LLM 호출 규격 전환: 고객사 사내 LLM(FabriX/Gauss) 헤더 지원 (LLM_PROVIDER=fabrix)

- settings: LLM_PROVIDER/LLM_CHAT_PATH/LLM_BODY_MODEL/LLM_JSON_MODE/LLM_MAX_TOKENS, FABRIX_* 3종, llm_enabled()
- llm_client: headers()/body() 를 규격별로 구성. fabrix 는 x-openapi-token(Bearer)/x-generative-ai-client/
  x-llm-model-id/x-generative-ai-user-email, body model 은 LLM_BODY_MODEL
- summarize/ping: 접속 점검 명령 (--show 로 요청만 확인)
- docs/llm-provider-plan.md: 계획·.env 값·오류별 조치. 기본값은 openai 라 기존 동작 불변

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

summarize/llm_client.py

@@ -55,10 +55,27 @@ def _extract_json(content: str) -> dict:
 
 
 class OpenAICompatClient(LLMClient):
+    """OpenAI 호환 `/chat/completions` 호출. 규격(LLM_PROVIDER)에 따라 헤더만 다르다.
+
+    - openai : Authorization: Bearer <LLM_API_KEY>
+    - fabrix : 고객사 사내 LLM. x-openapi-token(Bearer ...) / x-generative-ai-client /
+               x-llm-model-id / x-generative-ai-user-email. body 의 model 은 LLM_BODY_MODEL.
+    """
+
     def __init__(self) -> None:
-        if not settings.llm_base_url or not settings.llm_api_key:
-            raise RuntimeError("LLM_BASE_URL / LLM_API_KEY 환경변수가 필요합니다")
+        if not settings.llm_base_url:
+            raise RuntimeError("LLM_BASE_URL 환경변수가 필요합니다")
+        self.provider = settings.llm_provider
+        if self.provider == "fabrix":
+            if not (settings.fabrix_client_key and settings.fabrix_openapi_token):
+                raise RuntimeError("LLM_PROVIDER=fabrix 는 FABRIX_CLIENT_KEY / FABRIX_OPENAPI_TOKEN 이 필요합니다")
+        elif self.provider == "openai":
+            if not settings.llm_api_key:
+                raise RuntimeError("LLM_BASE_URL / LLM_API_KEY 환경변수가 필요합니다")
+        else:
+            raise RuntimeError(f"알 수 없는 LLM_PROVIDER: {self.provider} (openai | fabrix)")
         self.base = settings.llm_base_url.rstrip("/")
+        self.url = self.base + settings.llm_chat_path
         self.key = settings.llm_api_key
         self.model = settings.llm_model
         # 호출 누적 사용량 — runner가 stats에 실어 보고한다
@@ -66,22 +83,44 @@ class OpenAICompatClient(LLMClient):
                       "retries": 0}
         self._lock = threading.Lock()  # 병렬 호출에서 usage 집계가 어긋나지 않게
 
-    def _post_once(self, system: str, user: str) -> dict:
+    def headers(self) -> dict:
+        h = {"Content-Type": "application/json"}
+        if self.provider == "fabrix":
+            token = settings.fabrix_openapi_token.strip()
+            if not token.lower().startswith("bearer "):
+                token = "Bearer " + token   # 날것으로 보내면 401 (팀원 실측)
+            h.update({
+                "x-openapi-token": token,
+                "x-generative-ai-client": settings.fabrix_client_key,
+                "x-llm-model-id": self.model,
+                "x-generative-ai-user-email": settings.fabrix_user_email,
+            })
+        else:
+            h["Authorization"] = f"Bearer {self.key}"
+        return h
+
+    def body(self, system: str, user: str) -> dict:
         body = {
-            "model": self.model,
+            "model": settings.llm_body_model or self.model,
             "temperature": 0.1,
             "messages": [
                 {"role": "system", "content": system},
                 {"role": "user", "content": user},
             ],
-            "response_format": {"type": "json_object"},
         }
+        if settings.llm_json_mode:
+            body["response_format"] = {"type": "json_object"}
+        if settings.llm_max_tokens > 0:
+            body["max_tokens"] = settings.llm_max_tokens
         if "openrouter" in self.base:
             body["usage"] = {"include": True}  # OpenRouter 확장 — usage.cost(USD 크레딧) 포함
+        return body
+
+    def _post_once(self, system: str, user: str) -> dict:
         req = urllib.request.Request(
-            f"{self.base}/chat/completions",
-            data=json.dumps(body).encode("utf-8"),
-            headers={"Authorization": f"Bearer {self.key}", "Content-Type": "application/json"},
+            self.url,
+            data=json.dumps(self.body(system, user), ensure_ascii=False).encode("utf-8"),
+            headers=self.headers(),
             method="POST",
         )
         with urllib.request.urlopen(req, timeout=settings.llm_timeout_s) as res: