hermes-agent/tests
Teknium 77c0bc6b13
fix(curator): defer first run and add --dry-run preview (#18373) (#18389)
* fix(curator): defer first run and add --dry-run preview (#18373)

Curator was meant to run 7 days after install, not on the very first
gateway tick. On a fresh install (no .curator_state), should_run_now()
returned True immediately because last_run_at was None — so the gateway
cron ticker fired Curator against a fresh skill library moments after
'hermes update'. Combined with the binary 'agent-created' provenance
model (anything not bundled and not hub-installed), this consolidated
hand-authored user workflow skills without consent.

Changes:
- should_run_now(): first observation seeds last_run_at='now' and returns
  False. The next real pass fires one full interval_hours later (7 days
  by default), matching the original design intent.
- hermes curator run --dry-run: produces the same review report without
  applying automatic transitions OR permitting the LLM to call
  skill_manage / terminal mv. A DRY-RUN banner is prepended to the
  prompt and the caller skips apply_automatic_transitions. State is
  NOT advanced so a preview doesn't defer the next scheduled real pass.
- hermes update: prints a one-liner on fresh installs pointing at
  --dry-run, pause, and the docs. Silent on steady state.
- Docs: curator.md and cli-commands.md explain the deferred first-run
  behavior and warn that hand-written SKILL.md files share the
  'agent-created' bucket, with guidance to pin or preview before the
  first pass.

Tests:
- test_first_run_defers replaces the old 'first run always eligible'
  assertion — same fixture, inverted expectation.
- test_maybe_run_curator_defers_on_fresh_install covers the gateway tick
  path end-to-end.
- Three new dry-run tests cover state-advance suppression, prompt
  banner injection, and apply_automatic_transitions skipping.

Fixes #18373.

* feat(curator): pre-run backup + rollback (#18373)

Every real curator pass now snapshots ~/.hermes/skills/ into
~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz before calling
apply_automatic_transitions or the LLM review. If a run consolidates or
archives something the user didn't want touched, 'hermes curator
rollback' restores the tree in one command. Dry-run is skipped — no
mutation means no snapshot needed.

Changes:
- agent/curator_backup.py (new): tar.gz snapshot + safe rollback. The
  snapshot excludes .curator_backups/ (would recurse) and .hub/ (managed
  by the skills hub). Extract refuses absolute paths and .. components,
  and uses tarfile's filter='data' on Python 3.12+. Rollback takes a
  pre-rollback safety snapshot FIRST, stages the current tree into
  .rollback-staging-<ts>/ so the extract lands in an empty dir, and
  cleans the staging dir on success. A failed extract restores the
  staged contents.
- agent/curator.py: run_curator_review() calls curator_backup.
  snapshot_skills(reason='pre-curator-run') before apply_automatic_
  transitions. Best-effort — a failed snapshot logs at debug and the
  run continues (a transient disk issue shouldn't silently disable
  curator forever).
- hermes_cli/curator.py: new 'hermes curator backup' and 'hermes curator
  rollback' subcommands. rollback supports --list, --id <ts>, -y.
- hermes_cli/config.py: curator.backup.{enabled, keep} config block
  with sane defaults (enabled=true, keep=5).
- Docs: curator.md gets a 'Backups and rollback' section; cli-commands
  .md table gets the new rows.

Tests (new file tests/agent/test_curator_backup.py, 16 cases):
- snapshot creates tarball + manifest with correct counts
- snapshot excludes .curator_backups/ (recursion guard) and .hub/
- snapshot disabled via config returns None without creating anything
- snapshot uniquifies ids within the same second (-01 suffix)
- prune honors keep count, newest-first
- list_backups + _resolve_backup cover newest-default and unknown-id
- rollback restores a deleted skill with content intact
- rollback is itself undoable — safety snapshot shows up in list_backups
- rollback with no snapshots returns an error
- rollback refuses tarballs with absolute paths or .. components
- real curator runs take a 'pre-curator-run' snapshot; dry-runs do not

All curator tests: 210 passing locally.
2026-05-01 09:49:59 -07:00
..
acp fix(compression): include system prompt + tool schemas in token estimates (#18265) 2026-04-30 23:03:54 -07:00
acp_adapter fix(acp): run /steer as a regular prompt on idle sessions (#18258) 2026-04-30 22:45:14 -07:00
agent fix(curator): defer first run and add --dry-run preview (#18373) (#18389) 2026-05-01 09:49:59 -07:00
cli fix(compression): include system prompt + tool schemas in token estimates (#18265) 2026-04-30 23:03:54 -07:00
cron fix(curator): rewrite cron job skill refs after consolidation (#18253) 2026-04-30 23:04:50 -07:00
e2e fix(gateway): coerce plaintext "restart gateway" DMs to /restart 2026-04-28 01:40:28 -07:00
environments/benchmarks
fakes
gateway fix(gateway): honor MATRIX_HOME_ROOM in onboarding 2026-04-30 23:13:34 -07:00
hermes_cli feat: /goal — persistent cross-turn goals (Ralph loop) (#18262) 2026-04-30 23:10:20 -07:00
hermes_state fix(resume): redirect --resume to the descendant that actually holds the messages 2026-04-24 03:04:42 -07:00
honcho_plugin feat(honcho): explain why when honcho_profile returns an empty card 2026-04-27 12:37:33 -07:00
integration fix(discord): strip RTP padding before DAVE/Opus decode (#11267) 2026-04-16 16:50:15 -07:00
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 feat(kanban): durable multi-profile collaboration board (#17805) 2026-04-30 13:36:47 -07:00
run_agent fix: lazy session creation — defer DB row until first message (#18370) 2026-05-01 18:39:12 +05:30
skills test(openclaw-migration): cover alias reverse-lookup for real OpenClaw schema 2026-04-28 04:58:13 -07:00
stress feat(kanban): durable multi-profile collaboration board (#17805) 2026-04-30 13:36:47 -07:00
tools fix: coerce show_reasoning and guard_agent_created config bools 2026-04-30 20:40:46 -07:00
tui_gateway fix(plugins): await async handlers in CLI and TUI dispatch 2026-04-30 19:56:18 -07:00
website fix(website): auto-wrap ASCII-art code blocks in generated skill pages (#16497) 2026-04-27 03:38:39 -07:00
__init__.py
conftest.py fix(ci): stabilize main test suite regressions (#17660) 2026-04-29 23:18:55 -07:00
run_interrupt_test.py
test_account_usage.py feat(account-usage): add per-provider account limits module 2026-04-21 01:56:35 -07:00
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 security(runtime_provider): close OLLAMA_API_KEY substring-leak sweep miss (#13522) 2026-04-21 06:06:16 -07:00
test_batch_runner_checkpoint.py test: regression coverage for checkpoint dedup and inf/nan coercion 2026-04-24 14:32:21 -07:00
test_cli_file_drop.py fix(tui): improve macOS paste and shortcut parity 2026-04-21 08:00:00 -07:00
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_constants.py
test_hermes_logging.py fix(logging): attach gateway log after cli init 2026-04-26 19:01:26 -07:00
test_hermes_state.py fix(state): include finish_reason in conversation replay 2026-04-30 20:40:28 -07:00
test_honcho_client_config.py
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_ipv4_preference.py
test_mcp_serve.py
test_mini_swe_runner.py fix(kimi): omit temperature entirely for Kimi/Moonshot models (#13157) 2026-04-20 12:23:05 -07:00
test_minimax_model_validation.py fix(models): validate MiniMax models against static catalog (#12611, #12460, #12399, #12547) 2026-04-19 22:44:47 -07:00
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(tests): attach caplog to specific logger in 3 order-dependent tests (#11453) 2026-04-17 00:20:40 -07:00
test_project_metadata.py build(deps): add qrcode to dingtalk + feishu extras (parity with messaging) (#11627) 2026-04-17 13:31:53 -07:00
test_retry_utils.py
test_sql_injection.py
test_subprocess_home_isolation.py
test_timezone.py test: speed up slow tests (backoff + subprocess + IMDS network) (#11797) 2026-04-17 14:21:22 -07:00
test_toolset_distributions.py
test_toolsets.py feat(discord): split discord_server into discord + discord_admin tools 2026-04-25 04:50:14 -07:00
test_trajectory_compressor.py fix(kimi): omit temperature entirely for Kimi/Moonshot models (#13157) 2026-04-20 12:23:05 -07:00
test_trajectory_compressor_async.py fix(kimi): omit temperature entirely for Kimi/Moonshot models (#13157) 2026-04-20 12:23:05 -07:00
test_transform_tool_result_hook.py test: stop testing mutable data — convert change-detectors to invariants (#13363) 2026-04-20 23:20:33 -07:00
test_tui_gateway_server.py fix(approval): harden YOLO mode env parsing against quoted-bool strings 2026-04-30 20:37:37 -07:00
test_utils_truthy_values.py
test_yuanbao_integration.py yuanbao platform (#16298) 2026-04-26 18:50:49 -07:00
test_yuanbao_markdown.py yuanbao platform (#16298) 2026-04-26 18:50:49 -07:00
test_yuanbao_pipeline.py yuanbao platform (#16298) 2026-04-26 18:50:49 -07:00
test_yuanbao_proto.py yuanbao platform (#16298) 2026-04-26 18:50:49 -07:00