hermes-agent/plugins
Teknium fe5e7799f2 refactor: fold tailored intents guidance into the connect classifier
The cherry-picked #79448 predated #85049's _classify_connect_exception,
so it added a parallel PrivilegedIntentsRequired branch ahead of the
classifier (plus its own _is_privileged_intents_required detector).
Fold the tailored guidance into the classifier's existing intents arm
instead: one classification path, one error code (discord_intents_required),
and the message now names exactly the intents Hermes requested (Message
Content always; Server Members only when username/role allowlists need it).
Wizard callout, docs corrections, and tests from #79448 kept as-is.
2026-08-13 00:10:30 -07:00
..
browser feat(browser): integrate Browser Use CLI 3.0 2026-08-10 10:45:44 -07:00
context_engine
…
cron_providers
…
dashboard_auth
…
disk-cleanup
…
google_meet
…
hermes-achievements
…
image_gen
…
kanban fix(kanban): move descendant invalidation to domain layer, make it non-silent 2026-08-10 12:43:46 -07:00
memory
…
model-providers Port from PrimeIntellect-ai/prime-agent#1258: derive OpenRouter reasoning support and effort levels from catalog metadata 2026-08-12 19:44:32 -07:00
observability fix(observability): parent marks to the live turn scope, not the session 2026-08-12 19:20:03 -07:00
platforms refactor: fold tailored intents guidance into the connect classifier 2026-08-13 00:10:30 -07:00
security-guidance plugins: add security-guidance — pattern-matched warnings on dangerous code writes (#33131) 2026-05-27 02:07:21 -07:00
spotify
…
teams_pipeline
…
video_gen
…
web
…
__init__.py
…
plugin_utils.py
…