Arthur Erlich

haylan opened issue haylan/LLM-Server#33

2026-09-03 17:17:47 +00:00

OmniRoute due-diligence: maintainer, repo history, npm package trust

haylan opened issue haylan/LLM-Server#32

2026-09-03 17:17:39 +00:00

OmniRoute: can it route to arbitrary OpenAI-compatible local endpoints (llama-server), not just Ollama?

haylan opened issue haylan/LLM-Server#31

2026-09-03 17:17:29 +00:00

Migrate the AI gateway from LiteLLM to OmniRoute

haylan deleted branch ctx-size-128k from haylan/LLM-Server

2026-09-03 04:44:35 +00:00

haylan pushed to main at haylan/LLM-Server

2026-09-03 04:44:35 +00:00

6b06d6001f Merge pull request 'feat(llama.cpp): raise default context to 128K, document RAM/SSD offload knobs' (#30) from ctx-size-128k into main

c5864beec9 feat(llama.cpp): raise default context to 128K, document RAM/SSD offload knobs

Compare 2 commits »

haylan merged pull request haylan/LLM-Server#30

2026-09-03 04:44:34 +00:00

feat(llama.cpp): raise default context to 128K, document RAM/SSD offload knobs

haylan created pull request haylan/LLM-Server#30

2026-09-03 04:44:28 +00:00

feat(llama.cpp): raise default context to 128K, document RAM/SSD offload knobs

haylan commented on issue haylan/LLM-Server#26

2026-09-03 04:43:40 +00:00

opencode: context size and compaction settings for the litellm/qwen3.8-27b-local stack

limit.context in ~/.config/opencode/opencode.json bumped 65536 -> 131072: the server's live LLAMA_CTX_SIZE was changed directly on the box, ahead of merging the ctx-size-128k branch into this…

haylan commented on issue haylan/LLM-Server#29

2026-09-03 04:42:16 +00:00

Point opencode's provider block at litellm.home with a virtual key

Done: provider block added to ~/.config/opencode/opencode.json (baseURL http://litellm.home/v1, model id qwen3.8-27b-local matching litellm's model_name, virtual key supplied directly by the user…

haylan commented on issue haylan/LLM-Server#28

2026-09-03 04:42:15 +00:00

Should opencode's context/output limits be generated from litellm-config.yaml, or hand-maintained?

Decided in practice, not via a generator script: opencode's limit.context/limit.output are hand-set in ~/.config/opencode/opencode.json (65536/16384, matching what's currently live), with an…

haylan closed issue haylan/LLM-Server#29

2026-09-03 04:42:01 +00:00

Point opencode's provider block at litellm.home with a virtual key

haylan closed issue haylan/LLM-Server#28

2026-09-03 04:42:00 +00:00

Should opencode's context/output limits be generated from litellm-config.yaml, or hand-maintained?

haylan pushed to ctx-size-128k at haylan/LLM-Server

2026-09-03 04:35:50 +00:00

c5864beec9 feat(llama.cpp): raise default context to 128K, document RAM/SSD offload knobs

haylan created branch ctx-size-128k in haylan/LLM-Server

2026-09-03 04:35:50 +00:00

haylan commented on issue haylan/LLM-Server#27

2026-09-03 04:26:22 +00:00

How does opencode's auto-compact actually work — trigger threshold and config surface?

Researched OpenCode's auto-compact mechanism directly from source (anomalyco/opencode @ b578b72, v1.18.27, cloned 2026-09-03) plus live docs.opencode.ai fetches.

Key findings — full writeup at…

haylan closed issue haylan/LLM-Server#27

2026-09-03 04:26:08 +00:00

How does opencode's auto-compact actually work — trigger threshold and config surface?

haylan opened issue haylan/LLM-Server#29

2026-09-03 04:19:56 +00:00

Point opencode's provider block at litellm.home with a virtual key

haylan opened issue haylan/LLM-Server#28

2026-09-03 04:19:45 +00:00

Should opencode's context/output limits be generated from litellm-config.yaml, or hand-maintained?

haylan opened issue haylan/LLM-Server#27

2026-09-03 04:19:33 +00:00

How does opencode's auto-compact actually work — trigger threshold and config surface?

haylan opened issue haylan/LLM-Server#26

2026-09-03 04:19:22 +00:00

opencode: context size and compaction settings for the litellm/qwen3.8-27b-local stack