This website requires JavaScript.
a3f1099bfc
docs(research): OmniRoute memory tools hijack classifier tool-call, x-omniroute-no-memory fix
haylan
2026-09-15 23:31:58 +02:00
ed90256f43
docs(research): trace 48-min outage to third OmniRoute timeout and open ROCm#6630 GPU hang
haylan
2026-09-15 23:31:58 +02:00
fa852c8fb4
docs(research): qwen-classifier needs no context-window match; 8B/30B won't fit VRAM
haylan
2026-09-15 23:31:58 +02:00
edad6b2249
Merge branch 'research/opencode-auto-compact'
haylan
2026-09-14 07:44:32 +02:00
2250e804db
Implement code changes to enhance functionality and improve performance
haylan
2026-09-11 13:15:30 +02:00
e31647812a
fix(omniroute): raise REQUEST_TIMEOUT_MS and enable --cache-reuse to stop non-ping SSE stream aborts
haylan and Claude-Bot
2026-09-10 10:10:40 +02:00
930e407053
docs(llm): document qwen-classifier reality, add --reasoning off safety net
haylan and Claude-Bot
2026-09-09 19:10:32 +02:00
76043e2c6f
tune(llm): partial GPU offload for qwen-classifier, real headroom
haylan and Claude-Bot
2026-09-09 18:10:39 +02:00
1102273384
fix(llm): enable flash-attn on qwen-classifier, real VRAM cause found
haylan and Claude-Bot
2026-09-09 17:04:05 +02:00
ba9ace6f71
fix(llm): shrink qwen-classifier's compute buffer for real VRAM headroom
haylan and Claude-Bot
2026-09-09 17:02:44 +02:00
8e2650807c
fix(llm): move qwen-classifier to GPU, right-size context
haylan and Claude-Bot
2026-09-09 16:59:02 +02:00
4353e5c0e8
merge: follow-up fix for qwen-classifier model file
haylan and Claude-Bot
2026-09-09 16:38:11 +02:00
20cc0bcc70
fix(llm): point qwen-classifier at the Q8 GGUF already on disk
haylan and Claude-Bot
2026-09-09 16:37:54 +02:00
c1e30ec9bb
Merge pull request 'Fix/omniroute pr agent timeout' (#54 ) from fix/omniroute-pr-agent-timeout into main
haylan
2026-09-09 14:29:13 +00:00
b3a64fe4b5
chroe(chore): added markdown for harnesses
haylan
2026-09-09 16:28:42 +02:00
828bd4c046
feat(llm): dedicate a CPU-only backend for the qwen-code tool-call classifier
haylan and Claude-Bot
2026-09-09 16:26:51 +02:00
16df051318
docs(research): add ponytail audit report highlighting over-engineering and complexity issues
haylan
2026-09-09 08:22:31 +02:00
128503b68a
docs: add AGENTS.md and QWEN.md with agent instructions and project overview
haylan
2026-09-09 07:32:09 +02:00
df900404c0
chore(config): fix ignored path .qwen/temp to .qwen/tmp
haylan
2026-09-08 12:46:32 +02:00
f4729ba704
docs(research): evaluate Colibrì for this stack
haylan
2026-09-08 12:46:16 +02:00
8f3feb4881
Merge branch 'feat-rag-databases'
haylan and Claude-Bot
2026-09-08 12:30:27 +02:00
6f4e736da8
docs(coding-cli-setup): split per-CLI docs into their own files
haylan and Claude-Bot
2026-09-08 12:30:08 +02:00
4c8a9c039e
Merge pull request 'fix(update.sh): stop config sync loop from dying silently on a missing key' (#53 ) from feat-rag-databases into main
haylan
2026-09-07 18:10:23 +00:00
2ee308c1d9
Merge branch 'main' into feat-rag-databases
haylan
2026-09-07 18:10:16 +00:00
1fcf30e9a1
fix(update.sh): stop config sync loop from dying silently on a missing key
haylan and Claude-Bot
2026-09-07 20:09:31 +02:00
31e9aab1f3
Merge pull request 'Add Qdrant/Neo4j RAG storage + update.sh gum fixes' (#52 ) from feat-rag-databases into main
haylan
2026-09-07 18:07:48 +00:00
665c3cb630
Merge branch 'main' into feat-rag-databases
haylan
2026-09-07 18:07:42 +00:00
e151aa6ffe
feat(update.sh): vendor gum binary for the R9700's offline install
haylan and Claude-Bot
2026-09-07 20:04:56 +02:00
feb7469f0b
fix(update.sh): report why gum auto-install failed instead of failing silently
haylan and Claude-Bot
2026-09-07 20:01:20 +02:00
b51f7f9ad5
Merge pull request 'feat: add qdrant and neo4j for RAG vector/graph storage' (#50 ) from feat-rag-databases into main
haylan
2026-09-07 17:56:49 +00:00
fbb949d417
Merge branch 'main' into feat-rag-databases
haylan
2026-09-07 17:56:40 +00:00
9767261a96
Merge pull request 'feat: remove llama-server-fast (Qwen3-4B classifier model)' (#51 ) from remove-fast-model into main
haylan
2026-09-07 17:56:27 +00:00
7a654ead91
chore: ignore .qwen/temp
haylan
2026-09-07 19:54:38 +02:00
2bfe6dbd29
docs: point knowledge.proxy-ai.home at Neo4j's browser
haylan and Claude-Bot
2026-09-07 19:40:51 +02:00
5d6a17fd9b
feat: remove llama-server-fast (Qwen3-4B classifier model)
haylan and Claude-Bot
2026-09-07 19:33:50 +02:00
20f2ec3ab2
feat: add qdrant and neo4j for RAG vector/graph storage
haylan and Claude-Bot
2026-09-07 19:20:14 +02:00
5b7548dc7c
Merge pull request 'Fix llama-server-fast context-size exhaustion breaking Auto Mode' (#49 ) from fix-fastmodel-context-size into main
haylan
2026-09-06 20:21:53 +00:00
ea7b05fb99
feat: interactive per-key conflict resolution in update.sh's config sync
haylan
2026-09-06 22:20:27 +02:00
9def240a8e
feat: update.sh force-syncs tracked config from .env.example
haylan
2026-09-06 22:10:51 +02:00
52a92f6508
fix: llama-server-fast context-size exhaustion breaking Auto Mode classifier
haylan and Claude-Bot
2026-09-06 22:06:59 +02:00
63938e95c9
Merge pull request 'Run git pull first in update.sh, not mid-script' (#48 ) from fix-update-sh-pull-order into main
haylan
2026-09-06 19:40:10 +00:00
7b6d3f5802
fix: run git pull first in update.sh, not mid-script
haylan
2026-09-06 21:38:18 +02:00
386a41200f
Merge pull request 'Fix GPU pinned at 100% with two containers, flaky render group' (#47 ) from fix-gpu-pin-and-render-group into main
haylan
2026-09-06 19:35:31 +00:00
75033dacd7
fix: GPU pinned at 100% with two llama.cpp containers, flaky render group
haylan and Claude-Bot
2026-09-06 21:33:40 +02:00
1ee2e76033
Merge pull request 'Downloader for Qwen-Image weights, switch-model.sh' (#46 ) from comfyui-model-and-switch-script into main
haylan
2026-09-06 19:01:02 +00:00
4b47a1769d
feat: downloader for Qwen-Image weights, switch-model.sh script
haylan and Claude-Bot
2026-09-06 20:57:38 +02:00
1932981f09
Merge pull request 'Add llama-server-fast: small non-thinking classifier/fast model' (#45 ) from add-fast-model into main
haylan
2026-09-06 18:39:30 +00:00
d984c10835
feat: add llama-server-fast, a small non-thinking classifier model
haylan and Claude-Bot
2026-09-06 20:24:59 +02:00
71c9003bd8
Create dashscope-websearch-selfhost-options.md
haylan
2026-09-06 16:10:26 +02:00
ed83fca05c
feat(comfyui): add local image-gen service (#41 )
haylan and Claude-Bot
2026-09-05 22:40:07 +02:00
7d1ff2f54f
docs(research): add image-gen backend survey and omniroute/qwen websearch notes
haylan and Claude-Bot
2026-09-05 21:24:23 +02:00
ac3f730f83
docs(research): recommend Qwen-Image FP8 for full-VRAM diffusion build
haylan and Claude-Bot
2026-09-05 21:03:13 +02:00
451d5c7b28
docs(research): confirm lazytainer/omniroute idle-stop conflict (#40 )
haylan and Claude-Bot
2026-09-05 20:57:24 +02:00
d8736b6dd7
fix(llama-server): quantize KV cache, restore full 262144 context
haylan and Claude-Bot
2026-09-05 12:00:07 +02:00
5767f548c3
perf(llama-server): enable flash attention
haylan and Claude-Bot
2026-09-05 11:32:17 +02:00
633292b291
fix(omniroute): raise stream-idle timeout to 180s
haylan and Claude-Bot
2026-09-05 11:29:12 +02:00
23e90fe8fb
fix(llama-server): cap concurrent slots at 2 to curb prefill contention
haylan and Claude-Bot
2026-09-05 11:26:30 +02:00
ae812cd9e0
feat(ctx): larger context size
haylan
2026-09-04 21:47:38 +02:00
9e9cac254b
feat(stack): drop qdrant and embedding-server, use OmniRoute's built-in memory
haylan
2026-09-03 22:19:21 +02:00
9e1362c22c
feat(omniroute): add dedicated embedding-server for memory feature
haylan and Claude-Bot
2026-09-03 21:43:20 +02:00
885de477ba
feat(stack): bring back qdrant as OmniRoute's memory vector store
haylan and Claude-Bot
2026-09-03 21:19:06 +02:00
c795993a64
fix(omniroute): publish API and dashboard ports directly, drop OMNIROUTE_PORT
haylan and Claude-Bot
2026-09-03 20:49:25 +02:00
c38375c0f4
fix(omniroute): add required WS bridge secret, memory ceiling, shutdown grace period
haylan and Claude-Bot
2026-09-03 20:37:49 +02:00
6132e6263e
docs: fix gateway hostname to proxy-ai.home/proxy-ai.haylan.ch
haylan and Claude-Bot
2026-09-03 20:28:21 +02:00
90ef1a1061
fix(omniroute): keep the gateway published on host port 4000
haylan and Claude-Bot
2026-09-03 20:17:08 +02:00
977e9d3dd7
fix(omniroute): healthcheck used python3, which the image doesn't have
haylan and Claude-Bot
2026-09-03 20:08:58 +02:00
3bbda098b3
feat(stack): remove Open WebUI and Qdrant
haylan and Claude-Bot
2026-09-03 19:55:31 +02:00
472e3a4738
feat(gateway): migrate LiteLLM to OmniRoute, drop the memory/knowledgebase feature
haylan and Claude-Bot
2026-09-03 19:49:35 +02:00
4fe910a5f3
docs(agents): fix tea comment syntax, note map-edit race condition
haylan and Claude-Bot
2026-09-03 19:29:10 +02:00
6b06d6001f
Merge pull request 'feat(llama.cpp): raise default context to 128K, document RAM/SSD offload knobs' (#30 ) from ctx-size-128k into main
haylan
2026-09-03 04:44:34 +00:00
c5864beec9
feat(llama.cpp): raise default context to 128K, document RAM/SSD offload knobs
haylan and Claude-Bot
2026-09-03 06:35:48 +02:00
1eaa2a0d2e
docs(research): document opencode auto-compact trigger and config surface
haylan and Claude-Bot
2026-09-03 06:25:57 +02:00
124053cf89
feat(scripts): auto-register memory-and-notes in litellm's DB for the Admin UI
haylan
2026-09-02 21:51:02 +00:00
47bdb22457
docs: record issue #24 's smoke-test findings and local litellm-pgvector patches
haylan
2026-09-02 21:32:38 +00:00
7e8b5069d4
fix(scripts): update.sh never applied litellm-pgvector's db schema
haylan
2026-09-02 21:32:33 +00:00
eaf11b6d4b
fix(scripts): ingest-memory.sh never actually computed embeddings
haylan
2026-09-02 21:32:29 +00:00
213550e44b
fix(litellm): prefix EMBEDDING__MODEL with openai/ for litellm-pgvector
haylan
2026-09-02 21:32:23 +00:00
3eda4e3ec0
fix(litellm-pgvector): honor caller-supplied id on vector store create
haylan
2026-09-02 21:32:18 +00:00
b627edb949
fix(litellm-pgvector): correct embedding vector dimension 1536 -> 768
haylan
2026-09-02 21:32:13 +00:00
ec476c7950
fix(litellm): add missing api_key to vector_store_registry
haylan
2026-09-02 21:32:08 +00:00
e2dd106f74
feat(scripts): fold model downloads into update.sh, skip if already present
haylan and Claude-Bot
2026-09-02 23:07:53 +02:00
fb7cfc9148
fix(litellm): raise qwen3.8-27b-local max_tokens floor 4096 -> 16384
haylan and Claude-Bot
2026-09-02 22:59:53 +02:00
30a8523433
fix(lazytainer): drop network_mode: host, join ai-stack (fixes self-ID panic)
haylan and Claude-Bot
2026-09-02 22:55:38 +02:00
c7848f356a
chore(scripts): mark update.sh executable
haylan and Claude-Bot
2026-09-02 22:47:53 +02:00
cb9b3a9045
fix(docs): update stale MEMORY_RETRIEVAL_EMBEDDING_KEY refs after litellm-pgvector revert
haylan and Claude-Bot
2026-09-02 22:46:10 +02:00
e7983f0710
Revert "feat(knowledgebase): replace litellm-pgvector connector with memory-retrieval"
haylan and Claude-Bot
2026-09-02 22:45:08 +02:00
b4dc83949e
feat(litellm): add Redis for router state/rate-limits/budgets/cache
haylan and Claude-Bot
2026-09-02 22:28:25 +02:00
b996b1fe88
fix(scripts): update.sh now appends vars missing from .env, not just blank ones
haylan and Claude-Bot
2026-09-02 22:21:50 +02:00
24d749b2e0
feat(scripts): fold generate-secrets.sh into update.sh, auto-mint virtual keys
haylan and Claude-Bot
2026-09-02 22:18:11 +02:00
abeadc49c8
feat(knowledgebase): replace litellm-pgvector connector with memory-retrieval
haylan and Claude-Bot
2026-09-02 22:09:25 +02:00
e2a79eab4a
docs(research): LangChain+pgvector-direct vs litellm-pgvector for issue #25
haylan and Claude-Bot
2026-09-02 22:02:58 +02:00
7247674a9f
fix(litellm-pgvector): vendor the source instead of a remote git build context
haylan and Claude-Bot
2026-09-02 21:50:45 +02:00
b0e37b2f4c
chore(scripts): add update.sh, hook it into agent/deploy workflow
haylan and Claude-Bot
2026-09-02 21:44:26 +02:00
f508f5670a
feat(litellm): wire SearXNG search, pgvector knowledgebase, and memory ingestion
haylan and Claude-Bot
2026-09-02 21:38:16 +02:00
a3ecbc0e02
docs(research): investigate LiteLLM knowledgebase/vector_store feature for #23
haylan and Claude-Bot
2026-09-02 21:26:39 +02:00
8c42f2518b
research: LiteLLM web-search + SearXNG wiring (issue #22 )
haylan and Claude-Bot
2026-09-02 21:25:30 +02:00
949802fb2b
Merge pull request 'fix(litellm): default max_tokens=4096 for the reasoning model' (#20 ) from fix/litellm-reasoning-max-tokens into main
haylan
2026-09-02 18:58:11 +00:00
100fed4274
fix(litellm): default max_tokens=4096 for the reasoning model
haylan and Claude-Bot
2026-09-02 20:55:39 +02:00
7609da7dad
Merge pull request 'feat(litellm): add UI_USERNAME/UI_PASSWORD for the admin UI login' (#19 ) from fix/litellm-ui-admin-creds into main
haylan
2026-09-02 18:29:30 +00:00
ee7ebfd8e1
feat(litellm): add UI_USERNAME/UI_PASSWORD for the admin UI login
haylan and Claude-Bot
2026-09-02 20:29:00 +02:00
haylan
