Enhanced golf swing analysis system with professional benchmarks and UI improvements

Major updates:
- Updated coach_prompt.md with 7 LPGA professional swing analyses (Lydia Ko, Nelly Korda, Park Sunghyun, Minjee Lee, Hyoo Joo Kim, Nasa Hataoka)
- Added comprehensive amateur swing issues reference and calibration data
- Implemented automatic AI-generated overall swing summary at top of analysis
- Fixed critical knee flexion calculation bug in llm_analyzer.py (vector calculation error)
- Enhanced UI with subtle developer tools and improved Step 1 video upload tips
- Added professional standards calibration ranges (25-35° back tilt, 16-28° knee flexion)
- Streamlined analysis display with overall summary above metric cards

app/models/coach_prompt.md

@@ -1,101 +1,224 @@
 # Golf Swing Analysis
 
 ## PROFESSIONAL BENCHMARKS FOR CALIBRATION
-Use these professional standards as your 100% reference for scoring. These represent elite-level golf swing mechanics based on actual LPGA Tour professional analysis:
+Use these professional standards as your 100% reference for scoring. These represent elite-level golf swing mechanics based on actual professional analysis:
 
 ### Professional Golfer Analysis Summary (100% Reference Standards):
 
-**Atthaya Thitikul (LPGA Tour - Elite Level):**
-- Hip Rotation: 63.4°, Shoulder Rotation: 120°, Back Tilt: 32°, Knee Bend: 28°
-- Weight Shift: 88.4%, Arm Extension: 99.8%, Wrist Hinge: 120°
-- Energy Transfer: 96.1%, Power Accumulation: 100%, Potential Distance: 295 yards
-- Sequential Kinematic Sequence: 100%, Swing Plane Consistency: 85%
-
-**Nelly Korda (LPGA Tour - Elite Level):**
-- Hip Rotation: 90°, Shoulder Rotation: 120°, Back Tilt: 35°, Knee Bend: 25°
-- Weight Shift: 73.5%, Arm Extension: 96.7%, Wrist Hinge: 114.8°
-- Energy Transfer: 91.2%, Power Accumulation: 100%, Potential Distance: 289 yards
-- Sequential Kinematic Sequence: 100%, Swing Plane Consistency: 85%
-
-**Demi Runas (Professional Level):**
-- Hip Rotation: 63.4°, Shoulder Rotation: 120°, Back Tilt: 30°, Knee Bend: 30°
-- Weight Shift: 63.9%, Arm Extension: 96.6%, Wrist Hinge: 93.4°
-- Energy Transfer: 88.0%, Power Accumulation: 100%, Potential Distance: 286 yards
-- Sequential Kinematic Sequence: 100%, Swing Plane Consistency: 85%
-
-**Rose Zhang (LPGA Tour Professional):**
-- Hip Rotation: 90°, Shoulder Rotation: 120°, Back Tilt: 38°, Knee Bend: 22°
-- Weight Shift: 89.9%, Arm Extension: 79.5%, Wrist Hinge: 112.8°
-- Energy Transfer: 96.6%, Power Accumulation: 100%, Potential Distance: 296 yards
-- Sequential Kinematic Sequence: 100%, Swing Plane Consistency: 85%
-- Speed Generation: Body-dominant
-
-**Lydia Ko (LPGA Tour Professional):**
-- Hip Rotation: 90°, Shoulder Rotation: 120°, Back Tilt: 33°, Knee Bend: 27°
-- Weight Shift: 66.2%, Arm Extension: 62.1%, Wrist Hinge: 120°
-- Energy Transfer: 88.7%, Power Accumulation: 100%, Potential Distance: 286 yards
-- Sequential Kinematic Sequence: 100%, Swing Plane Consistency: 70%
-- Speed Generation: Body-dominant
-
-### **PROFESSIONAL STANDARDS CALIBRATION (100% Level):**
-**Core Biomechanical Metrics:**
-- **Hip Rotation**: 25-90° (Professional range - multiple successful approaches)
-- **Shoulder Rotation**: 60-120° (Professional upper body coil range)
-- **Back Tilt**: 20-40° (Proper spine forward tilt across all professionals)
-- **Knee Bend**: 15-35° (Athletic stance consistency across all professionals)
-- **Weight Shift**: 53-90% (Professional range varies significantly by style)
-
-**Upper Body Excellence:**
-- **Arm Extension**: 62-100% (Wide professional range - Lydia shows low extension can work)
-- **Wrist Hinge**: 93-120° (Optimal lag and release timing)
-- **Swing Plane Consistency**: 70-85% (Professional-level repeatability)
-- **Chest Rotation Efficiency**: 66-100% (Coordination varies by swing style)
-
-**Power & Efficiency Markers:**
-- **Energy Transfer Efficiency**: 65-97% (Wide professional range - multiple successful approaches)
-- **Power Accumulation**: 84-100% (Power generation across all styles)
-- **Sequential Kinematic Sequence**: 69-100% (Professional coordination standards)
-- **Potential Distance**: 242-296 yards (Professional power range)
-
-**Movement Quality Standards:**
-- **Head Movement**: 1-8 inches (Controlled movement varies by professional)
-- **Ground Force Efficiency**: 53-90% (Professional ground interaction range)
-- **Hip Thrust**: 30-100% (Lower body drive varies significantly)
+**Lydia Ko Iron (LPGA Tour Professional):** https://www.youtube.com/shorts/ING2iZ3M8wg
+- Shaft Plane @ Top: Slightly Laid-off — 🟢 Mild laid-off bias — Confidence ~75%
+- Back Tilt @ Setup: 33.9° — 🟢 On-plane posture — Confidence ~85%
+- Knee Flexion: 27.6° — 🟢 Athletic — Confidence ~60%
+- Wrist Pattern: Set-Hold-Release — Excellent — 🟢 — Confidence ~75%
+- Power Source: Hip-Led — 🟢 60% hip power
+- Shoulder Turn Quality: Excellent — 🟢 Complete shoulder rotation — Confidence ~70% DTL-only
+
+Raw values for qualitative assessments - for calibration purposes:
+• Shaft Angle @ Top: -26.2° (status: needs_work)
+• Hip Rotation @ Impact: None° (status: needs_face_on)
+• X-Factor @ Top: None° (status: needs_face_on)
+• Shoulder Rotation @ Top: 45.0° (status: ok)
+
+**Nelly Korda Iron (Pink):** https://www.youtube.com/shorts/GRzaXCNJq1o
+- Shaft Plane @ Top: Neutral — 🟢 Good plane control
+- Back Tilt @ Setup: 34.9° — 🟢 On-plane posture — Confidence ~85%
+- Knee Flexion: 18.7° — 🟢 Athletic — Confidence ~60%
+- Wrist Pattern: Set-Hold-Release — Excellent — 🟢 — Confidence ~75%
+- Power Source: Hip-Led — 🟢 60% hip power
+- Shoulder Turn Quality: Excellent — 🟢 Complete shoulder rotation — Confidence ~70% DTL-only
+
+Raw values for qualitative assessments - for calibration purposes:
+• Shaft Angle @ Top: None° (status: club_not_visible)
+• Hip Rotation @ Impact: None° (status: needs_face_on)
+• X-Factor @ Top: None° (status: needs_face_on)
+• Shoulder Rotation @ Top: 45.0° (status: ok)
+
+**Nelly Korda Iron (Blue):** https://www.youtube.com/shorts/M1eaHdaSzh4
+- Shaft Plane @ Top: Neutral — 🟢 Good plane control
+- Back Tilt @ Setup: 31.2° — 🟢 On-plane posture — Confidence ~85%
+- Knee Flexion: 16.4° — 🟢 Athletic — Confidence ~60%
+- Wrist Pattern: Set-Hold-Release — Excellent — 🟢 — Confidence ~75%
+- Power Source: Hip-Led — 🟢 60% hip power
+- Shoulder Turn Quality: Excellent — 🟢 Complete shoulder rotation — Confidence ~70% DTL-only
+
+Raw values for qualitative assessments - for calibration purposes:
+• Shaft Angle @ Top: None° (status: club_not_visible)
+• Hip Rotation @ Impact: None° (status: needs_face_on)
+• X-Factor @ Top: None° (status: needs_face_on)
+• Shoulder Rotation @ Top: 45.0° (status: ok)
+
+**Park Sunghyun Iron:** https://www.youtube.com/shorts/imtyz_n06gA
+- Back Tilt @ Setup: 29.2° — 🟢 On-plane posture — Confidence ~90%
+- Knee Flexion: 25.9° — 🟢 Athletic — Confidence ~90%
+- Wrist Pattern: Inconsistent Pattern — 🟠 — Confidence ~75% approx.
+💡 Tip: Work on consistent wrist angles.
+- Kinematic Sequence (DTL-approx): Good Hip Turn — 🟢 Good hip rotation DTL-only
+- Shoulder Turn Quality: Excellent — 🟢 Complete shoulder rotation — Confidence ~70% approx. DTL-only
+
+Raw values for qualitative assessments - for calibration purposes:
+• Shaft Angle @ Top: None° (status: Unavailable (club occluded))
+• Hip Rotation @ Impact: None° (status: needs_face_on)
+• X-Factor @ Top: None° (status: needs_face_on)
+• Shoulder Rotation @ Top: None° (status: DTL proxy only, low confidence)
+
+**Minjee Lee Driver:** https://www.youtube.com/shorts/Ioo3VSiCUhs
+- Back Tilt @ Setup: 27.6° — 🟠 Slightly out of range — Confidence ~90%
+- Knee Flexion: 24.8° — 🟢 Athletic — Confidence ~90%
+- Wrist Pattern: Set-Hold-Release — Excellent — 🟢 Needs work — Confidence ~75% approx.
+- Kinematic Sequence (DTL-approx): Good Hip Turn — 🟢 Good hip rotation
+- Shoulder Turn Quality: Excellent — 🟢 Complete shoulder rotation — Confidence ~70% approx. DTL-only
+
+Raw values for qualitative assessments - for calibration purposes:
+• Shaft Angle @ Top: None° (status: Unavailable (club occluded))
+• Hip Rotation @ Impact: None° (status: needs_face_on)
+• X-Factor @ Top: None° (status: needs_face_on)
+• Shoulder Rotation @ Top: None° (status: DTL proxy only, low confidence)
+
+**Hyoo Joo Kim Iron:** https://www.youtube.com/watch?v=zDheOLEEmdU&t=7s
+- Back Tilt @ Setup: 27.3° — 🟠 Slightly out of range — Confidence ~90%
+- Knee Flexion: 26.8° — 🟢 Athletic — Confidence ~90%
+- Wrist Pattern: Set-Hold-Release — Excellent — 🟢 Needs work — Confidence ~75% approx.
+- Kinematic Sequence (DTL-approx): Good Hip Turn — 🟢 Good hip rotation
+- Shoulder Turn Quality: Excellent — 🟢 Complete shoulder rotation — Confidence ~70% approx. DTL-only
+
+Raw values for qualitative assessments - for calibration purposes:
+• Shaft Angle @ Top: None° (status: target_line_error)
+• Hip Rotation @ Impact: None° (status: needs_face_on)
+• X-Factor @ Top: None° (status: needs_face_on)
+• Shoulder Rotation @ Top: None° (status: DTL proxy only, low confidence)
+
+**Nasa Hataoka Iron:** https://www.youtube.com/shorts/sMqEwl1Tfus
+- Back Tilt @ Setup: 25.3° — 🟠 Slightly out of range — Confidence ~90%
+- Knee Flexion: 24.1° — 🟢 Athletic — Confidence ~90%
+- Wrist Pattern: Set-Hold-Release — Excellent — 🟢 Needs work — Confidence ~75% approx.
+- Kinematic Sequence (DTL-approx): Good Hip Turn — 🟢 Good hip rotation
+- Shoulder Turn Quality: Excellent — 🟢 Complete shoulder rotation — Confidence ~70% approx. DTL-only
+
+Raw values for qualitative assessments - for calibration purposes:
+• Shaft Angle @ Top: None° (status: target_line_error)
+• Hip Rotation @ Impact: None° (status: needs_face_on)
+• X-Factor @ Top: None° (status: needs_face_on)
+• Shoulder Rotation @ Top: None° (status: DTL proxy only, low confidence)
 
 ### **AMATEUR REFERENCE EXAMPLES FOR CALIBRATION:**
 
-**70% Level Skilled Amateur (Female):**
-- Hip Rotation: 23.0°, Shoulder Rotation: 120° (Excellent shoulder turn, limited hip mobility)
-- Back Tilt: 35°, Knee Bend: 25°, Weight Shift: 90.0% (Strong fundamentals)
-- Arm Extension: 99.8%, Wrist Hinge: 49.4° (Great extension, needs more lag)
-- Energy Transfer: 94.5%, Power Accumulation: 82.1% (Very good coordination)
-- Potential Distance: 273 yards, Sequential Kinematic: 93.6%
-- Head Movement: 8.0in lateral, 6.0in vertical (Excessive movement)
-- Speed Generation: Mixed
-
-**50-60% Level Amateur (Female - Arms-Dominant):**
-- Hip Rotation: 25°, Shoulder Rotation: 60° (Limited body rotation)
-- Back Tilt: 45°, Knee Bend: 12°, Weight Shift: 50.0% (Needs improvement)
-- Arm Extension: 94.8%, Wrist Hinge: 116.6° (Good extension, excellent lag)
-- Energy Transfer: 56.8%, Power Accumulation: 89.3% (Mixed efficiency)
-- Potential Distance: 241 yards, Sequential Kinematic: 66.8%
-- Head Movement: 3.0in lateral, 2.0in vertical (Good head control)
-- Ground Force: 50.0%, Hip Thrust: 30.0% (Weak lower body)
-- Speed Generation: Arms-dominant
-
-**CRITICAL INSIGHTS FROM PROFESSIONAL AND AMATEUR ANALYSIS:**
-1. **Hip Rotation Shows Variation**: Professionals range from 63-90°, with moderate rotation (63°) and full rotation (90°) both achieving elite results
-2. **Shoulder Rotation Critical Threshold**: 120° consistently achieved by all professionals, showing this as the elite standard
-3. **Multiple Successful Swing Styles**: Body-dominant swings both achieve elite results with different hip mobility approaches
-4. **Posture Consistency Universal**: All professionals maintain 20-40° back tilt and 15-35° knee bend regardless of swing style
-5. **Arm Extension Varies Dramatically**: Professional range 62-100% shows that both high extension (96-100%) and compact swings (62%) can be highly effective
-6. **Energy Transfer Multiple Pathways**: Range from 88-97% in professionals, showing consistent high-level power generation approaches
-7. **Power Accumulation Excellence**: All professionals achieve 100% efficiency, showing this as the elite standard
-8. **Distance Generation Diversity**: Professional distances range 285-296 yards through different mechanical approaches
-9. **Weight Transfer Success Patterns**: Professional range 63-90% shows multiple effective weight shift strategies
-10. **Sequential Timing Excellence**: Professional kinematic sequence consistently at 100%, showing perfect coordination as the standard
-11. **Wrist Hinge Consistency**: Professionals range 93-120°, showing different but effective lag and release strategies
-12. **Ground Force Utilization Excellence**: Range 63-90% with elite players achieving consistent high efficiency through proper lower body mechanics
+**90% Amateur Swing:**
+Known problems: Wrist casting during downswing/impact, lacks powerful hip rotation, possibly too much knee flex
+- Shaft Plane @ Top: Neutral — 🟢 Good plane control — Confidence ~85%
+- Back Tilt @ Setup: 69.4° — 🔴 Likely problematic — Confidence ~60% - detected wrong
+💡 Tip: Typical tour range ≈30–40°.
+- Knee Flexion: 26.0° — 🟢 Athletic — Confidence ~60%
+- Wrist Pattern: Set-Hold-Release — Excellent — 🟢 — Confidence ~75%
+- Power Source: Hip-Led — 🟢 60% hip power
+- Shoulder Turn Quality: Excellent — 🟢 Complete shoulder rotation — Confidence ~70% DTL-only
+
+Raw values for qualitative assessments - for calibration purposes:
+• Shaft Angle @ Top: -6.8° (status: good)
+• Hip Rotation @ Impact: None° (status: needs_face_on)
+• X-Factor @ Top: None° (status: needs_face_on)
+• Shoulder Rotation @ Top: 45.0° (status: ok)
+
+**40-50% Male Amateur Swing:**
+Known problems: Standing up during impact, head movement severe, bent arms in follow through, inconsistent swing path and ball contact, wrong stance because the club is too short for his height, some wrist casting during impact
+- Back Tilt @ Setup: 39.0° — 🟠 Slightly out of range — Confidence ~90%
+- Knee Flexion: 39.4° — 🟠 Too bent — Confidence ~90%
+- Wrist Pattern: Set-Hold-Release — Excellent — 🟢 Needs work — Confidence ~75% approx.
+- Kinematic Sequence (DTL-approx): Good Hip Turn — 🟢 Good hip rotation
+- Shoulder Turn Quality: Excellent — 🟢 Complete shoulder rotation — Confidence ~70% approx. DTL-only
+
+Raw values for qualitative assessments - for calibration purposes:
+• Shaft Angle @ Top: None° (status: target_line_error)
+• Hip Rotation @ Impact: None° (status: needs_face_on)
+• X-Factor @ Top: None° (status: needs_face_on)
+• Shoulder Rotation @ Top: None° (status: DTL proxy only, low confidence)
+
+**40-50% Female Amateur Swing:**
+Known problems: Hands keep going at the top of backswing when they should stop, wrist casting, hands leading downswing not hips, standing up during impact, head movement
+- Knee Flexion: 33.8° — 🟠 Slightly too bent — Confidence ~90%
+- Wrist Pattern: Inconsistent Pattern — 🟠 Needs work — Confidence ~75% approx.
+💡 Tip: Work on consistent wrist angles.
+- Kinematic Sequence (DTL-approx): Good Hip Turn — 🟢 Good hip rotation
+- Shoulder Turn Quality: Excellent — 🟢 Complete shoulder rotation — Confidence ~70% approx. DTL-only
+
+Raw values for qualitative assessments - for calibration purposes:
+• Shaft Angle @ Top: None° (status: target_line_error)
+• Hip Rotation @ Impact: None° (status: needs_face_on)
+• X-Factor @ Top: None° (status: needs_face_on)
+• Shoulder Rotation @ Top: None° (status: DTL proxy only, low confidence)
+
+### **KEY AMATEUR SWING PROBLEMS FOR EVALUATION REFERENCE:**
+**Common Issues in 40-50% Level Swings:**
+- **Standing up during impact** (loss of posture maintenance)
+- **Severe head movement** (stability and consistency issues)
+- **Wrist casting** (early release, loss of lag)
+- **Hands leading downswing instead of hips** (poor kinematic sequence)
+- **Excessive knee flexion** (39.4° male, 33.8° female vs 16-28° professional range)
+- **Back tilt out of professional range** (39.0° vs 25-35° professional range)
+- **Inconsistent swing path and ball contact**
+- **Equipment issues** (wrong club length affecting stance and mechanics)
+- **Bent arms in follow through** (loss of extension and power)
+- **Hands continuing at top when they should stop** (over-swing, timing issues)
+
+**Evaluation Emphasis Points:**
+- Knee flexion >35° should be flagged as problematic for power and stability
+- Back tilt >35° indicates setup issues that affect entire swing
+- Wrist casting patterns significantly impact ball striking and distance
+- Head movement and standing up during impact are major consistency killers
+- Poor kinematic sequence (hands before hips) reduces power generation
+
+### **COMPREHENSIVE AMATEUR SWING ISSUES REFERENCE:**
+
+**Swing Mechanics & Tempo Issues:**
+1. **Over-Swinging:**
+   - Swinging with excessive force leads to loss of control and poor tempo
+   - Makes it harder to stay connected and achieve consistent contact
+   - Often results in loss of balance and timing
+
+2. **Over-the-Top Swing Path:**
+   - Golfer starts downswing from the outside, causing club to swing across the ball
+   - Results in pulls, slices, and inconsistent ball striking
+   - Common in amateur swings due to improper sequencing
+
+3. **Lack of Weight Transfer:**
+   - Not shifting weight from back foot to lead foot during downswing
+   - Reduces power generation and can cause inconsistent contact
+   - Often combined with poor hip rotation
+
+4. **Poor Rotation & Early Extension:**
+   - Lack of proper body rotation through the swing
+   - Hips moving towards the ball during downswing (early extension)
+   - Leads to loss of posture and inconsistent strike patterns
+
+5. **"Lifting" the Ball:**
+   - Attempting to lift the ball into the air rather than hitting down and through
+   - Common counter-intuitive mistake that leads to poor contact
+   - Results in topped shots and inconsistent ball flight
+
+6. **Wrist Casting:**
+   - Early release of wrist hinge, reducing power and distance
+   - Loss of lag angle that professionals maintain
+   - Significantly impacts ball compression and distance
+
+7. **Moving Head/Standing Up in Swing:**
+   - Loss of spine angle and posture during swing
+   - Creates inconsistent contact points
+   - Major factor in amateur swing inconsistency
+
+**Impact on Evaluation:**
+- Look for combinations of these issues in amateur swings
+- Multiple issues often compound each other (e.g., over-swinging + early extension)
+- Early extension and standing up are visible in DTL analysis as posture loss
+- Weight transfer issues may manifest as poor hip rotation or kinematic sequence problems
+- Over-the-top swing path affects shaft plane and swing consistency
+
+### **PROFESSIONAL STANDARDS CALIBRATION (100% Level):**
+**Core Biomechanical Metrics (Based on 7 LPGA Tour Professionals):**
+- **Back Tilt @ Setup**: 25-35° (Professional range: Nasa 25.3° to Nelly Blue 34.9°)
+- **Knee Flexion**: 16-28° (Professional range: Nelly Blue 16.4° to Lydia Ko 27.6°)
+- **Shaft Plane @ Top**: Neutral to slightly laid-off (Professional plane control when visible)
+- **Wrist Pattern**: Set-Hold-Release sequence (Excellent timing and control across all professionals)
+- **Power Source**: Hip-Led 60% hip power (Professional power generation standard)
+- **Shoulder Turn Quality**: Excellent complete rotation (Consistent across all professionals)
 
 ## CURRENT SWING ANALYSIS
 
@@ -110,6 +233,8 @@ Use these professional standards as your 100% reference for scoring. These repre
 **GOLF SWING ANALYSIS FORMAT**
 Use the benchmarks above to guide your evaluation. Follow this exact format:
 
+**OVERALL_SUMMARY:** [1-2 sentences maximum providing a concise evaluation of the swing's overall quality and main strengths/areas for improvement]
+
 **PERFORMANCE_CLASSIFICATION:** [XX%]
 (XX = number from 10% to 100%)
 
@@ -120,7 +245,7 @@ For each of the 5 DTL-reliable core metrics below, write exactly 3 sentences eva
 2. Second sentence: Compare the specific value to professional ranges  
 3. Third sentence: Brief explanation of impact on swing performance
 
-**1. Shaft Angle @ Top Evaluation:**
+**1. Shaft Plane @ Top Evaluation:**
 [3 sentences about club shaft position relative to target line at top]
 
 **2. Head Sway Evaluation:**
@@ -129,7 +254,7 @@ For each of the 5 DTL-reliable core metrics below, write exactly 3 sentences eva
 **3. Back Tilt @ Setup Evaluation:**
 [3 sentences about spine forward tilt angle during setup position]
 
-**4. Knee Bend @ Setup Evaluation:**
+**4. Knee Flexion @ Setup Evaluation:**
 [3 sentences about knee flexion angle during setup position]
 
 **5. Wrist Pattern Evaluation:**
@@ -137,13 +262,13 @@ For each of the 5 DTL-reliable core metrics below, write exactly 3 sentences eva
 
 **SCORING GUIDELINES (Use to help decide % score)**
 
-| Metric | Professional Standard | Note |
-|--------|----------------------|------|
-| Shaft Angle @ Top | ±5° | Neutral (0°), across (+), laid-off (-) |
-| Head Sway | <15% shoulder width | Stable head during swing |
-| Back Tilt @ Setup | 20-40° | Forward spine tilt from vertical |
-| Knee Bend @ Setup | 15-35° | Athletic stance flexion |
-| Wrist Pattern | Good sequence, no casting | Set→hold→release timing |
+| Metric | Professional Standard | Amateur Problem Indicators | Note |
+|--------|----------------------|---------------------------|------|
+| Shaft Angle @ Top | Neutral to slightly laid-off | N/A (often not visible) | Neutral (0°), slightly laid-off (-26°) acceptable |
+| Head Sway | <15% shoulder width | Severe movement (40-50% level) | Stable head during swing |
+| Back Tilt @ Setup | 25-35° | >35° problematic (39° seen in 40-50% level) | Forward spine tilt from vertical |
+| Knee Flexion @ Setup | 16-28° | >35° problematic (33-39° seen in 40-50% level) | Athletic stance flexion |
+| Wrist Pattern | Set-Hold-Release sequence | Casting, inconsistent patterns | Excellent timing and control, no early casting |
 
 **Classification Bands:**
 - **90–100%**: Tour-level
@@ -155,12 +280,15 @@ For each of the 5 DTL-reliable core metrics below, write exactly 3 sentences eva
 - **10–39%**: Novice
 
 **STYLE & FORMATTING RULES:**
-- Use these headers: PERFORMANCE_CLASSIFICATION, Metric Evaluations, and the 5 numbered metric sections
-- No emojis anywhere in the response
+- Use these headers: OVERALL_SUMMARY, PERFORMANCE_CLASSIFICATION, Metric Evaluations, and the 5 numbered metric sections
+- No emojis anywhere in the response  
+- Write 1-2 sentences maximum for the overall summary - be concise and highlight main strengths/improvement areas
 - Write exactly 3 sentences for each metric evaluation
-- Tie all evaluations to professional standards and ranges
+- Tie all evaluations to professional standards and ranges based on 7 LPGA Tour professionals (Lydia Ko, Nelly Korda, Park Sunghyun, Minjee Lee, Hyoo Joo Kim, Nasa Hataoka)
 - Use a positive, coaching tone throughout
 - Avoid saying "perfect" — say "strong" or "meets standards"
-- Focus on biomechanics and compare actual values to pro ranges
+- Focus on biomechanics and compare actual values to professional ranges (25-35° back tilt, 16-28° knee flexion, etc.)
+- Consider common amateur swing issues when evaluating: over-swinging, over-the-top path, lack of weight transfer, early extension, lifting the ball, wrist casting, head movement/standing up
+- Look for combinations of swing problems that often compound each other in amateur golfers
 
 

app/models/llm_analyzer.py

@@ -1186,8 +1186,10 @@ def calculate_knee_bend_degree(pose_data, address_idx):
             knee_point = kp[25][:2]
             ankle_point = kp[27][:2]
         
-        # Calculate vectors
-        thigh_vector = (knee_point[0] - hip_point[0], knee_point[1] - hip_point[1])
+        # Calculate vectors from knee joint
+        # Vector from knee to hip (thigh direction)
+        thigh_vector = (hip_point[0] - knee_point[0], hip_point[1] - knee_point[1])
+        # Vector from knee to ankle (shin direction)  
         shin_vector = (ankle_point[0] - knee_point[0], ankle_point[1] - knee_point[1])
         
         # Calculate angle between thigh and shin vectors
@@ -1201,19 +1203,23 @@ def calculate_knee_bend_degree(pose_data, address_idx):
         cos_angle = dot_product / (thigh_magnitude * shin_magnitude)
         cos_angle = max(-1.0, min(1.0, cos_angle))  # Clamp to valid range
         
-        # Calculate the angle at the knee joint (hip-knee-ankle angle)
-        # This is the internal angle at the knee
+        # Calculate the angle between the thigh and shin vectors
+        # This gives us the internal angle at the knee joint
         angle_between_rad = math.acos(cos_angle)
-        hip_knee_ankle_angle = math.degrees(angle_between_rad)
+        internal_knee_angle = math.degrees(angle_between_rad)
         
-        # Calculate knee flexion as 180 - hip_knee_ankle_angle
-        # When leg is straight, hip-knee-ankle ≈ 180°, so flexion ≈ 0°
-        # When knee is bent, hip-knee-ankle < 180°, so flexion > 0°
-        knee_flexion_deg = 180.0 - hip_knee_ankle_angle
+        # For knee flexion: when the leg is straight, internal angle ≈ 180°, flexion ≈ 0°
+        # When knee is bent, internal angle < 180°, so flexion = 180° - internal_angle
+        knee_flexion_deg = 180.0 - internal_knee_angle
         
         # Ensure flexion is non-negative
         knee_flexion_deg = max(0.0, knee_flexion_deg)
         
+        # Debug check: ensure we're returning the flexion angle, not the hip-knee-ankle angle
+        # If we see large angles (>90°) being returned, there's likely a calculation error
+        if knee_flexion_deg > 90.0:
+            # This suggests we might be returning the wrong angle - return None for safety
+            return None
         
         return knee_flexion_deg
         
@@ -1352,6 +1358,7 @@ def parse_and_format_analysis(raw_analysis):
     """
     # Default structure
     formatted_analysis = {
+        'overall_summary': '',  # New field for overall summary
         'classification': 50,  # Default to 50%
         'metric_evaluations': {
             'shaft_angle': '',
@@ -1362,6 +1369,14 @@ def parse_and_format_analysis(raw_analysis):
         }
     }
     
+    # Extract overall summary
+    summary_match = re.search(r'\*\*OVERALL_SUMMARY:\*\*\s*(.*?)(?=\*\*PERFORMANCE_CLASSIFICATION|\*\*|$)', raw_analysis, re.IGNORECASE | re.DOTALL)
+    if summary_match:
+        summary_text = summary_match.group(1).strip()
+        # Clean up the text and remove extra whitespace/newlines
+        summary_clean = re.sub(r'\s+', ' ', summary_text).strip()
+        formatted_analysis['overall_summary'] = summary_clean
+    
     # Extract percentage classification using the new structured format
     classification_match = re.search(r'\*\*PERFORMANCE_CLASSIFICATION:\*\*\s*\[?(\d+)%?\]?', raw_analysis, re.IGNORECASE)
     if classification_match:
@@ -1577,7 +1592,7 @@ def display_formatted_analysis(analysis_data):
 
 def display_formatted_analysis(analysis_data):
     """
-    Display the formatted analysis with individual metric evaluations
+    Display the formatted analysis with overall summary and individual metric evaluations
     
     Args:
         analysis_data (dict): Structured analysis data from parse_and_format_analysis
@@ -1587,6 +1602,16 @@ def display_formatted_analysis(analysis_data):
     
     st.markdown("---")
     
+    # Display overall summary at the top if available
+    overall_summary = analysis_data.get('overall_summary', '')
+    if overall_summary:
+        st.markdown(f"""
+        <div style='background-color: #e8f4fd; padding: 20px; border-radius: 10px; margin-bottom: 20px; border-left: 5px solid #1f77b4;'>
+            <h3 style='color: #1f77b4; margin-top: 0; margin-bottom: 10px;'>🎯 Overall Swing Assessment</h3>
+            <p style='margin: 0; line-height: 1.6; font-size: 16px; color: #2c3e50;'>{overall_summary}</p>
+        </div>
+        """, unsafe_allow_html=True)
+    
     # Display metric evaluations
     st.subheader("Individual Metric Evaluations")
     

app/streamlit_app.py

@@ -306,12 +306,18 @@ def get_knee_flexion_grading(value, confidence):
     if 15 <= value <= 30:
         badge = "🟢"
         label = "Athletic"
-    elif (12 <= value < 15) or (30 < value <= 35):
+    elif (12 <= value < 15):
         badge = "🟠"
-        label = "Slightly tight/soft"
-    elif (8 <= value < 12) or (35 < value <= 40):
+        label = "Slightly too stiff"
+    elif (30 < value <= 35):
         badge = "🟠"
-        label = "Needs adjustment"
+        label = "Slightly too bent"
+    elif (8 <= value < 12):
+        badge = "🟠"
+        label = "Too stiff"
+    elif (35 < value <= 40):
+        badge = "🟠"
+        label = "Too bent"
     else:
         badge = "🔴"
         label = "Likely problematic"
@@ -364,7 +370,7 @@ def get_wrist_pattern_grading(pattern_data, confidence):
     return {
         'display_value': label,
         'badge': badge,
-        'label': "",  # Label is included in display_value
+        'label': "Needs work",  # Add descriptive text after badge
         'confidence': confidence,
         'tip': tip
     }
@@ -1453,7 +1459,10 @@ def render_step_1():
     """Step 1: Upload Swing Video"""
     st.markdown('<h2 style="color: #0B3B0B; font-family: Georgia, serif;">Step 1: Upload Your Video</h2>', unsafe_allow_html=True)
     
-    st.markdown("**Choose your input method below. Tip: Aim for a video of 5 seconds or less for fastest processing.**")
+    st.markdown("**Choose your input method below.**")
+    st.markdown("💡 **Tips:**")
+    st.markdown("- Aim for a video of 5 seconds or less")
+    st.markdown("- Make sure the video is in a down the line view, not face forward")
     
     col1, col2 = st.columns(2)
     
@@ -1636,61 +1645,97 @@ def render_step_4():
             data['analysis_data']['core_metrics'] = core_metrics
         
         
-        # Display the new grading scheme
+        # Generate and display LLM analysis automatically at the top
+        if 'llm_analysis' not in st.session_state:
+            # Generate LLM analysis automatically on first load
+            with st.spinner("Generating AI swing analysis..."):
+                try:
+                    # Prepare data for LLM analysis
+                    analysis_data = data.get('analysis_data', {})
+                    if not analysis_data:
+                        # Fallback: prepare data if not already done
+                        analysis_data = prepare_data_for_llm(pose_data, swing_phases, data.get('trajectory_data', {}), fps=30.0, frame_shape=None)
+                    
+                    # Generate LLM analysis
+                    raw_analysis = generate_swing_analysis(pose_data, swing_phases, data.get('trajectory_data', {}))
+                    
+                    if raw_analysis and not raw_analysis.startswith("Error:"):
+                        # Parse and format the analysis
+                        formatted_analysis = parse_and_format_analysis(raw_analysis)
+                        
+                        # Store the analysis in session state for future reference
+                        st.session_state.llm_analysis = {
+                            'raw': raw_analysis,
+                            'formatted': formatted_analysis
+                        }
+                    else:
+                        # Store error state
+                        st.session_state.llm_analysis = {
+                            'error': raw_analysis or "Failed to generate analysis"
+                        }
+                        
+                except Exception as e:
+                    # Store error state
+                    st.session_state.llm_analysis = {
+                        'error': f"Error generating AI analysis: {str(e)}"
+                    }
+        
+        # Display the overall summary at the very top if analysis was successful
+        if 'llm_analysis' in st.session_state and 'formatted' in st.session_state.llm_analysis:
+            formatted_analysis = st.session_state.llm_analysis['formatted']
+            overall_summary = formatted_analysis.get('overall_summary', '')
+            if overall_summary:
+                st.markdown(f"""
+                <div style='background-color: #e8f4fd; padding: 20px; border-radius: 10px; margin-bottom: 20px; border-left: 5px solid #1f77b4;'>
+                    <h3 style='color: #1f77b4; margin-top: 0; margin-bottom: 10px;'>🎯 Overall Swing Assessment</h3>
+                    <p style='margin: 0; line-height: 1.6; font-size: 16px; color: #2c3e50;'>{overall_summary}</p>
+                </div>
+                """, unsafe_allow_html=True)
+        elif 'llm_analysis' in st.session_state and 'error' in st.session_state.llm_analysis:
+            st.warning(f"AI Analysis unavailable: {st.session_state.llm_analysis['error']}")
+        
+        # Display the new grading scheme below the summary
         display_new_grading_scheme(core_metrics)
         
-        # Add calibration debug section for qualitative metrics
-        with st.expander("🔧 Calibration Data (Raw Numbers)", expanded=False):
-            st.write("**Raw values for qualitative assessments - for calibration purposes:**")
-            
-            # Shaft angle raw value
-            shaft_raw = core_metrics.get("shaft_angle_top", {}).get('value')
-            shaft_status = core_metrics.get("shaft_angle_top", {}).get('status', 'n/a')
-            st.write(f"• **Shaft Angle @ Top**: {shaft_raw}° (status: {shaft_status})")
-            
-            # Hip rotation raw value  
-            hip_raw = core_metrics.get("hip_rotation_impact_deg", {}).get('value')
-            hip_status = core_metrics.get("hip_rotation_impact_deg", {}).get('status', 'n/a')
-            st.write(f"• **Hip Rotation @ Impact**: {hip_raw}° (status: {hip_status})")
-            
-            # X-factor raw value (bonus)
-            xfactor_raw = core_metrics.get("x_factor_top_deg", {}).get('value')
-            xfactor_status = core_metrics.get("x_factor_top_deg", {}).get('status', 'n/a')
-            st.write(f"• **X-Factor @ Top**: {xfactor_raw}° (status: {xfactor_status})")
-            
-            # Shoulder rotation raw value
-            shoulder_raw = core_metrics.get("shoulder_rotation_top_deg", {}).get('value')
-            shoulder_status = core_metrics.get("shoulder_rotation_top_deg", {}).get('status', 'n/a')
-            st.write(f"• **Shoulder Rotation @ Top**: {shoulder_raw}° (status: {shoulder_status})")
-            
-            st.write("---")
-            st.write("**Calibration Notes:**")
-            st.write("- Use these raw numbers to adjust qualitative thresholds")
-            st.write("- Shaft angle: Professional range ~±0-20°, >35° likely calibration error")
-            st.write("- Hip rotation: 25°+ = High Hip Turn, 18-24° = Good Hip Turn, 12-17° = Moderate Hip Turn, 8-11° = Limited Hip Turn, <8° = Minimal Hip Turn")
-            st.write("- X-Factor: Separation between shoulders and hips at top")
-            st.write("- **Note**: DTL-only view shows kinematic sequence approximation, not actual power percentage distribution")
-            st.write("- **Framework**: For accurate power source analysis, face-on view is required")
+        # Developer tools (small and subtle)
+        st.write("")
+        st.write("")
         
-        st.markdown("---")
+        # Small developer buttons in bottom right corner
+        dev_col1, dev_col2, dev_col3 = st.columns([4, 1, 1])
         
-        # Add button to show exact LLM prompt
-        col1, col2, col3 = st.columns([1, 2, 1])
-        with col2:
-            if st.button("🔍 Show Original LLM Prompt", key="show_prompt_btn", use_container_width=True):
-                if 'prompt' in st.session_state.analysis_data:
-                    st.markdown("### 🤖 Original LLM Prompt")
-                    st.info("This is the exact prompt that was prepared for AI analysis:")
+        with dev_col2:
+            if st.button("📊 Debug", key="debug_calibration", help="View calibration data"):
+                with st.expander("Calibration Data", expanded=True):
+                    st.caption("Raw values for qualitative assessments:")
                     
-                    with st.expander("📋 View Full Prompt", expanded=True):
-                        st.code(st.session_state.analysis_data['prompt'], language="text")
+                    # Shaft angle raw value
+                    shaft_raw = core_metrics.get("shaft_angle_top", {}).get('value')
+                    shaft_status = core_metrics.get("shaft_angle_top", {}).get('status', 'n/a')
+                    st.caption(f"Shaft Angle @ Top: {shaft_raw}° ({shaft_status})")
+                    
+                    # Hip rotation raw value  
+                    hip_raw = core_metrics.get("hip_rotation_impact_deg", {}).get('value')
+                    hip_status = core_metrics.get("hip_rotation_impact_deg", {}).get('status', 'n/a')
+                    st.caption(f"Hip Rotation @ Impact: {hip_raw}° ({hip_status})")
+                    
+                    # X-factor raw value (bonus)
+                    xfactor_raw = core_metrics.get("x_factor_top_deg", {}).get('value')
+                    xfactor_status = core_metrics.get("x_factor_top_deg", {}).get('status', 'n/a')
+                    st.caption(f"X-Factor @ Top: {xfactor_raw}° ({xfactor_status})")
                     
-                    st.markdown("**Prompt Components:**")
-                    st.markdown("- **System Instructions**: How the AI should analyze your swing")
-                    st.markdown("- **Your Swing Data**: Core metrics and swing phases")
-                    st.markdown("- **Analysis Format**: Instructions for structured output")
+                    # Shoulder rotation raw value
+                    shoulder_raw = core_metrics.get("shoulder_rotation_top_deg", {}).get('value')
+                    shoulder_status = core_metrics.get("shoulder_rotation_top_deg", {}).get('status', 'n/a')
+                    st.caption(f"Shoulder Rotation @ Top: {shoulder_raw}° ({shoulder_status})")
+        
+        with dev_col3:
+            if st.button("🔍 Prompt", key="show_prompt_btn", help="View LLM prompt"):
+                if 'prompt' in st.session_state.analysis_data:
+                    with st.expander("LLM Prompt", expanded=True):
+                        st.code(st.session_state.analysis_data['prompt'], language="text")
                 else:
-                    st.error("No prompt data available. Please re-analyze the video to generate a new prompt.")
+                    st.error("No prompt data available.")
         
     else:
         st.error("No analysis data available. Please analyze a video first.")