shahondin1624
  • Germay
  • Joined on 2026-01-30
shahondin1624 pushed to main at llm-multiverse/llm-multiverse 2026-03-10 14:05:10 +01:00
457c086696 Merge pull request 'feat: implement model routing logic (#40)' (#138) from feature/issue-40-model-routing into main
8620a88f0a feat: implement model routing logic and audit logging (issue #40)
Compare 2 commits »
shahondin1624 commented on issue llm-multiverse/llm-multiverse#40 2026-03-10 14:05:10 +01:00
Implement model routing logic

Implemented and merged via PR #138.\n\n- ModelRouter with resolve_model() and resolve_embedding_model()\n- model_hint proto field for explicit model override\n- Audit logging helper (best-effort,…

shahondin1624 deleted branch feature/issue-40-model-routing from llm-multiverse/llm-multiverse 2026-03-10 14:05:10 +01:00
shahondin1624 merged pull request llm-multiverse/llm-multiverse#138 2026-03-10 14:05:08 +01:00
feat: implement model routing logic (#40)
shahondin1624 created pull request llm-multiverse/llm-multiverse#138 2026-03-10 14:05:04 +01:00
feat: implement model routing logic (#40)
shahondin1624 created branch feature/issue-40-model-routing in llm-multiverse/llm-multiverse 2026-03-10 14:04:54 +01:00
8620a88f0a feat: implement model routing logic and audit logging (issue #40)
shahondin1624 pushed to main at llm-multiverse/llm-multiverse 2026-03-10 13:57:41 +01:00
0dd9dcd876 docs: mark issue #39 as COMPLETED in implementation plans
shahondin1624 closed issue llm-multiverse/llm-multiverse#39 2026-03-10 13:57:17 +01:00
Implement Ollama HTTP client
shahondin1624 commented on issue llm-multiverse/llm-multiverse#39 2026-03-10 13:57:13 +01:00
Implement Ollama HTTP client

Implemented and merged via PR #137.\n\n- OllamaClient with generate, generate_stream, chat, embed, list_models, is_healthy\n- NDJSON streaming parser for streaming responses\n- Serde types for all…

shahondin1624 merged pull request llm-multiverse/llm-multiverse#137 2026-03-10 13:57:12 +01:00
feat: implement Ollama HTTP client (#39)
shahondin1624 deleted branch feature/issue-39-ollama-http-client from llm-multiverse/llm-multiverse 2026-03-10 13:57:12 +01:00
shahondin1624 pushed to main at llm-multiverse/llm-multiverse 2026-03-10 13:57:12 +01:00
43978aa211 Merge pull request 'feat: implement Ollama HTTP client (#39)' (#137) from feature/issue-39-ollama-http-client into main
a38ea1db51 feat: implement Ollama HTTP client for Model Gateway (issue #39)
Compare 2 commits »
shahondin1624 created pull request llm-multiverse/llm-multiverse#137 2026-03-10 13:57:06 +01:00
feat: implement Ollama HTTP client (#39)
a38ea1db51 feat: implement Ollama HTTP client for Model Gateway (issue #39)
shahondin1624 pushed to main at llm-multiverse/llm-multiverse 2026-03-10 13:43:51 +01:00
0c55de22f2 docs: mark issue #38 as COMPLETED in implementation plans
shahondin1624 commented on issue llm-multiverse/llm-multiverse#38 2026-03-10 13:43:29 +01:00
Scaffold Model Gateway Rust project

Implemented and merged via PR #136.\n\n- Workspace member services/model-gateway created\n- Config loading (TOML) with model routing, Ollama URL, audit address\n- IsModelReady endpoint returns…

shahondin1624 closed issue llm-multiverse/llm-multiverse#38 2026-03-10 13:43:29 +01:00
Scaffold Model Gateway Rust project
shahondin1624 deleted branch feature/issue-38-scaffold-model-gateway from llm-multiverse/llm-multiverse 2026-03-10 13:43:24 +01:00