Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
launch: fix web search, add web fetch, and enable both for local (#14886)
bcf6d55 Parth Sareen committed 8 months ago
runner: fix swallowed error in allocModel graph reservation
810d4f9 easonysliu committed 8 months ago
cmd/launch: skip --install-daemon when systemd is unavailable (#14883)
856c047 Bruce MacDonald committed 8 months ago
config: use native OpenClaw Ollama onboarding (#14829)
10fefe0 Bruce MacDonald committed 8 months ago
server: decompress zstd request bodies in cloud passthrough middleware (#14827)
3980c02 Bruce MacDonald committed 8 months ago
middleware: handle non-JSON error responses gracefully (#14828)
abf8e8e Bruce MacDonald committed 8 months ago
anthropic: close thinking block before tool_use when no text in between (#14825)
f3f31a8 Shivam Tiwari committed 8 months ago
cmd: still populate `ollama ls` when using `ollama run <model:cloud>` (#14824)
9e7ba83 Devon Rifkin committed 8 months ago
api/create: always propagate `:cloud` source for cloud models (#14822)
081b9eb Devon Rifkin committed 8 months ago
launch: fix headless --yes integration flow and policy scoping (#14815)
bb867c6 Parth Sareen committed 8 months ago
docs: document reasoning_effort support in OpenAI-compatible API (#14821)
81f4506 Cadu committed 8 months ago
openai: split mixed thinking stream chunks via ToChunks (#14648)
97013a1 Parth Sareen committed 8 months ago
Revert "runner: add token history sampling parameters to ollama runner (#14537)" (#14776)
54e0517 Jeffrey Morgan committed 8 months ago
server: add experimental web search and web fetch routes (#14753)
6108608 Parth Sareen committed 8 months ago