Upload streamlit_app.py

streamlit_app.py

@@ -1,9 +1,9 @@
-# streamlit_app.py — Motion Path Planner (Frontend, Public HF Space)
-# Talks to backend FastAPI: /health, /constraints/upload, /constraints/reset,
-# /detect, /plan, /plan_report, /analyze_xyz
+# streamlit_app.py — AI Motion Path Planner (Frontend)
+# Konuştuğu backend FastAPI uçları:
+# /health, /constraints/upload, /constraints/reset, /detect, /plan, /plan_report, /analyze_xyz
 
 import os, io, uuid, base64, requests
-from typing import List, Tuple, Optional
+from typing import List, Tuple, Optional, Dict, Any
 from PIL import Image, ImageDraw, ImageFont, ImageOps
 import streamlit as st
 
@@ -34,6 +34,7 @@ _defaults = {
     "primary_labels": ["plate", "food"],
     "extra_labels": "",
     "box_pick": "Highest score",  # "Highest score", "Largest area", "Center-most"
+    "want_notes": True,
 }
 for k, v in _defaults.items():
     st.session_state.setdefault(k, v)
@@ -80,13 +81,11 @@ def _center_crop_aspect(img: Image.Image, target_ratio: float) -> Image.Image:
         y0 = (H - new_h) // 2
         return img.crop((0, y0, W, y0 + new_h))
 
-def _preprocess_image(file, target_w=1280, target_h=720,
-                      aspect_mode="16:9 crop") -> Image.Image:
+def _preprocess_image(file, target_w=1280, target_h=720, aspect_mode="16:9 crop") -> Image.Image:
     img = Image.open(file).convert("RGB")
     if aspect_mode in _ASPECTS:
         img = _center_crop_aspect(img, _ASPECTS[aspect_mode])
-    # Esnetme yok — sadece yüksek kaliteli resize
-    img = img.resize((target_w, target_h), Image.Resampling.LANCZOS)
+    img = img.resize((target_w, target_h), Image.Resampling.LANCZOS)  # esnetme yok: önce crop, sonra resize
     return img
 
 def _b64_from_pil(img: Image.Image, jpeg_quality=90) -> str:
@@ -94,8 +93,7 @@ def _b64_from_pil(img: Image.Image, jpeg_quality=90) -> str:
     img.save(buf, format="JPEG", quality=int(jpeg_quality))
     return base64.b64encode(buf.getvalue()).decode("utf-8")
 
-def _b64_from_file(file, target_w=1280, target_h=720, jpeg_quality=90,
-                   aspect_mode="16:9 crop") -> Tuple[str, Image.Image]:
+def _b64_from_file(file, target_w=1280, target_h=720, jpeg_quality=90, aspect_mode="16:9 crop") -> Tuple[str, Image.Image]:
     img = _preprocess_image(file, target_w, target_h, aspect_mode)
     return _b64_from_pil(img, jpeg_quality), img
 
@@ -170,7 +168,7 @@ def _detect_boxes_backend(image_b64: str, labels: List[str]) -> Optional[dict]:
 # ================= Sidebar (backend + constraints) =================
 with st.sidebar:
     st.title("Backend")
-    st.caption("Point to your private backend Space.")
+    st.caption("Private backend URL’inizi girin.")
     url_in = st.text_input("Backend URL", value=st.session_state["API_BASE"],
                            placeholder="https://<org>-backend.hf.space")
     colb1, colb2 = st.columns([1,1])
@@ -179,16 +177,19 @@ with st.sidebar:
         _success(f"Using {st.session_state['API_BASE']}")
         st.rerun()
     if colb2.button("Health"):
-        r = _get("/health")
-        if r.status_code == 200:
-            _success("Backend reachable.")
-            st.json(r.json(), expanded=False)
-        else:
-            _err(f"{r.status_code}: {r.text[:300]}")
+        try:
+            r = _get("/health")
+            if r.status_code == 200:
+                _success("Backend reachable.")
+                st.json(r.json(), expanded=False)
+            else:
+                _err(f"{r.status_code}: {r.text[:300]}")
+        except Exception as e:
+            _err(str(e))
 
     st.markdown("---")
     st.subheader("Rig Limits (export.txt)")
-    st.caption("Upload Flair export to enforce hardware constraints.")
+    st.caption("Flair export.txt yükleyin; hız/ivme/jerk ve açı limitleri uygulanır.")
     export_file = st.file_uploader("Upload export.txt", type=["txt"], key="exp_txt")
     cola, colb = st.columns(2)
     with cola:
@@ -199,11 +200,7 @@ with st.sidebar:
                 r = _post_file("/constraints/upload", "file", export_file.read(), export_file.name)
                 if r.status_code == 200:
                     _success("Constraints loaded.")
-                    data = r.json()
-                    st.json(data.get("parsed", {}), expanded=False)
-                    if "parser_log" in data:
-                        with st.expander("Parser log (constraints)"):
-                            st.json(data["parser_log"], expanded=False)
+                    st.json(r.json(), expanded=False)
                 else:
                     _err(f"{r.status_code}: {r.text[:300]}")
     with colb:
@@ -215,16 +212,16 @@ with st.sidebar:
                 _err(f"{r.status_code}: {r.text[:300]}")
 
 # ================= Main =================
-st.title("Motion Path Planner for Flair")
-st.caption("Describe the camera move in English. Get a rig-checked `.xyz` path.")
+st.title("AI Motion Path Planner for Flair")
+st.caption("İngilizce komutla kamera hareketini tarif edin; AI planı .xyz olarak üretir, rig limitlerine göre kontrol eder.")
 
 with st.expander("How it works"):
     st.markdown(
         """
-1) Upload a camera image.  
-2) Describe the move (e.g., “Orbit 90° in 4s, jib up 0.6 m, radius 0.5 m”).  
-3) Generate a `.xyz` compatible with Flair.  
-Optionally load `export.txt` in the sidebar to enforce rig limits.
+1) Bir kamera görseli yükleyin.  
+2) Hareketi tarif edin (örn: “Orbit 90° in 4s, jib up 0.6 m, radius 0.5 m, 25 fps”).  
+3) **Generate + Report** ile AI yorumlarını, kinematik tepe değerleri ve kısıt kontrollerini görün.  
+4) **Generate Path** ile `.xyz`’yi indirin.
         """
     )
 
@@ -254,16 +251,16 @@ with col_img:
     img_file = st.file_uploader("Camera image (JPG/PNG)", type=["jpg","jpeg","png"], key="scene")
 with col_text:
     presets = [
-        "Orbit 90° in 4 seconds, jib up 0.6 m, radius 0.5 m, keep subject centered.",
-        "Quick push-in 0.2 m over 3 seconds, then 40° orbit right, keep subject in frame.",
-        "Fast start, soft finish, orbit -60° in 3.5 seconds, jib down 0.2 m."
+        "Orbit 90° in 4 seconds, jib up 0.6 m, radius 0.5 m, keep subject centered, 25 fps.",
+        "Quick push-in 0.2 m over 3 seconds, then 40° orbit right, keep subject in frame, 25 fps.",
+        "Fast start, soft finish, orbit -60° in 3.5 seconds, jib down 0.2 m, 25 fps."
     ]
     preset_pick = st.selectbox("Presets (optional)", options=["(none)"] + presets, index=0)
     instr = st.text_area(
         "Describe the move",
         value=(preset_pick if preset_pick != "(none)" else ""),
         height=110,
-        placeholder="Example: Orbit 90° in 4s, jib up 0.6 m, radius 0.45 m, keep subject centered."
+        placeholder="Example: Orbit 90° in 4s, jib up 0.6 m, radius 0.45 m, 25 fps."
     )
 
     st.markdown("**Subject labels**")
@@ -284,6 +281,7 @@ with col_text:
         ["Highest score", "Largest area", "Center-most"],
         index=["Highest score", "Largest area", "Center-most"].index(st.session_state["box_pick"])
     )
+    st.session_state["want_notes"] = st.checkbox("Show AI Notes in report", value=bool(st.session_state["want_notes"]))
 
 def _gather_labels() -> List[str]:
     labels = list(st.session_state.get("primary_labels") or [])
@@ -302,7 +300,6 @@ if img_file:
     with det_card:
         st.subheader("Preview")
         st.caption("Subject placement and detection overlay.")
-
         boxes_img = None
         try:
             labels = _gather_labels() or ["subject"]
@@ -317,8 +314,7 @@ if img_file:
         except Exception as e:
             _warn(f"Detection preview issue: {e}")
 
-        # Esnetmeden, kullanışlı genişlikte göster (aspect otomatik korunur)
-        max_w = 900
+        max_w = 900  # Sayfayı taşırmadan büyük göster
         if boxes_img is not None:
             st.image(boxes_img, caption="Detection overlay", width=max_w)
         else:
@@ -346,7 +342,12 @@ def _payload_prebuilt():
         aspect_mode=st.session_state["aspect_mode"],
     )
     labels = _gather_labels() or ["subject"]
-    return {"instruction": instr.strip(), "image_b64": img_b64, "detect_query": ", ".join(labels)}
+    return {
+        "instruction": instr.strip(),
+        "image_b64": img_b64,
+        "detect_query": ", ".join(labels),
+        "want_notes": bool(st.session_state["want_notes"]),
+    }
 
 # Generate-only
 if btn_generate and _require_inputs():
@@ -368,9 +369,6 @@ if btn_generate and _require_inputs():
             data = r.json()
             st.error("Violated constraints:"); st.write(data.get("violated", []))
             st.info("Suggestions:"); st.write(data.get("suggestions", []))
-            if "parser_log" in data:
-                with st.expander("Parser log (instruction)"):
-                    st.json(data["parser_log"], expanded=False)
         except Exception:
             _err(r.text[:600])
     else:
@@ -383,6 +381,8 @@ if btn_report and _require_inputs():
     if r.status_code == 200:
         data = r.json()
         _success("Report ready.")
+
+        # Metrics
         m1, m2, m3 = st.columns(3)
         with m1:
             st.metric("Orbit requested (deg)", f"{data.get('orbit_requested', 0):.1f}")
@@ -394,14 +394,38 @@ if btn_report and _require_inputs():
             st.metric("Duration (s)", f"{data.get('duration_s', 0):.2f}")
             st.metric("FPS", f"{data.get('fps', 0)}")
 
+        # Kinematics
+        kin = data.get("kinematics", {}) or {}
+        st.subheader("Kinematics (Pan)")
+        colk1, colk2, colk3, colk4 = st.columns(4)
+        colk1.metric("Max Speed (°/s)", f"{kin.get('pan_max_dps', 0.0):.2f}")
+        colk2.metric("Max Acc (°/s²)", f"{kin.get('pan_max_dps2', 0.0):.2f}")
+        colk3.metric("Max Jerk (°/s³)", f"{kin.get('pan_max_dps3', 0.0):.2f}")
+        colk4.metric("Avg Speed (°/s)", f"{kin.get('pan_avg_dps', 0.0):.2f}")
+
+        # Constraints result
         ok = bool(data.get("constraints_passed", False))
         st.markdown(f"**Constraints:** {'✅ Passed' if ok else '❌ Failed'}")
         if not ok:
             st.error("Violated constraints:"); st.write(data.get("violated", []))
             st.info("Suggestions:"); st.write(data.get("suggestions", []))
-        if "parser_log" in data:
-            with st.expander("Parser log (instruction)"):
-                st.json(data["parser_log"], expanded=False)
+
+        # Detection summary
+        with st.expander("Detection summary"):
+            st.json(data.get("detection_summary", {}), expanded=False)
+
+        # AI Notes (UI’da görünür)
+        ai_notes = data.get("ai_notes", []) or []
+        if ai_notes:
+            st.subheader("AI Notes")
+            for n in ai_notes:
+                st.write(f"• {n}")
+        else:
+            st.caption("AI Notes unavailable (no key or parsing fallback).")
+
+        # Param kaynağı
+        st.caption(f"Param source: {data.get('param_source', 'unknown')}")
+
         st.caption("Use “Generate Path (.xyz)” to download the file.")
     else:
         _err(f"{r.status_code}: {r.text[:600]}")
@@ -409,7 +433,7 @@ if btn_report and _require_inputs():
 # ---------- Analyze existing .xyz ----------
 st.markdown("---")
 st.subheader("Analyze a .xyz file")
-st.caption("Upload a Flair .xyz to inspect duration, FPS, orbit and jib.")
+st.caption("Flair `.xyz` yükleyin; süre, FPS, orbit, jib ve kinematik pikleri görün.")
 xyz_up = st.file_uploader("Upload .xyz", type=["xyz"], key="xyz_file")
 if xyz_up and st.button("Analyze"):
     with st.spinner("Analyzing…"):
@@ -425,5 +449,6 @@ st.markdown("---")
 st.caption(
     "Set env vars in this Space:\n"
     "• MotionPath_AI_API = https://<your-private-backend>.hf.space\n"
-    "• MotionPath_AI_TOKEN = <same token as backend>"
-)
+    "• MotionPath_AI_TOKEN = <same token as backend>\n"
+    "This app shows concise **AI Notes** (not chain-of-thought)."
+)