hermes-agent/plugins
Brooklyn Nicholson f0ed0aebbc feat(kanban): expose the per-task reasoning effort over REST
Carries the new column through create, PATCH, and bulk. Clearing is an
explicit clear_reasoning_effort flag rather than a null, because a null in a
PATCH body means "field not sent", not "set to NULL" — the same shape the
model override already uses, and the reason "none" can stay a real value.

Tests cover normalization, the depth-survives-a-model-clear invariant, both
spawn-argv branches, and the REST round-trip. One asserts the worker CLI
actually accepts the --reasoning flag the dispatcher emits: a spawn arg no
parser accepts would fail every dispatch while every unit test stayed green.
2026-08-01 16:10:03 -05:00
..
browser fix(desktop): honest browser-backend readiness + explicit backend activation + full OpenAI TTS voice/model options 2026-07-28 23:52:49 -07:00
context_engine
…
cron_providers fix(cron): set headers for chronos JWKS requests 2026-07-31 10:17:30 -04:00
dashboard_auth fix(dashboard): set headers for Nous JWKS requests 2026-07-31 10:17:30 -04:00
disk-cleanup fix(disk-cleanup): re-validate stale test entries and protect new dirs from sweep 2026-07-31 22:36:04 -07:00
google_meet
…
hermes-achievements
…
image_gen
…
kanban feat(kanban): expose the per-task reasoning effort over REST 2026-08-01 16:10:03 -05:00
memory fix(hindsight): create embedded profile env file owner-only (0600) 2026-07-31 22:39:34 -07:00
model-providers Revert "remove Vercel AI Gateway and Vercel Sandbox (#33067)" 2026-07-29 19:48:37 -07:00
observability Reapply "feat(observability): integrate NeMo Relay runtime and shared metrics" 2026-07-27 21:10:51 -07:00
platforms refactor: simplify pairing check return and drop over-defensive getattr 2026-08-01 12:38:38 +05:30
security-guidance
…
spotify
…
teams_pipeline
…
video_gen
…
web
…
__init__.py
…
plugin_utils.py
…