hermes-agent/tests/plugins
kshitijk4poor 67df958dbe fix(custom-provider): emit reasoning_effort at the live profile path
PR #57601's original branch added a top-level reasoning_effort emit to the
LEGACY build_kwargs path (agent/transports/chat_completions.py), but
provider=custom resolves to CustomProfile (plugins/model-providers/custom/),
so chat_completion_helpers takes the profile path and returns early — the
added branch was unreachable dead code for every custom endpoint.

Move the fix to its real site, CustomProfile.build_api_kwargs_extras(), and
follow the DeepSeek/Zai profile precedent:
  - disabled            -> extra_body.think = False (unchanged)
  - enabled + effort    -> TOP-LEVEL reasoning_effort (the OpenAI-compatible
                           format GLM-5.2/ARK expect), passed through verbatim
                           incl. max/xhigh
  - enabled + no effort -> omit, so the endpoint's server default applies
                           (avoids silently forcing 'medium' as the original
                           branch did)

Deliberately does NOT force think=True on enable — that flag is Ollama-only
and risks a 400 on GLM/vLLM endpoints that don't recognize it; thinking is
already server-default-on for these backends.

Verified end-to-end through the real profile dispatch (temp HERMES_HOME):
custom+high -> reasoning_effort=high; custom+max -> reasoning_effort=max;
custom+none -> think=False; custom+unset -> nothing; num_ctx composes.

Adds tests/plugins/model_providers/test_custom_profile.py (13 cases).
Addresses the custom-provider half of #55276.

Co-authored-by: huanshan5195 <huanshan5195@users.noreply.github.com>
2026-07-04 14:19:44 +05:30
..
browser
dashboard_auth feat(dashboard_auth): support confidential clients (client_secret) in self-hosted OIDC (#55344) 2026-06-30 13:32:51 +10:00
image_gen fix(image-gen): route local-input credential guard through one shared chokepoint + cover xai (#57698) 2026-07-03 18:47:53 +05:30
memory fix(memory/holographic): sanitize FTS5 queries for natural-language recall 2026-06-30 15:55:11 -07:00
model_providers fix(custom-provider): emit reasoning_effort at the live profile path 2026-07-04 14:19:44 +05:30
platforms/photon fix(photon): correlate tapbacks to bot message context 2026-06-27 00:51:34 -07:00
transcription
tts
video_gen fix(xai): route video-gen local inputs through the shared read guard 2026-07-03 18:47:53 +05:30
web revert(web): remove keyless Parallel search fallback (#46350) 2026-06-14 16:47:57 -07:00
__init__.py
test_achievements_plugin.py
test_chronos_cron.py fix(cron): avoid provider package shadowing core cron 2026-06-23 23:39:22 -07:00
test_chronos_verify.py fix(cron): avoid provider package shadowing core cron 2026-06-23 23:39:22 -07:00
test_discord_runtime_failure.py
test_disk_cleanup_plugin.py fix: protect cron output root from cleanup 2026-07-01 15:42:04 +05:30
test_google_meet_audio.py
test_google_meet_node.py
test_google_meet_plugin.py
test_google_meet_realtime.py
test_hindsight_health_grace_timeout.py feat(hindsight): configurable embedded daemon health grace timeout (#50341) 2026-06-21 12:20:53 -07:00
test_hindsight_root_guard.py fix(hindsight): skip local_embedded daemon when running as root 2026-06-21 11:47:02 -07:00
test_kanban_attachments.py
test_kanban_dashboard_plugin.py fix(security): sanitize kanban markdown html 2026-06-21 13:10:17 -07:00
test_kanban_worker_runs.py
test_langfuse_plugin.py test(langfuse): pin exact surviving key in turn-isolation test 2026-06-18 13:00:01 +05:30
test_nemo_relay_plugin.py
test_plugin_dashboard_auth_contract.py
test_raft_check_fn_silent.py fix(plugins): silence raft check_fn log spam for users without raft CLI 2026-06-19 17:12:58 -07:00
test_retaindb_plugin.py
test_security_guidance_plugin.py
test_teams_pipeline_plugin.py fix(teams-pipeline): reject dot-only recording display_name 2026-07-01 02:03:48 -07:00