Arthur Erlich

haylan pushed to comfyui-model-and-switch-script at haylan/LLM-Server

2026-09-06 18:57:40 +00:00

4b47a1769d feat: downloader for Qwen-Image weights, switch-model.sh script

haylan created branch comfyui-model-and-switch-script in haylan/LLM-Server

2026-09-06 18:57:40 +00:00

haylan deleted branch add-fast-model from haylan/LLM-Server

2026-09-06 18:39:33 +00:00

haylan pushed to main at haylan/LLM-Server

2026-09-06 18:39:33 +00:00

1932981f09 Merge pull request 'Add llama-server-fast: small non-thinking classifier/fast model' (#45) from add-fast-model into main

d984c10835 feat: add llama-server-fast, a small non-thinking classifier model

Compare 2 commits »

haylan closed issue haylan/LLM-Server#44

2026-09-06 18:39:31 +00:00

Add llama-server-fast: small non-thinking classifier/fast model for qwen-code Auto Mode

haylan merged pull request haylan/LLM-Server#45

2026-09-06 18:39:31 +00:00

Add llama-server-fast: small non-thinking classifier/fast model

haylan created pull request haylan/LLM-Server#45

2026-09-06 18:27:27 +00:00

Add llama-server-fast: small non-thinking classifier/fast model

haylan pushed to add-fast-model at haylan/LLM-Server

2026-09-06 18:25:05 +00:00

d984c10835 feat: add llama-server-fast, a small non-thinking classifier model

haylan created branch add-fast-model in haylan/LLM-Server

2026-09-06 18:25:05 +00:00

haylan opened issue haylan/LLM-Server#44

2026-09-06 18:17:27 +00:00

Add llama-server-fast: small non-thinking classifier/fast model for qwen-code Auto Mode

haylan pushed to main at haylan/delegate-ai-mcp

2026-09-06 17:56:41 +00:00

80807df095 Update qwen-delegate.ts

haylan pushed to main at haylan/delegate-ai-mcp

2026-09-06 16:23:05 +00:00

5cd0453162 Fix qwen_delegate: quote args for shell:true on Windows

061a1f381d Rewrite README to match locked TS conventions; minor tool/doc tweaks

Compare 2 commits »

haylan closed issue haylan/delegate-ai-mcp#1

2026-09-06 16:11:23 +00:00

TypeScript project conventions for delegate-ai-mcp

haylan commented on issue haylan/delegate-ai-mcp#1

2026-09-06 16:11:22 +00:00

TypeScript project conventions for delegate-ai-mcp

Map complete — frontier is empty, no open children, remaining fog (npm-publish, once-#4's-refactor-is-implemented) is explicitly deferred, not ticket-ready. Closing the map.

haylan closed issue haylan/delegate-ai-mcp#6

2026-09-06 16:10:54 +00:00

Publish-shaped package.json for delegate-ai-mcp

haylan commented on issue haylan/delegate-ai-mcp#6

2026-09-06 16:10:53 +00:00

Publish-shaped package.json for delegate-ai-mcp

Closed as out of scope: this ticket assumed a real npm-publish eventually happens, but the no-build decision (ticket #3, reverted to no-build) means native strip-types can't run from inside…

haylan closed issue haylan/delegate-ai-mcp#5

2026-09-06 16:00:04 +00:00

Lint/format tooling for delegate-ai-mcp

haylan commented on issue haylan/delegate-ai-mcp#5

2026-09-06 16:00:03 +00:00

Lint/format tooling for delegate-ai-mcp

Resolved: skip lint/format tooling entirely for now. Project is too small (~4 source files) to justify it; revisit only if growth makes inconsistency an actual problem. No enforcement point needed…

haylan closed issue haylan/delegate-ai-mcp#4

2026-09-06 15:57:50 +00:00

Multi-tool source structure for delegate-ai-mcp

haylan commented on issue haylan/delegate-ai-mcp#4

2026-09-06 15:57:49 +00:00

Multi-tool source structure for delegate-ai-mcp

Resolved:

Separate process per backend \u2014 each delegate tool (qwen, and whatever comes next) is its own MCP server process with its own claude mcp add --scope user registration. Not one…