Commit Graph
78 Commits
Author SHA1 Message Date
Mikei386 5f793020b0 Adopt persistent Portainer volume explicitly 2026-09-01 11:07:11 +02:00
Mikei386 16ac177782 Make gateway-bound UIs reproducible 2026-09-01 10:54:22 +02:00
Mikei386 7e14da77f9 Restore vision projector for medium profile 2026-09-01 09:19:20 +02:00
Mikei386 c031fd2c55 Remove obsolete experimental profile 2026-09-01 09:04:45 +02:00
Mikei386 91fbb276bd Remove obsolete review model service 2026-09-01 08:54:33 +02:00
Mikei386 b2ea53c383 Add global research verification policy 2026-08-31 22:35:09 +02:00
Mikei386 21d10db890 Merge remote-tracking branch 'origin/main' into codex/cache24-sync
# Conflicts:
#	.env.example
#	ATHENA.md
#	README.md
#	compose.yaml
#	config/install.env.example
#	docs/ARCHITECTURE.md
#	docs/RECOVERY.md
#	router/ai_profile_router.py
2026-08-31 21:17:18 +02:00
Mikei386 211ede9fc5 Update llama runtime and isolate background reviews 2026-08-31 21:11:17 +02:00
Mikei386 7e36f1dbb7 Fix Thinking Off handling 2026-08-31 08:15:27 +02:00
Mikei386 0fa9a34886 Increase llama prompt cache to 24 GiB 2026-08-30 22:33:37 +02:00
Mikei386 8be1cd6a6f Default Athena profiles to one inference slot 2026-08-30 22:11:55 +02:00
Mikei386 014583e7f6 Enable benchmarked two-slot medium profile 2026-08-30 22:11:26 +02:00
Mikei386 5b78d12112 Default reasoning effort to medium 2026-08-30 22:11:26 +02:00
Mikei386 27d2bb1b4b Tune prefill batching across Qwen profiles 2026-08-30 22:11:26 +02:00
Mikei386 9c10b0ab88 Tune Qwen medium prefill batching 2026-08-30 22:11:26 +02:00
Mikei386 c27636ac34 Add local FLUX image editing 2026-08-30 22:11:26 +02:00
Mikei386 0b927d47b9 Simplify Athena runtime and document current architecture 2026-08-30 22:11:26 +02:00
Mikei386 a41d6dc28c Enable benchmarked two-slot medium profile 2026-08-30 20:54:22 +02:00
Mikei386 db3719af7a Default reasoning effort to medium 2026-08-30 20:08:32 +02:00
Mikei386 2661553e20 Tune prefill batching across Qwen profiles 2026-08-30 19:50:40 +02:00
Mikei386 edb8b2868f Tune Qwen medium prefill batching 2026-08-30 18:39:17 +02:00
Mikei386 6af25cf30c Add local FLUX image editing 2026-08-30 10:07:40 +02:00
Mikei386 c6517ee137 Simplify Athena runtime and document current architecture 2026-08-30 08:45:52 +02:00
Mikei386 ab671a6396 simplify Athena runtime and centralize MCP management 2026-08-26 09:57:38 +02:00
Mikei386 d1eed44341 Cap runaway chat generations in router 2026-08-26 07:01:04 +02:00
Mikei386 896c12193e Replace compression sidecar with Hermes micro-compaction 2026-08-26 06:18:51 +02:00
Mikei386 aaadc57c07 Harden and demote experimental Hermes compressor 2026-08-26 01:40:38 +02:00
Mikei386 99285fe81a Pin compressor to RTX 3060 device 2026-08-26 00:48:10 +02:00
Mikei386 43d9903d13 Add dedicated Hermes compression model 2026-08-26 00:45:32 +02:00
Mikei386 069da8b4f0 Simplify Athena stack and recovery 2026-08-25 22:27:26 +02:00
Mikei386 c25e57af57 Limit prompt cache reuse to text-only profiles 2026-08-25 19:26:48 +02:00
Mikei386 d921dfaf69 Enable cross-chat llama prompt cache reuse 2026-08-25 19:19:49 +02:00
Mikei386 ba12aaaac6 Build Hermes MCP patches into managed image 2026-08-25 16:41:12 +02:00
Mikei386 a984ce1892 Refresh MCP tools in Hermes API agents 2026-08-25 15:33:59 +02:00
Athena Operator 1056784642 Add managed Deemix MCP integration 2026-08-25 10:26:37 +02:00
Mikei386 71775891b4 Add Hermes WebUI and Athena operator skill 2026-08-24 21:50:23 +02:00
Mikei386 335c9a8501 fix: prevent Qwen reasoning and tool loops 2026-08-24 20:06:26 +02:00
Mikei386 8ef079d40e Fail closed when Hermes local config is unreadable 2026-08-24 17:15:15 +02:00
Mikei386 348ca1324e Add Hermes Agent as reproducible second client 2026-08-24 17:00:39 +02:00
Mikei386 7978a4ee56 feat: standardize long-running tool workflows 2026-08-24 15:02:25 +02:00
Mikei386 0a5da6e5f1 feat: add bounded marketplace research 2026-08-24 13:54:17 +02:00
Mikei386 308b8a4d1f fix: bound broad tool workflows 2026-08-24 13:29:41 +02:00
Mikei386 5db73d0a92 feat: open Athena tool architecture 2026-08-24 12:46:33 +02:00
Mikei386 5cb6079918 feat: harden Qwen agentic tool orchestration 2026-08-24 10:47:13 +02:00
Mikei386 4ac0c479c4 fix(openwebui): synthesize after six tool calls 2026-08-24 08:43:14 +02:00
Mikei386 50c37b09bb fix(openwebui): bound calls and force prose synthesis 2026-08-24 08:33:44 +02:00
Mikei386 4d4eb0b8d8 fix(openwebui): pin migrated database-compatible base 2026-08-24 08:14:27 +02:00
Mikei386 81a563372d fix(openwebui): guarantee answer after tool budget 2026-08-24 08:06:34 +02:00
Mikei386 c402ea79f7 feat(vpn): expose Athena services directly over WireGuard 2026-08-24 07:33:16 +02:00
Mikei386 e24839bfe1 fix(tools): harden OpenWebUI tool workflows 2026-08-24 00:40:32 +02:00