mateclaw/mateclaw-server/src/main/java/vip/mate/llm
倪程伟 8e00613e69
fix(embedding): use chatModel field for protocol routing instead of providerId matching (#170)
Closes #166

EmbeddingModelFactory used EmbeddingProtocol.fromProviderId() to pick the
embedding protocol, which substring-matches 'dashscope' / 'qwen' / 'aliyun'
in the providerId. The dashscope-compat provider carries 'dashscope' in its
id but runs in OpenAI compatible mode (chatModel='OpenAIChatModel',
baseUrl='https://dashscope.aliyuncs.com/compatible-mode/v1'). Routing it to
DASHSCOPE_EMBEDDING made DashScopeApi build its native path against the
compat base, producing 404s on every embedding call.

Switch to the chatModel column instead — the same signal ModelProtocol
.fromChatModel() uses for the chat path. chatModel='DashScopeChatModel'
takes the native protocol; everything else (including dashscope-compat)
takes OpenAI-compatible.

EmbeddingProtocol.fromProviderId() is retained for reference but is no
longer called; future callers should follow the chatModel pattern.
2026-05-20 09:22:06 +08:00
..
anthropic/oauth chore: drop external project name references from code comments 2026-05-20 08:09:43 +08:00
cache chore: drop external project name references from code comments 2026-05-20 08:09:43 +08:00
chatgpt fix(mcp): expand JVM system properties in stdio args/env/cwd 2026-05-05 14:46:08 +08:00
chatmodel feat(llm): native Gemini chat builder, Nano Banana image gen, xAI/Grok provider 2026-05-18 10:00:55 +08:00
config fix(llm): skip Ollama auto-discovery network probe when provider disabled 2026-05-03 20:32:17 +08:00
controller fix(rbac): let viewers read active model so they can actually chat 2026-05-15 10:19:03 +08:00
embedding fix(embedding): use chatModel field for protocol routing instead of providerId matching (#170) 2026-05-20 09:22:06 +08:00
event Initial commit: MateClaw — Java + Vue 3 AI Assistant System 2026-04-04 19:03:49 +08:00
failover fix(llm): stop MODEL_NOT_FOUND from evicting the whole provider (#150) 2026-05-18 16:27:20 +08:00
gemini feat(llm): native Gemini chat builder, Nano Banana image gen, xAI/Grok provider 2026-05-18 10:00:55 +08:00
model fix(embedding): use chatModel field for protocol routing instead of providerId matching (#170) 2026-05-20 09:22:06 +08:00
oauth fix(llm): activate default model after OpenAI OAuth and gate provider checks by enabled 2026-05-12 09:58:30 +08:00
repository Initial commit: MateClaw — Java + Vue 3 AI Assistant System 2026-04-04 19:03:49 +08:00
routing refactor(llm): decouple model construction from the agent graph layer (#147) 2026-05-18 07:47:49 +08:00
service feat(chat): per-conversation model selection (#150) 2026-05-18 16:27:27 +08:00