feat/Update_Controllers_to_Allow_for_Premium_Membership

tools/summarizer/app.py

@@ -17,6 +17,7 @@ import torch
 import pytesseract
 from urllib import request as urllib_request
 from urllib.error import URLError, HTTPError
+from contextvars import ContextVar
 
 app = FastAPI(title="Local AI Service")
 
@@ -33,6 +34,8 @@ AI_SERVICE_TOKEN_HEADER = "X-Ai-Service-Token"
 # /health stays open: the backend probe and the compose healthcheck both call it, and it
 # exposes no user data and no generation path.
 AI_SERVICE_OPEN_PATHS = {"/health"}
+EXTERNAL_AI_ALLOWED_HEADER = "X-Ai-External-Allowed"
+_external_ai_allowed = ContextVar("external_ai_allowed", default=False)
 
 
 @app.middleware("http")
@@ -45,7 +48,18 @@ async def require_service_token(request: Request, call_next):
                 {"detail": "Invalid or missing service token."},
                 status_code=401,
             )
-    return await call_next(request)
+    allowed = (
+        EXTERNAL_AI_ENABLED
+        and request.headers.get(EXTERNAL_AI_ALLOWED_HEADER, "").strip().lower() == "true"
+    )
+    token = _external_ai_allowed.set(allowed)
+    try:
+        response = await call_next(request)
+        if request.url.path.startswith("/cv/"):
+            response.headers["X-Ai-Provider"] = _effective_provider()
+        return response
+    finally:
+        _external_ai_allowed.reset(token)
 
 MODEL_NAME = "sshleifer/distilbart-cnn-12-6"
 MAX_INPUT_CHARS = 20000
@@ -61,6 +75,7 @@ OLLAMA_MODEL = os.getenv("OLLAMA_MODEL", "")
 # Default stays "ollama" so the service works keyless/local. /summarize stays local
 # (distilbart) regardless of this setting.
 AI_PROVIDER = (os.getenv("AI_PROVIDER", "ollama").strip().lower() or "ollama")
+EXTERNAL_AI_ENABLED = os.getenv("EXTERNAL_AI_ENABLED", "").strip().lower() in {"1", "true", "yes"}
 GEMINI_API_KEY = os.getenv("GEMINI_API_KEY", "").strip()
 GEMINI_MODEL = os.getenv("GEMINI_MODEL", "gemini-2.0-flash").strip()
 GEMINI_BASE_URL = os.getenv("GEMINI_BASE_URL", "https://generativelanguage.googleapis.com").rstrip("/")
@@ -448,6 +463,12 @@ def _provider_configured() -> bool:
     return bool(OLLAMA_MODEL)
 
 
+def _effective_provider() -> str:
+    if EXTERNAL_AI_ENABLED and _external_ai_allowed.get() and AI_PROVIDER in {"gemini", "groq"}:
+        return AI_PROVIDER
+    return "ollama"
+
+
 def _http_post_json(url: str, payload: dict, headers: dict, timeout: int) -> dict:
     data = json.dumps(payload).encode("utf-8")
     req = urllib_request.Request(
@@ -514,7 +535,7 @@ def _groq_generate(prompt: str, *, json_mode: bool, temperature: float, timeout:
 
 
 def _provider_generate(prompt: str, *, json_mode: bool, temperature: float, timeout: int) -> str:
-    provider = AI_PROVIDER
+    provider = _effective_provider()
     try:
         if provider == "gemini":
             return _gemini_generate(prompt, json_mode=json_mode, temperature=temperature, timeout=timeout)
@@ -530,9 +551,10 @@ def _provider_generate(prompt: str, *, json_mode: bool, temperature: float, time
 
 
 def _ollama_generate_json(prompt: str):
+    provider = _effective_provider()
     raw = _provider_generate(prompt, json_mode=True, temperature=0.1, timeout=120)
     if not raw:
-        raise HTTPException(status_code=502, detail=f"{_provider_display(AI_PROVIDER)} returned an empty response.")
+        raise HTTPException(status_code=502, detail=f"{_provider_display(provider)} returned an empty response.")
     try:
         return json.loads(raw)
     except json.JSONDecodeError:
@@ -540,13 +562,14 @@ def _ollama_generate_json(prompt: str):
         end = raw.rfind("}")
         if start >= 0 and end > start:
             return json.loads(raw[start:end + 1])
-        raise HTTPException(status_code=502, detail=f"{_provider_display(AI_PROVIDER)} did not return valid JSON.")
+        raise HTTPException(status_code=502, detail=f"{_provider_display(provider)} did not return valid JSON.")
 
 
 def _ollama_generate_text(prompt: str) -> str:
+    provider = _effective_provider()
     raw = _provider_generate(prompt, json_mode=False, temperature=0.2, timeout=180)
     if not raw:
-        raise HTTPException(status_code=502, detail=f"{_provider_display(AI_PROVIDER)} returned an empty rewrite.")
+        raise HTTPException(status_code=502, detail=f"{_provider_display(provider)} returned an empty rewrite.")
     return raw