop npm launcher 2026-05-14 22:27:09 -07:00
skills chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
stress chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
tools fix(mcp): use module-level time so test patches do not race background sleepers 2026-05-17 13:33:26 -07:00
tui_gateway chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
website docs(skills): explain restoring bundled skills 2026-05-05 13:46:20 -07:00
__init__.py
conftest.py Switch to JWT token for inference against Nous, falling back to old opaque token on failure. 2026-05-17 16:56:37 -07:00
run_interrupt_test.py
test_account_usage.py
test_atomic_replace_symlinks.py
test_base_url_hostname.py
test_batch_runner_checkpoint.py
test_cli_file_drop.py
test_cli_manual_compress.py
test_cli_skin_integration.py
test_ctx_halving_fix.py fix(cache): kill long-lived prefix layout — system prompt is now byte-static within a session (#24778) 2026-05-12 20:46:04 -07:00
test_empty_model_fallback.py
test_evidence_store.py
test_gateway_streaming_nested_config.py fix(gateway): load streaming config from nested gateway.streaming key 2026-05-14 14:51:07 -07:00
test_get_tool_definitions_cache_isolation.py
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(session): route OR-combined short CJK tokens to LIKE fallback (#20494) 2026-05-09 17:53:02 -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_browser_install.py fix(install): support non-sudo service-user installs on apt distros (#25814) 2026-05-14 09:05:31 -07:00
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
test_install_sh_symlink_stomp.py fix(install): preserve pip entry point when re-running on symlinked install 2026-05-14 07:08:45 -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_live_system_guard_self_test.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -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 fix(minimax): harden OAuth dashboard and runtime 2026-05-11 22:15:16 -07:00
test_minisweagent_path.py
test_model_picker_scroll.py
test_model_tools.py chore: remove Atropos RL environments and tinker-atropos integration (#26106) 2026-05-15 10:36:38 +05:30
test_model_tools_async_bridge.py
test_ollama_num_ctx.py
test_package_json_lazy_deps.py fix(update): make Camofox lazy-installed instead of eager (#27055) 2026-05-16 12:15:45 -07:00
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 fix(install): use --extra all not --all-extras; drop lazy-covered extras from [all] (#24515) 2026-05-12 15:06:25 -07:00
test_retry_utils.py
test_sanitize_tool_error.py security: sanitize tool error strings before injecting into model context (#26823) 2026-05-16 00:57:39 -07:00
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 chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_toolset_distributions.py
test_toolsets.py test(toolsets): lock web search into default platform coverage 2026-05-14 08:03:33 -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 chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_utils_truthy_values.py
test_yuanbao_integration.py
test_yuanbao_markdown.py
test_yuanbao_pipeline.py
test_yuanbao_proto.py