hermes-bsd/tests
Teknium 38c8a9c10f
feat(memory): batch operations for single-turn memory updates (#48507)
The memory tool was strictly one-op-per-call. With the store running near
its char limit by design, a new add that would overflow gets rejected with
'consolidate now, then retry' -- but the model could not consolidate and add
in one call. It had to remove/replace across several turns, then retry the
add, each turn re-sending the whole conversation context. Expensive thrash.

Add an 'operations' array: a list of add/replace/remove ops applied
atomically against the FINAL char budget. The model frees space and adds new
entries in ONE call, even when an add alone would overflow. All-or-nothing:
any bad op aborts the whole batch, nothing written.

Root-cause note: the two agent-level memory interception sites
(agent_runtime_helpers.py, tool_executor.py) silently dropped any param not
in their explicit kwarg list, so 'operations' never reached the handler and
batch calls failed with 'Unknown action None'. Both now pass it through and
bridge each add/replace op to external memory providers.

Also: success response is now terminal (done=true + 'do not repeat' note,
no full-entries echo that invited re-edits); schema rewritten to lead with
the batch mechanism and an explicit one-shot stop rule (2138 -> 1476 chars).

Live-verified: near-full consolidate-and-add went 7 calls -> 1 call,
stable across 3 reps. 103 memory/approval tests + 398 background-review/
run_agent tests green; 6 new batch tests added.
2026-06-18 10:19:33 -07:00
..
acp feat(gateway): inject stable human-readable message timestamps 2026-06-16 15:49:59 -07:00
acp_adapter
agent fix(xai): scope native web_search to swap-only + reconcile composer ctx to 200k 2026-06-17 17:33:32 -07:00
cli fix(cli): preserve renderer state on resize 2026-06-13 05:40:18 -07:00
cron fix: complete cron jobs lock salvage 2026-06-15 06:29:00 -07:00
docker Harden hosted Docker install tree against self-modification (#47490) 2026-06-18 09:09:21 +10:00
e2e fix(gateway): include replied-to media attachments (#46107) 2026-06-14 04:51:50 -07:00
fakes
fixtures/plugins/example-dashboard/dashboard
gateway feat(relay): managed-boot self-provision client (Phase 3, gateway side) (#48242) 2026-06-18 15:25:29 +10:00
hermes_cli feat(dashboard): surface full per-MCP catalog detail; fix pip-install doc (#48520) 2026-06-18 09:40:56 -07:00
hermes_state
honcho_plugin
integration
openviking_plugin fix(openviking): adapt memory provider for current api 2026-06-18 16:58:11 +08:00
plugins fix(openviking): adapt memory provider for current api 2026-06-18 16:58:11 +08:00
providers fix(models): pass model.base_url to fetch_models in /model picker 2026-06-16 13:09:40 -07:00
run_agent Merge upstream/main into OpenViking setup-UX (salvage #32445) 2026-06-18 11:28:51 +05:30
scripts
skills
stress
tools feat(memory): batch operations for single-turn memory updates (#48507) 2026-06-18 10:19:33 -07:00
tui_gateway feat(desktop): stream subagent activity into watch windows (#47060) 2026-06-16 14:30:11 -04:00
website
__init__.py
conftest.py fix(tests): guard against real 'hermes update' subprocess spawns in conftest 2026-06-12 13:42:42 -04:00
run_interrupt_test.py
test_account_usage.py
test_assistant_ui_tap_compat.py test(deps): guard @assistant-ui cluster on one tap version 2026-06-15 11:55:02 -04:00
test_atomic_replace_symlinks.py fix(utils): copy fallback for atomic replace across devices (#43852) 2026-06-13 14:50:05 -07:00
test_base_url_hostname.py
test_batch_runner_checkpoint.py
test_bitwarden_secrets.py
test_cli_file_drop.py
test_cli_manual_compress.py
test_cli_skin_integration.py
test_ctx_halving_fix.py
test_dashboard_sidecar_close_on_disconnect.py fix(dashboard): scope chat sidebar model card to selected profile (#46665) 2026-06-15 12:50:19 -04:00
test_desktop_electron_pin.py fix(desktop): resolve electronDist dynamically + self-heal blocked installs (supersedes #48081/#48082) (#48091) 2026-06-17 18:48:35 -05:00
test_desktop_mac_entitlements.py
test_dispatch_session_id.py fix(dispatch): forward session_id into registry.dispatch (#28479) 2026-06-14 00:27:59 -04:00
test_docker_home_override_scripts.py
test_docker_stage2_browser_discovery.py
test_dockerfile_tini_compat_shim.py
test_empty_model_fallback.py
test_empty_session_hygiene.py
test_env_loader_secret_sources.py
test_evidence_store.py
test_gateway_streaming_nested_config.py
test_get_tool_definitions_cache_isolation.py
test_hermes_bootstrap.py
test_hermes_constants.py fix(cli): detect containerd/CRI cgroup-v2 containers in is_container() (#47131) 2026-06-17 12:11:31 +10:00
test_hermes_home_profile_warning.py
test_hermes_logging.py fix(logging): alias RotatingFileHandler to concurrent-log-handler (salvage #44921) (#46794) 2026-06-17 15:39:04 -05:00
test_hermes_state.py feat(gateway): inject stable human-readable message timestamps 2026-06-16 15:49:59 -07:00
test_hermes_state_compression_locks.py
test_hermes_state_wal_fallback.py
test_honcho_client_concurrency.py
test_honcho_client_config.py
test_honcho_session_context.py
test_honcho_startup_fail_open.py
test_install_no_initial_commit.py
test_install_ps1_native_stderr_eap.py fix(install): fail fast when uv venv genuinely fails under relaxed EAP 2026-06-18 22:11:35 +05:30
test_install_ps1_uv_powershell_host.py test(install): lock uv installer to a resolved PowerShell host 2026-06-18 16:26:34 +07:00
test_install_sh_browser_install.py
test_install_sh_install_method_stamp.py fix(update): scope install-method stamp to the code tree, not $HERMES_HOME (#48188) 2026-06-18 14:14:41 +10:00
test_install_sh_node_global_prefix.py fix(install): repair existing managed-Node global prefix on re-run 2026-06-14 17:34:11 +07:00
test_install_sh_pythonpath_sanitization.py
test_install_sh_root_fhs_uv_python_path.py
test_install_sh_setup_wizard_tty_probe.py
test_install_sh_symlink_stomp.py
test_install_sh_termux_network_prereqs.py
test_install_unmerged_index.py test(installer): regression for unmerged-index update failure 2026-06-13 05:19:44 -07:00
test_ipv4_preference.py
test_lazy_session_regressions.py
test_lint_config.py
test_live_system_guard_self_test.py
test_mcp_serve.py
test_mini_swe_runner.py
test_minimax_model_validation.py
test_minimax_oauth.py
test_minisweagent_path.py
test_model_forces_max_completion_tokens.py
test_model_picker_scroll.py
test_model_tools.py
test_model_tools_async_bridge.py
test_ollama_num_ctx.py
test_output_cap_parsing.py
test_package_json_lazy_deps.py
test_packaging_metadata.py feat(mcp-catalog): add official Unreal Engine 5.8 MCP server 2026-06-18 09:16:40 -07:00
test_plugin_skills.py
test_plugin_utils.py
test_process_loop_event_loop_warning.py
test_project_metadata.py
test_retry_utils.py
test_run_tests_parallel.py fix(ci): remove pytest-timeout, use per-file timeout only 2026-06-12 13:42:42 -04:00
test_sanitize_tool_error.py
test_slash_worker_watchdog.py
test_sql_injection.py
test_state_db_malformed_repair.py
test_subprocess_home_isolation.py fix: make profile subprocess HOME policy explicit 2026-06-14 03:20:21 -07:00
test_termux_all_extra_compat.py
test_timezone.py
test_toolset_distributions.py
test_toolsets.py
test_trajectory_compressor.py
test_trajectory_compressor_async.py
test_transform_llm_output_hook.py
test_transform_tool_result_hook.py
test_tui_gateway_server.py fix(tui): don't make Enter swallow trailing-space-only slash completions (#48425) 2026-06-18 11:04:59 -05:00
test_tui_gateway_ws.py feat(desktop): composer status stack, live subagent windows, editable prompts (#44630) 2026-06-12 08:30:06 -05:00
test_tui_mcp_late_refresh.py fix(tui): refresh tool snapshot when MCP discovery lands after agent build (#48403) 2026-06-18 05:41:23 -07:00
test_utils_truthy_values.py
test_web_server.py refactor(desktop): use port 0 for ephemeral port discovery instead of PortPool reservation 2026-06-12 14:02:19 -04:00
test_wheel_locales_e2e.py
test_yuanbao_integration.py
test_yuanbao_markdown.py
test_yuanbao_pipeline.py feat(Yuanbao): support wechat forward msg (#43508) 2026-06-12 02:06:47 -07:00
test_yuanbao_proto.py
test_yuanbao_shutdown.py