feat: expert mode + stage outputs in value table (Issue #47)
FEATURE: Experten-Modus 🔬 - Toggle-Button in Wertetabelle - Normal: Nur gefüllte Werte anzeigen - Experten: Alle Platzhalter inkl. leere/technische - Anzeige: "(+X ausgeblendet)" wenn Werte gefiltert - Button-Style: Accent wenn aktiv FILTER: Leere Werte ausblenden (Normal-Modus) - Filtert: '', 'nicht verfügbar', '[Nicht verfügbar]' - Zeigt nur relevante Nutzer-Daten - Experten-Modus zeigt alles FEATURE: Stage-Outputs in Wertetabelle ✅ ROOT CAUSE: stage_N_key Platzhalter hatten keine Werte - Stage-Outputs (z.B. stage_1_body) sind Basis-Analysen-Ergebnisse - Wurden nicht in cleaned_values gefunden (nur statische Platzhalter) FIX: - Collect stage outputs aus result.debug.stages[].output - Store als stage_N_key dict - Lookup: erst stage_outputs, dann cleaned_values - Description: "Output aus Stage X (Basis-Analyse)" - JSON-Werte automatisch serialisiert BEISPIEL Pipeline-Wertetabelle: ┌──────────────────────────────────────────────┐ │ 📊 Verwendete Werte (8) (+3 ausgeblendet) 🔬│ │ ┌──────────────────────────────────────────┐ │ │ │ weight_aktuell │ 85.2 kg │ Gewicht │ │ │ │ stage_1_body │ {"bmi":...│ Output...│ │ ← Stage output! │ │ stage_1_nutr... │ {"kcal"...│ Output...│ │ │ └──────────────────────────────────────────┘ │ └──────────────────────────────────────────────┘ AKTIVIERUNG Experten-Modus: 1. Analyse öffnen 2. "📊 Verwendete Werte" aufklappen 3. Button "🔬 Experten-Modus" klicken 4. Zeigt alle Platzhalter (auch leere stage outputs) version: 9.8.0 (feature) module: prompts 2.3.0, insights 1.6.0
This commit is contained in:
1 parent
15bd6cddeb
commit
e799edbae4
2 files changed
+82
-26
No files matched your search
+29
-11
@@ -856,6 +856,19 @@ async def execute_unified_prompt(
|
||||
elif result['type'] == 'pipeline':
|
||||
# Pipeline: collect from all stages
|
||||
stages_debug = result['debug'].get('stages', [])
|
||||
|
||||
# First, collect stage outputs (outputs from base prompts in each stage)
|
||||
stage_outputs = {}
|
||||
for stage_debug in stages_debug:
|
||||
stage_num = stage_debug.get('stage', 0)
|
||||
stage_output = stage_debug.get('output', {})
|
||||
if isinstance(stage_output, dict):
|
||||
for output_key, output_value in stage_output.items():
|
||||
# Store stage outputs (e.g., stage_1_body)
|
||||
placeholder_key = f"stage_{stage_num}_{output_key}"
|
||||
stage_outputs[placeholder_key] = output_value
|
||||
|
||||
# Collect all resolved placeholders from prompts
|
||||
for stage_debug in stages_debug:
|
||||
for prompt_debug in stage_debug.get('prompts', []):
|
||||
resolved_keys = []
|
||||
@@ -867,20 +880,25 @@ async def execute_unified_prompt(
|
||||
|
||||
for key in resolved_keys:
|
||||
if key not in metadata['placeholders']: # Avoid duplicates
|
||||
# Get full untruncated value
|
||||
value = cleaned_values.get(key, '')
|
||||
# Get value: first try stage outputs, then cleaned_values
|
||||
value = stage_outputs.get(key, cleaned_values.get(key, ''))
|
||||
|
||||
# Find description in catalog
|
||||
desc = None
|
||||
for cat_items in catalog.values():
|
||||
matching = [item for item in cat_items if item['key'] == key]
|
||||
if matching:
|
||||
desc = matching[0].get('description', '')
|
||||
break
|
||||
# For stage output placeholders, add special description
|
||||
if key.startswith('stage_'):
|
||||
desc = f"Output aus Stage {key.split('_')[1]} (Basis-Analyse)"
|
||||
else:
|
||||
# Find description in catalog
|
||||
desc = None
|
||||
for cat_items in catalog.values():
|
||||
matching = [item for item in cat_items if item['key'] == key]
|
||||
if matching:
|
||||
desc = matching[0].get('description', '')
|
||||
break
|
||||
desc = desc or ''
|
||||
|
||||
metadata['placeholders'][key] = {
|
||||
'value': value,
|
||||
'description': desc or ''
|
||||
'value': value if isinstance(value, str) else json.dumps(value, ensure_ascii=False),
|
||||
'description': desc
|
||||
}
|
||||
|
||||
# Save to database with metadata
|
||||
|
||||
Reference in new issue
Block a user