Upload app.py

app.py

@@ -1,12 +1,16 @@
 # app.py — DiagStudio AI (Streamlit frontend)
-# Works with the FastAPI backend you just built (single composite image + JSON mode).
-# Configure the backend URL via:
-#   CARDIAG_AI_API  (or AI_LIGHTBOX_API / LUXFIT_API)
-# Optional auth header passthrough:
-#   CARDIAG_AI_TOKEN (or AI_LIGHTBOX_TOKEN / LUXFIT_TOKEN)
+# Pairs with the FastAPI backend you built (composite image + JSON mode).
+# Configure the backend URL via one of:
+#   CARDIAG_AI_API  (preferred)  |  AI_LIGHTBOX_API  |  LUXFIT_API
+# Optional bearer auth passthrough:
+#   CARDIAG_AI_TOKEN | AI_LIGHTBOX_TOKEN | LUXFIT_TOKEN
+#
+# Run (example):
+#   CARDIAG_AI_API="https://<your-private-backend>" streamlit run app.py --server.port 7860
 
 import os, io, json, time, base64, requests, hashlib
-# Prevent /.streamlit permission issues on HF Spaces/containers
+
+# Avoid /.streamlit permission errors on containers/HF
 os.environ.setdefault("HOME", "/tmp")
 os.environ.setdefault("STREAMLIT_BROWSER_GATHER_USAGE_STATS", "false")
 os.environ.setdefault("STREAMLIT_SERVER_HEADLESS", "true")
@@ -24,7 +28,8 @@ except Exception:
     pass
 
 # ================= Env & API =================
-def _env(k): return (os.getenv(k) or "").strip().strip("'\"")
+def _env(k: str) -> str:
+    return (os.getenv(k) or "").strip().strip("'\"")
 
 API_BASE = (
     _env("CARDIAG_AI_API") or _env("AI_LIGHTBOX_API") or _env("LUXFIT_API")
@@ -38,15 +43,15 @@ st.title("DiagStudio AI")
 st.caption("Upload a short engine recording and get a clear diagnosis with visuals and next steps.")
 
 # ================= Helpers =================
-@st.cache_data(show_spinner=False, ttl=20)
-def _health(url, headers):
+@st.cache_data(show_spinner=False, ttl=30)
+def _health(url: str, headers: dict) -> bool:
     try:
         r = requests.get(f"{url}/health", headers=headers, timeout=10)
         return r.status_code == 200
     except Exception:
         return False
 
-def _nice_conf(x):
+def _nice_conf(x) -> float:
     try:
         return min(max(float(x), 0.0), 1.0)
     except Exception:
@@ -58,7 +63,6 @@ def _post_analyze(audio_file, rpm_file, sr_target, n_fft, hop, env_band, run_llm
         files["audio"] = (audio_file.name, audio_file.getvalue(), audio_file.type or "application/octet-stream")
     if rpm_file is not None:
         files["rpm_csv"] = (rpm_file.name, rpm_file.getvalue(), "text/csv")
-
     data = {
         "sr_target": str(sr_target),
         "n_fft": str(n_fft),
@@ -66,14 +70,13 @@ def _post_analyze(audio_file, rpm_file, sr_target, n_fft, hop, env_band, run_llm
         "env_band": env_band,
         "run_llm": "true" if run_llm else "false",
         "extra_text": notes or "",
-        # cache-bypass hint for intermediaries (backend already sets no-store)
-        "nonce": str(time.time())
+        "nonce": str(time.time())  # cache-bypass hint; backend already sets no-store
     }
     r = requests.post(f"{API_BASE}/analyze", headers=HEADERS, files=files, data=data, timeout=240)
     r.raise_for_status()
     return r.json()
 
-def _post_analyze_zip(audio_file, rpm_file, sr_target, n_fft, hop, env_band, run_llm, notes):
+def _post_analyze_zip(audio_file, rpm_file, sr_target, n_fft, hop, env_band, run_llm, notes) -> bytes:
     files = {}
     if audio_file is not None:
         files["audio"] = (audio_file.name, audio_file.getvalue(), audio_file.type or "application/octet-stream")
@@ -99,7 +102,7 @@ with st.sidebar:
     rpm_up = st.file_uploader("Optional RPM CSV (time_sec,rpm)", type=["csv"])
 
     st.header("Options")
-    run_llm = st.toggle("Explain with AI", value=True, help="Adds an easy-to-read diagnosis and next steps.")
+    run_llm = st.toggle("Explain with AI", value=True, help="Get a readable diagnosis and next steps.")
     user_notes = st.text_area("Context (optional)", placeholder="Vehicle, engine type, driving condition, symptoms…")
 
     with st.expander("Advanced (defaults are fine)"):
@@ -112,10 +115,10 @@ with st.sidebar:
         st.error("Backend URL is not set. Define CARDIAG_AI_API (or AI_LIGHTBOX_API / LUXFIT_API).")
     ok = _health(API_BASE, HEADERS) if API_BASE else False
     if not ok and API_BASE:
-        st.warning("Could not reach the backend. Verify your private Space URL.")
+        st.warning("Could not reach the backend. Check your private Space URL.")
     analyze_btn = st.button("Analyze now", type="primary", disabled=(audio_up is None or not ok))
 
-# ================= Clear old result on file change =================
+# ================= Reset state on file change (prevents stale results) =================
 if "last_audio_id" not in st.session_state:
     st.session_state["last_audio_id"] = None
 if audio_up is not None:
@@ -148,11 +151,10 @@ if res:
     params = res.get("params", {})
     llm = res.get("llm_report") or {}
 
-    # Model name is known from backend params (JSON mode removes auto-added model field)
     model_name = params.get("vision_model", "gpt-4o")
     st.caption(f"AI model: **{model_name}**")
 
-    # Show audio hash and basic features to prove input is unique
+    # Input uniqueness proof + quick features
     if params.get("audio_id"):
         st.caption(f"Audio ID: **{params['audio_id']}**")
     if params.get("features"):
@@ -166,12 +168,11 @@ if res:
         except Exception:
             st.caption(f"Features — {feat}")
 
-    # If model returned meta, show it (proof it saw the image)
+    # Show meta proving Vision read the image
     if isinstance(llm, dict) and llm.get("meta"):
         meta = llm["meta"]
         st.caption(f"Vision meta — seen_images: {meta.get('seen_images')}, views: {meta.get('views')}")
 
-    # Layout
     col1, col2 = st.columns([1, 1])
     diag_list = llm.get("diagnosis", [])
     notes = llm.get("notes", "")