s010mn 221cd60242 feat: add reasoning_effort support to ollama-cloud provider ... Map Hermes xhigh→max to unlock DeepSeek V4's 'Max thinking' tier through Ollama Cloud's OpenAI-compatible /v1/chat/completions endpoint. low/medium/high pass through unchanged; disabled/none suppress reasoning entirely. Empirically confirmed: reasoning_effort:max produces ~2.5× more thinking tokens than high on deepseek-v4-pro:cloud (1576 vs 642).		2026-06-23 11:51:43 -07:00
..
browser
context_engine
cron	feat(cron,gateway): NAS-JWT fire verifier + /api/cron/fire webhook (Chronos)	2026-06-18 14:46:33 +10:00
dashboard_auth
disk-cleanup	🐛 fix(disk-cleanup): avoid brittle sweep review issues	2026-06-15 05:25:27 -07:00
google_meet	fix: prevent TUI gateway stdin EOF crash across all TUI-context subprocess calls	2026-06-08 22:46:57 -07:00
hermes-achievements	fix(security): restrict dashboard plugin backend import to bundled plugins (#43719)	2026-06-22 17:51:37 +05:30
image_gen	feat(image-gen): add image-to-image / editing to image_generate (#48705)	2026-06-18 22:13:07 -07:00
kanban	fix(security): sanitize kanban markdown html	2026-06-21 13:10:17 -07:00
memory	feat(memory): Honcho OAuth connect — desktop and CLI flows + token refresh (#44335)	2026-06-22 19:16:47 -05:00
model-providers	feat: add reasoning_effort support to ollama-cloud provider	2026-06-23 11:51:43 -07:00
observability	fix(langfuse): bound _TRACE_STATE growth from non-finalizing turns	2026-06-18 12:59:41 +05:30
platforms	fix(slack): report ext-matched audio mimetype for rerouted voice clips	2026-06-23 14:44:12 +05:30
security-guidance
spotify
teams_pipeline
video_gen
web	docs(xai): update default model references to grok-build-0.1	2026-06-16 11:50:17 -07:00
__init__.py
plugin_utils.py