Commit Graph
100 Commits
Author SHA1 Message Date
Mikei386 e30f4f024c Fix Athena recovery and installation consistency 2026-09-01 10:19:13 +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 548f6643fd Benchmark Dirk Qwen3.8 against production 2026-09-01 08:44:55 +02:00
Mikei386 78096c9027 Pin and verify Dirk model artifacts 2026-09-01 06:24:59 +02:00
Mikei386 ee28272999 Prepare isolated Dirk Qwen3.8 benchmark 2026-09-01 06:18:39 +02:00
Mikei386 b2ea53c383 Add global research verification policy 2026-08-31 22:35:09 +02:00
Mikei386 82a1809423 Use unambiguous Hermes reasoning-off values 2026-08-31 21:55:59 +02:00
Mikei386 3fbcc6ee2c Disable reasoning by default across clients 2026-08-31 21:41:50 +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 a15bb2a0cf Document current Athena services 2026-08-30 22:16:33 +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 40e73d82a8 Add Athena GPU allocation map 2026-08-30 22:11:26 +02:00
Mikei386 d71f2ebbfe Show Qwen profile contexts in architecture map 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 9bc7d9803a Document Athena slot toggle 2026-08-30 21:59:44 +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 b18bc8964a Add Athena GPU allocation map 2026-08-30 09:06:46 +02:00
Mikei386 60d91fc7a8 Show Qwen profile contexts in architecture map 2026-08-30 09:03:12 +02:00
Mikei386 c6517ee137 Simplify Athena runtime and document current architecture 2026-08-30 08:45:52 +02:00
Mikei386 aab9579b06 Move Deemix MCP to standalone repository 2026-08-28 22:44:02 +02:00
Mikei386 c721db47d0 Move Deemix MCP to standalone repository 2026-08-28 22:42:55 +02:00
Mikei386 da3571ef9f Move STRATO MCP to standalone repository 2026-08-28 19:56:39 +02:00
Mikei386 79be9e7f40 Move STRATO MCP to standalone repository 2026-08-28 19:56:04 +02:00
Mikei386 da6e762d72 Harden ARR MCP tool surface and installer 2026-08-28 13:05:21 +02:00
Mikei386 0008dd3b3e Add read-only STRATO DNS MCP prototype 2026-08-27 22:18:59 +02:00
Mikei386 d570a06911 Add standalone Unraid ARR MCP package 2026-08-27 21:49:01 +02:00
Mikei386 588f24894d add autonomous GitHub MCP installer 2026-08-26 12:46:48 +02:00
Mikei386 9ae7d22618 fix MCPHub group publishing and recovery 2026-08-26 11:42:39 +02:00
Mikei386 167448d778 publish MCPs through a filtered Hermes group 2026-08-26 11:34:15 +02:00
Mikei386 2595bab17b let Hermes manage MCPHub through its API 2026-08-26 11:28:51 +02:00
Mikei386 bc902261b9 simplify MCPHub extensions and restore Hermes web tools 2026-08-26 11:08:47 +02:00
Mikei386 9455a79dc2 harden MCPHub deployer credential boundary 2026-08-26 10:18:55 +02:00
Mikei386 ab671a6396 simplify Athena runtime and centralize MCP management 2026-08-26 09:57:38 +02:00
Mikei386 104c9904a5 Stream llama responses without proxy buffering 2026-08-26 07:06:03 +02:00
Mikei386 d1eed44341 Cap runaway chat generations in router 2026-08-26 07:01:04 +02:00
Mikei386 400de54ff9 Bound Hermes context compression latency 2026-08-26 06:54:57 +02:00
Mikei386 a702353134 Make MCPHub skill reloadable after compaction 2026-08-26 06:44:29 +02:00
Mikei386 5ed1f571a1 Make MCPHub deployments deterministic 2026-08-26 06:43:18 +02:00
Mikei386 640ef087ac Hide Hermes reasoning output by default 2026-08-26 06:28:36 +02:00
Mikei386 896c12193e Replace compression sidecar with Hermes micro-compaction 2026-08-26 06:18:51 +02:00
Mikei386 438bd34b72 Keep experimental compressor stopped by default 2026-08-26 01:42:14 +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 e872829b11 Route Athena operator through MCPHub 2026-08-26 00:25:44 +02:00
Mikei386 c0c1c6db66 Add Hermes MCPHub deployment skill 2026-08-26 00:06:29 +02:00
Mikei386 3ab7c57043 Document Hermes migration to Unraid 2026-08-25 23:52:55 +02:00
Mikei386 5087048e0c Add official Hermes Agent Unraid template 2026-08-25 23:32:18 +02:00
Mikei386 24ac244ff6 Document DockerMan-managed MCPHub deployment 2026-08-25 23:28:31 +02:00
Mikei386 81e56d78c6 Keep migrated MCPs off fresh Athena installs 2026-08-25 23:23:08 +02:00
Mikei386 cca1fb217e Consolidate portable MCPs in Unraid MCPHub 2026-08-25 23:21:29 +02:00
Mikei386 d38af69380 Add Unraid MCPHub template 2026-08-25 22:53:57 +02:00
Mikei386 069da8b4f0 Simplify Athena stack and recovery 2026-08-25 22:27:26 +02:00
Mikei386 c4851305d1 Correct Deemix MCP image version 2026-08-25 21:56:57 +02:00
Mikei386 0a640e76ea Simplify Athena operator architecture 2026-08-25 21:53:12 +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 57afdd4f15 Use minimal reasoning for responsive Hermes chats 2026-08-25 18:26:31 +02:00
Mikei386 a9bd832c71 Document Hermes latency budget 2026-08-25 18:07:28 +02:00
Mikei386 8dfc879f26 Bound Hermes prompt and reasoning latency 2026-08-25 18:01:52 +02:00
Mikei386 37f744eaa2 Persist managed Hermes image in recovery installs 2026-08-25 16:41:45 +02:00
Mikei386 ba12aaaac6 Build Hermes MCP patches into managed image 2026-08-25 16:41:12 +02:00
Mikei386 488518a5e9 Bound Hermes tool loops and document MCP fixes 2026-08-25 15:55:49 +02:00
Mikei386 f5c2817c19 Avoid Hermes Home Assistant toolset collision 2026-08-25 15:41:30 +02:00
Mikei386 137b2e915c Refresh changed Hermes tool search catalogs 2026-08-25 15:38:06 +02:00
Mikei386 a984ce1892 Refresh MCP tools in Hermes API agents 2026-08-25 15:33:59 +02:00
Mikei386 a237c8d81c Wait for complete Hermes MCP discovery 2026-08-25 15:26:46 +02:00
Mikei386 63fc921988 Map Hermes reasoning controls into Qwen templates 2026-08-25 14:52:43 +02:00
Mikei386 7df28d9750 Make Hermes tool work bounded and evidence driven 2026-08-25 13:27:47 +02:00
Mikei386 63afc672c5 Fail fast on unreachable operator Git 2026-08-25 10:35:15 +02:00
Mikei386 bc1fbe9388 Preserve file modes in operator updates 2026-08-25 10:30:24 +02:00
Mikei386 4a260ae7d7 Make Hermes secret permissions idempotent 2026-08-25 10:25:52 +02:00
Mikei386 221f88c939 Give operator Docker a writable config 2026-08-25 10:23:11 +02:00
Mikei386 b588e0eb0c Fix operator Compose validation environment 2026-08-25 10:20:50 +02:00
Mikei386 397042b989 Bump Athena operator image to 2.3.0 2026-08-25 10:06:00 +02:00
Mikei386 f4faf27db4 Add staged MCP release imports 2026-08-25 10:03:44 +02:00
Mikei386 662913f8ab Add compact Athena MCP release workflow 2026-08-25 08:51:46 +02:00
Mikei386 ac725416b8 Simplify Athena operator maintenance workflow 2026-08-25 08:42:30 +02:00
Mikei386 fa9911eb3b Define Hermes router as named authenticated provider 2026-08-24 23:35:01 +02:00
Mikei386 9c1c0b8696 Keep Hermes gateway bound to authenticated router 2026-08-24 23:20:08 +02:00
Mikei386 a8ae77dbc3 Render Hermes router API key safely 2026-08-24 22:40:02 +02:00
Mikei386 53f10d1d3f Include Hermes WebUI state in recovery 2026-08-24 21:51:22 +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 dec4709ae9 Normalize punctuation before German TTS 2026-08-24 19:26:07 +02:00
Mikei386 faba681153 Configure Hermes for German voice and responses 2026-08-24 19:18:46 +02:00