feat(llm): add disableThinking option to suppress reasoning in extraction models (#228)

Support multiple inference engines and model providers via a strategy
enum so each receives its own thinking-disabling field in
chat-completion request bodies.

Strategies:
- "vllm"      → chat_template_kwargs: { enable_thinking: false }  (vLLM / SGLang)
- "deepseek"  → enable_thinking: false  (DeepSeek official API)
- "dashscope" → enable_thinking: false  (Alibaba DashScope / Qwen)
- "openai"    → reasoning_effort: "low"  (OpenAI o-series, cannot fully disable)
- "anthropic" → thinking: { type: "disabled" }  (Anthropic Claude)
- "kimi"      → thinking: { type: "disabled" }  (Kimi / Moonshot)
- "gemini"    → thinking_config: { thinking_budget: 0 }  (Google Gemini)

Defaults to false (no wrapper). Also accepts boolean true as a shorthand
for "vllm" for convenience.

Covered paths:
- StandaloneLLMRunner (OpenClaw plugin + gateway): llm.disableThinking,
  wired through parseConfig, tdai-core, seed-runtime, and gateway config
  (TDAI_LLM_DISABLE_THINKING env also accepts strategy names).
- Offload local mode (L1/L1.5/L2): separate offload.disableThinking.

The fetch wrapper lives in src/utils/no-think-fetch.ts with a
STRATEGY_TRANSFORMERS map for clean dispatch. StandaloneLLMRunner builds
it once in the constructor; LocalLlmClient caches it at construction
time and passes it through to callLlm().

Add vitest unit tests for all 7 strategies, normalization, validation,
embedding skip, and non-JSON tolerance (20 tests total).

Signed-off-by: jackson.jia <jiazhenghua0@gmail.com>

openclaw.plugin.json

@@ -140,7 +140,8 @@
           "apiKey": { "type": "string", "description": "API Key" },
           "model": { "type": "string", "default": "gpt-4o", "description": "模型名称（如 gpt-4o, deepseek-v3, claude-sonnet-4-6）" },
           "maxTokens": { "type": "number", "default": 4096, "description": "最大输出 token 数" },
-          "timeoutMs": { "type": "number", "default": 120000, "description": "请求超时（毫秒）" }
+          "timeoutMs": { "type": "number", "default": 120000, "description": "请求超时（毫秒）" },
+          "disableThinking": { "oneOf": [{ "type": "boolean" }, { "type": "string", "enum": ["vllm", "deepseek", "dashscope", "openai", "anthropic", "kimi", "gemini"] }], "default": false, "description": "禁用推理模型思考过程。可选策略: \"vllm\" (vLLM/SGLang), \"deepseek\" (DeepSeek API), \"dashscope\" (阿里云 DashScope/Qwen), \"openai\" (OpenAI o系列), \"anthropic\" (Anthropic Claude), \"kimi\" (Kimi/Moonshot), \"gemini\" (Google Gemini)。" }
         }
       },
       "offload": {
@@ -150,6 +151,7 @@
           "enabled": { "type": "boolean", "default": false, "description": "是否启用 Context Offload（默认关闭，不影响 Memory 功能）" },
           "model": { "type": "string", "description": "Offload 使用的 LLM 模型（格式: provider/model），未填写时使用 openclaw 默认模型" },
           "temperature": { "type": "number", "default": 0.2, "description": "LLM 温度参数" },
+          "disableThinking": { "oneOf": [{ "type": "boolean" }, { "type": "string", "enum": ["vllm", "deepseek", "dashscope", "openai", "anthropic", "kimi", "gemini"] }], "default": false, "description": "禁用推理模型思考过程（仅 local 模式）。可选策略: \"vllm\"/\"deepseek\"/\"dashscope\"/\"openai\"/\"anthropic\"/\"kimi\"/\"gemini\"。" },
           "forceTriggerThreshold": { "type": "number", "default": 4, "description": "累积多少个 tool pair 后强制触发 L1" },
           "dataDir": { "type": "string", "description": "自定义数据目录（绝对路径），默认 ~/.openclaw/context-offload" },
           "defaultContextWindow": { "type": "number", "default": 200000, "description": "默认上下文窗口大小" },