hermes-agent/tests/gateway
Teknium e97c0cb578
fix: replace hardcoded ~/.hermes paths with get_hermes_home() for profile support
* feat: GPT tool-use steering + strip budget warnings from history

Two changes to improve tool reliability, especially for OpenAI GPT models:

1. GPT tool-use enforcement prompt: Adds GPT_TOOL_USE_GUIDANCE to the
   system prompt when the model name contains 'gpt' and tools are loaded.
   This addresses a known behavioral pattern where GPT models describe
   intended actions ('I will run the tests') instead of actually making
   tool calls. Inspired by similar steering in OpenCode (beast.txt) and
   Cline (GPT-5.1 variant).

2. Budget warning history stripping: Budget pressure warnings injected by
   _get_budget_warning() into tool results are now stripped when
   conversation history is replayed via run_conversation(). Previously,
   these turn-scoped signals persisted across turns, causing models to
   avoid tool calls in all subsequent messages after any turn that hit
   the 70-90% iteration threshold.

* fix: replace hardcoded ~/.hermes paths with get_hermes_home() for profile support

Prep for the upcoming profiles feature — each profile is a separate
HERMES_HOME directory, so all paths must respect the env var.

Fixes:
- gateway/platforms/matrix.py: Matrix E2EE store was hardcoded to
  ~/.hermes/matrix/store, ignoring HERMES_HOME. Now uses
  get_hermes_home() so each profile gets its own Matrix state.

- gateway/platforms/telegram.py: Two locations reading config.yaml via
  Path.home()/.hermes instead of get_hermes_home(). DM topic thread_id
  persistence and hot-reload would read the wrong config in a profile.

- tools/file_tools.py: Security path for hub index blocking was
  hardcoded to ~/.hermes, would miss the actual profile's hub cache.

- hermes_cli/gateway.py: Service naming now uses the profile name
  (hermes-gateway-coder) instead of a cryptic hash suffix. Extracted
  _profile_suffix() helper shared by systemd and launchd.

- hermes_cli/gateway.py: Launchd plist path and Label now scoped per
  profile (ai.hermes.gateway-coder.plist). Previously all profiles
  would collide on the same plist file on macOS.

- hermes_cli/gateway.py: Launchd plist now includes HERMES_HOME in
  EnvironmentVariables — was missing entirely, making custom
  HERMES_HOME broken on macOS launchd (pre-existing bug).

- All launchctl commands in gateway.py, main.py, status.py updated
  to use get_launchd_label() instead of hardcoded string.

Test fixes: DM topic tests now set HERMES_HOME env var alongside
Path.home() mock. Launchd test uses get_launchd_label() for expected
commands.
2026-03-28 13:51:08 -07:00
..
__init__.py test: reorganize test structure and add missing unit tests 2026-02-26 03:20:08 +03:00
test_agent_cache.py fix(gateway): fingerprint full auth token in agent cache signature (#3247) 2026-03-26 13:19:43 -07:00
test_allowlist_startup_check.py fix(gateway): include per-platform ALLOW_ALL and SIGNAL_GROUP in startup allowlist check (#3313) 2026-03-26 18:23:49 -07:00
test_api_server.py feat(api-server): add /v1/health alias for OpenAI compatibility (#3572) 2026-03-28 13:32:39 -07:00
test_api_server_jobs.py fix(api-server): harden jobs API — input limits, field whitelist, startup check, tests 2026-03-22 04:18:18 -07:00
test_api_server_toolset.py fix: add explicit hermes-api-server toolset for API server platform (#3304) 2026-03-26 18:02:26 -07:00
test_approve_deny_commands.py fix(gateway): replace bare text approval with /approve and /deny commands (#2002) 2026-03-18 16:58:20 -07:00
test_async_memory_flush.py feat(gateway): proactive async memory flush on session expiry 2026-03-07 11:27:50 -08:00
test_background_command.py fix(gateway): track background task references in GatewayRunner (#3254) 2026-03-26 14:33:48 -07:00
test_background_process_notifications.py fix(gateway): persist watcher metadata in checkpoint for crash recovery (#1706) 2026-03-17 03:52:15 -07:00
test_base_topic_sessions.py fix(gateway): isolate telegram forum topic sessions 2026-03-11 09:15:34 +01:00
test_channel_directory.py fix: finish HERMES_HOME path cleanup 2026-03-13 21:35:07 -07:00
test_config.py feat: support ignoring unauthorized gateway DMs (#1919) 2026-03-18 04:06:08 -07:00
test_config_cwd_bridge.py refactor(cli): implement approval locking mechanism to serialize concurrent requests 2026-03-13 23:59:18 -07:00
test_delivery.py fix: salvage gateway dedup and executor cleanup from PR #993 2026-03-14 11:03:20 -07:00
test_dingtalk.py feat(gateway): add DingTalk platform adapter (#1685) 2026-03-17 03:04:58 -07:00
test_discord_bot_filter.py feat(discord): add DISCORD_ALLOW_BOTS config for bot message filtering (inspired by openclaw) 2026-03-09 02:20:57 -07:00
test_discord_document_handling.py feat(discord): add document caching and text-file injection (#2503) 2026-03-22 07:38:14 -07:00
test_discord_free_response.py feat(discord): auto-thread on @mention + skip mention in bot threads 2026-03-15 07:59:55 -07:00
test_discord_imports.py fix: defer discord adapter annotations 2026-03-14 09:32:05 -07:00
test_discord_media_metadata.py feat(discord): add /thread command, auto_thread config, and media metadata fix (#1178) 2026-03-13 08:52:54 -07:00
test_discord_opus.py fix: add macOS Homebrew Opus fallback and fix shutdown dict iteration 2026-03-14 14:27:21 +03:00
test_discord_send.py fix: align salvaged Discord send test mock with current slash-command API 2026-03-14 21:44:50 -07:00
test_discord_slash_commands.py fix(discord): properly route slash event handling in threads 2026-03-22 04:25:19 -07:00
test_discord_system_messages.py fix(discord): ignore system messages in on_message handler (#2618) 2026-03-23 06:50:09 -07:00
test_discord_thread_persistence.py fix(discord): persist thread participation across gateway restarts 2026-03-17 02:26:34 -07:00
test_dm_topics.py fix: replace hardcoded ~/.hermes paths with get_hermes_home() for profile support 2026-03-28 13:51:08 -07:00
test_document_cache.py fix(security): patch path traversal, size bypass, and prompt injection in document processing 2026-02-27 11:53:46 -05:00
test_email.py fix: verify SMTP TLS in send_message_tool 2026-03-14 06:31:52 -07:00
test_extract_local_files.py feat: auto-detect local file paths in gateway responses for native media delivery (#1640) 2026-03-17 01:47:34 -07:00
test_flush_memory_stale_guard.py fix(gateway): silence background agent terminal output (#3297) 2026-03-26 17:40:31 -07:00
test_gateway_shutdown.py fix(gateway): track background task references in GatewayRunner (#3254) 2026-03-26 14:33:48 -07:00
test_homeassistant.py fix: Home Assistant event filtering now closed by default (#1169) 2026-03-13 07:40:38 -07:00
test_honcho_lifecycle.py fix(honcho): isolate session routing for multi-user gateway (#1500) 2026-03-16 00:23:47 -07:00
test_hooks.py test: strengthen assertions across 7 test files (batch 1) 2026-03-05 18:39:37 -08:00
test_interrupt_key_match.py test(gateway): cover photo burst interrupt regressions 2026-03-15 03:50:45 -07:00
test_matrix.py fix(matrix): harden e2ee access-token handling (#3562) 2026-03-28 12:13:35 -07:00
test_mattermost.py fix(tests): resolve all consistently failing tests 2026-03-22 05:58:26 -07:00
test_media_download_retry.py fix(gateway): add media download retry to Mattermost, Slack, and base cache (#3323) 2026-03-26 19:33:18 -07:00
test_media_extraction.py fix(gateway): prevent TTS voice messages from accumulating across turns 2026-02-28 03:38:27 -05:00
test_mirror.py fix(gateway): isolate telegram forum topic sessions 2026-03-11 09:15:34 +01:00
test_pairing.py test: strengthen assertions across 7 test files (batch 1) 2026-03-05 18:39:37 -08:00
test_pii_redaction.py fix(privacy): skip PII redaction on Discord/Slack (mentions need real IDs) 2026-03-16 05:58:34 -07:00
test_plan_command.py fix: save /plan output in workspace (#1381) 2026-03-14 21:28:51 -07:00
test_platform_base.py fix: complete send_message MEDIA delivery salvage 2026-03-14 04:02:03 -07:00
test_platform_reconnect.py feat: auto-reconnect failed gateway platforms with exponential backoff (#2584) 2026-03-22 23:48:24 -07:00
test_queue_consumption.py fix(gateway): process /queue'd messages after agent completion (#2469) 2026-03-22 04:56:13 -07:00
test_reasoning_command.py fix: MCP toolset resolution for runtime and config (#3252) 2026-03-26 13:39:41 -07:00
test_resume_command.py fix(honcho): isolate session routing for multi-user gateway (#1500) 2026-03-16 00:23:47 -07:00
test_retry_replacement.py test: lock retry replacement semantics 2026-03-14 21:19:22 -07:00
test_retry_response.py test(gateway): add regression test for /retry response fix 2026-03-10 23:34:52 -07:00
test_run_progress_topics.py fix(gateway): scope progress thread fallback to Slack only (salvage #3414) (#3488) 2026-03-27 22:37:53 -07:00
test_runner_fatal_adapter.py feat: auto-reconnect failed gateway platforms with exponential backoff (#2584) 2026-03-22 23:48:24 -07:00
test_runner_startup_failures.py fix(gateway): restart on retryable startup failures (#1517) 2026-03-16 05:26:31 -07:00
test_send_image_file.py feat(telegram): auto-discover fallback IPs via DoH when api.telegram.org is unreachable (#3376) 2026-03-27 04:03:13 -07:00
test_send_retry.py fix(gateway): retry transient send failures and notify user on exhaustion (#3288) 2026-03-26 17:37:10 -07:00
test_session.py fix: gateway token double-counting — use absolute set instead of increment (#3317) 2026-03-26 19:13:07 -07:00
test_session_env.py fix: preserve thread context for cronjob deliver=origin 2026-03-15 06:57:00 -07:00
test_session_hygiene.py fix(gateway): preserve transcript on /compress and hygiene compression (salvage #3516) (#3556) 2026-03-28 12:23:43 -07:00
test_session_info.py feat(gateway): surface session config on /new, /reset, and auto-reset (#3321) 2026-03-26 19:27:58 -07:00
test_session_race_guard.py fix(gateway): track background task references in GatewayRunner (#3254) 2026-03-26 14:33:48 -07:00
test_session_reset_notify.py feat(gateway): notify users when session auto-resets (#2519) 2026-03-22 09:33:39 -07:00
test_signal.py fix(tests): resolve all consistently failing tests 2026-03-22 05:58:26 -07:00
test_slack.py fix(gateway/slack): send progress messages to correct thread (#3063) 2026-03-25 15:51:15 -07:00
test_sms.py feat: add SMS (Twilio) platform adapter 2026-03-17 03:14:53 -07:00
test_sse_agent_cancel.py fix(api-server): cancel orphaned agent + true interrupt on SSE disconnect (salvage #3399) (#3427) 2026-03-27 11:33:19 -07:00
test_ssl_certs.py fix(gateway): SSL certificate auto-detection for NixOS and non-standard systems 2026-03-15 23:04:34 -07:00
test_status.py fix(gateway): detect script-style gateway processes for --replace 2026-03-18 03:12:59 -07:00
test_status_command.py feat: add route-aware pricing estimates (#1695) 2026-03-17 03:44:44 -07:00
test_sticker_cache.py test: add unit tests for 8 untested modules (batch 3) (#191) 2026-03-01 05:28:12 -08:00
test_stt_config.py fix: restore local STT fallback for gateway voice notes 2026-03-15 21:51:40 -07:00
test_telegram_conflict.py feat(telegram): auto-discover fallback IPs via DoH when api.telegram.org is unreachable (#3376) 2026-03-27 04:03:13 -07:00
test_telegram_documents.py feat(telegram): auto-discover fallback IPs via DoH when api.telegram.org is unreachable (#3376) 2026-03-27 04:03:13 -07:00
test_telegram_format.py feat(telegram): auto-discover fallback IPs via DoH when api.telegram.org is unreachable (#3376) 2026-03-27 04:03:13 -07:00
test_telegram_network.py feat(telegram): auto-discover fallback IPs via DoH when api.telegram.org is unreachable (#3376) 2026-03-27 04:03:13 -07:00
test_telegram_network_reconnect.py feat(telegram): auto-discover fallback IPs via DoH when api.telegram.org is unreachable (#3376) 2026-03-27 04:03:13 -07:00
test_telegram_photo_interrupts.py test(gateway): cover photo burst interrupt regressions 2026-03-15 03:50:45 -07:00
test_telegram_reply_mode.py feat(telegram): auto-discover fallback IPs via DoH when api.telegram.org is unreachable (#3376) 2026-03-27 04:03:13 -07:00
test_telegram_text_batching.py fix(telegram): aggregate split text messages before dispatching (#1674) 2026-03-17 02:49:57 -07:00
test_telegram_thread_fallback.py fix(telegram): fall back to no thread_id on 'Message thread not found' (#3390) 2026-03-27 06:07:28 -07:00
test_title_command.py fix(test): add missing _voice_mode attr to GatewayRunner test stubs 2026-03-14 14:27:20 +03:00
test_transcript_offset.py fix(gateway): use filtered history length for transcript message extraction 2026-03-04 21:34:40 +03:00
test_unauthorized_dm_behavior.py feat: support ignoring unauthorized gateway DMs (#1919) 2026-03-18 04:06:08 -07:00
test_update_command.py fix(gateway): fall back to sys.executable -m hermes_cli.main when hermes not on PATH 2026-03-14 12:15:51 -07:00
test_verbose_command.py feat: config-gated /verbose command for messaging gateway (#3262) 2026-03-26 14:41:04 -07:00
test_voice_command.py fix(voice): enable TTS voice reply when streaming is active (#2322) 2026-03-21 08:08:37 -07:00
test_webhook_adapter.py feat(gateway): add webhook platform adapter for external event triggers 2026-03-20 06:33:36 -07:00
test_webhook_integration.py feat(gateway): add webhook platform adapter for external event triggers 2026-03-20 06:33:36 -07:00
test_whatsapp_connect.py fix(gateway): restart on whatsapp bridge child exit (#2334) 2026-03-21 09:38:52 -07:00
test_whatsapp_reply_prefix.py feat: OpenAI-compatible API server + WhatsApp configurable reply prefix (#1756) 2026-03-17 10:44:37 -07:00