v0.7.3: 重构 Provider 层 + 计算层隔离 + Cleaner/NoMemory 架构

- 删除 OpenAIProvider/OllamaProvider 死代码，LuaAdaptedProvider 独存
- DisableThinking 从 ExtraBody 移到 CompletionRequest 顶层字段
- ContextWindow 从 Provider 签名移到 BaseConfig/ModelContextWindow() 统管
- 确认 CleanText 仅做基本空白 trim，QQ 模板剥离归插件 Cleaner
- Cleaner/NoMemory 仅作用于向量计算和 jieba 分词层，原文不变
- context.ContextEvent/Doc.Content 始终保存原文
- 删除 nlp/download.go 死代码
- media.go: context.Background() -> a.ctx 级联
- clawhubadapter: HTTP 超时
- cut.go: 跨平台 mod cache 路径 (GOMODCACHE->GOPATH->HomeDir)
- bridge_e2e_test: 移除未用 runtime import
- lua 适配器: disable_thinking 传参

internal/lua/adapters/anthropic.lua

@@ -7,7 +7,6 @@ adapter.headers = {
     ["anthropic-version"] = "2023-06-01"
 }
 
--- Anthropic Messages API: { model, messages[], max_tokens, system, stream }
 function adapter.transform_request(raw_body)
     local ok, req = pcall(json.decode, raw_body)
     if not ok then return raw_body end
@@ -28,6 +27,11 @@ function adapter.transform_request(raw_body)
         messages = msgs,
         stream = req.stream or false,
     }
+
+    if not req.disable_thinking then
+        anthropic_req.thinking = { type = "enabled", budget_tokens = 4096 }
+    end
+
     if system ~= "" then
         anthropic_req.system = system
     end

internal/lua/adapters/deepseek.lua

@@ -5,12 +5,16 @@ adapter.version = "2.0.0"
 adapter.endpoint = "/chat/completions"
 adapter.headers = {}
 
--- DeepSeek 格式与 OpenAI 兼容，thinking 模式由 Go 端 ExtraBody 控制
 function adapter.transform_request(raw_body)
     local ok, req = pcall(json.decode, raw_body)
     if not ok then return raw_body end
     req.model = req.model or "deepseek-chat"
     req.stream = req.stream or false
+    if req.disable_thinking then
+        req.extra_body = req.extra_body or {}
+        req.extra_body.thinking = { type = "disabled" }
+    end
+    req.disable_thinking = nil
     return json.encode(req)
 end
 

internal/lua/adapters/github.lua

@@ -14,6 +14,8 @@ function adapter.transform_request(raw_body)
     req.temperature = req.temperature or 0.7
     req.max_tokens = req.max_tokens or 4096
     req.stream = req.stream or false
+    req.disable_thinking = nil
+    req.extra_body = nil
     return json.encode(req)
 end
 

internal/lua/adapters/groq.lua

@@ -13,6 +13,8 @@ function adapter.transform_request(raw_body)
     req.temperature = req.temperature or 0.7
     req.max_tokens = req.max_tokens or 4096
     req.stream = req.stream or false
+    req.disable_thinking = nil
+    req.extra_body = nil
     return json.encode(req)
 end
 

internal/lua/adapters/mistral.lua

@@ -13,6 +13,8 @@ function adapter.transform_request(raw_body)
     req.temperature = req.temperature or 0.7
     req.max_tokens = req.max_tokens or 4096
     req.stream = req.stream or false
+    req.disable_thinking = nil
+    req.extra_body = nil
     return json.encode(req)
 end
 

internal/lua/adapters/openai.lua

@@ -5,14 +5,15 @@ adapter.version = "2.0.0"
 adapter.endpoint = "/chat/completions"
 adapter.headers = {}
 
--- raw_body: JSON string as received from Go (CompletionRequest marshalled)
--- return: transformed JSON string to send to API
+-- OpenAI /chat/completions format (pass-through, strip disable_thinking)
 function adapter.transform_request(raw_body)
-    return raw_body
+    local ok, req = pcall(json.decode, raw_body)
+    if not ok then return raw_body end
+    req.disable_thinking = nil
+    req.extra_body = nil
+    return json.encode(req)
 end
 
--- raw_body: JSON string from HTTP response body
--- return: unified JSON string in CompletionResponse format
 function adapter.transform_response(raw_body)
     local ok, resp = pcall(json.decode, raw_body)
     if not ok then return raw_body end
@@ -57,8 +58,6 @@ function adapter.transform_response(raw_body)
     return json.encode(unified)
 end
 
--- raw_chunk: single SSE data line (after "data: " prefix)
--- return: unified chunk JSON string, or "" to skip
 function adapter.transform_stream_chunk(raw_chunk)
     local ok, chunk = pcall(json.decode, raw_chunk)
     if not ok then return "" end