fix: Analysis page now uses unified prompt executor (Issue #28)

BREAKING: Analysis page switched from old /insights/run to new /prompts/execute

Changes:
- Backend: Added save=true parameter to /prompts/execute
  - When enabled, saves final output to ai_insights table
  - Extracts content from pipeline output (last stage)
- Frontend api.js: Added save parameter to executeUnifiedPrompt()
- Frontend Analysis.jsx: Switched from api.runInsight() to api.executeUnifiedPrompt()
  - Transforms new result format to match InsightCard expectations
  - Pipeline outputs properly extracted and displayed

Fixes: PIPELINE_MASTER responses (old template being sent to AI)
The old /insights/run endpoint used raw template field, which for the
legacy "pipeline" prompt was literally "PIPELINE_MASTER". The new
executor properly handles stages and data processing.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

backend/routers/prompts.py

@@ -700,6 +700,7 @@ async def execute_unified_prompt(
     modules: Optional[dict] = None,
     timeframes: Optional[dict] = None,
     debug: bool = False,
+    save: bool = False,
     session: dict = Depends(require_auth)
 ):
     """
@@ -710,6 +711,7 @@ async def execute_unified_prompt(
         modules: Dict of enabled modules (e.g., {"körper": true})
         timeframes: Dict of timeframes per module (e.g., {"körper": 30})
         debug: If true, include debug information (placeholders, final prompts, etc.)
+        save: If true, save result to ai_insights table
 
     Returns:
         Execution result with outputs (and debug info if debug=true)
@@ -745,6 +747,33 @@ async def execute_unified_prompt(
         enable_debug=debug
     )
 
+    # Save to ai_insights if requested
+    if save:
+        # Extract final output text/markdown
+        if result['type'] == 'pipeline':
+            # For pipeline, get the last stage's output
+            final_output = result.get('output', {})
+            # If output is dict with single key, use that value
+            if isinstance(final_output, dict) and len(final_output) == 1:
+                content = list(final_output.values())[0]
+            else:
+                content = json.dumps(final_output, ensure_ascii=False)
+        else:
+            # For base prompts, use output directly
+            content = result.get('output', '')
+            if isinstance(content, dict):
+                content = json.dumps(content, ensure_ascii=False)
+
+        # Save to database
+        with get_db() as conn:
+            cur = get_cursor(conn)
+            cur.execute(
+                """INSERT INTO ai_insights (id, profile_id, scope, content, created)
+                   VALUES (%s, %s, %s, %s, CURRENT_TIMESTAMP)""",
+                (str(uuid.uuid4()), profile_id, prompt_slug, content)
+            )
+            conn.commit()
+
     return result
 
 

frontend/src/pages/Analysis.jsx

@@ -75,8 +75,25 @@ export default function Analysis() {
   const runPrompt = async (slug) => {
     setLoading(slug); setError(null); setNewResult(null)
     try {
-      const result = await api.runInsight(slug)
+      // Use new unified executor with save=true
-      setNewResult(result)
+      const result = await api.executeUnifiedPrompt(slug, null, null, false, true)
+
+      // Transform result to match old format for InsightCard
+      let content = ''
+      if (result.type === 'pipeline') {
+        // For pipeline, extract final output
+        const finalOutput = result.output || {}
+        if (typeof finalOutput === 'object' && Object.keys(finalOutput).length === 1) {
+          content = Object.values(finalOutput)[0]
+        } else {
+          content = JSON.stringify(finalOutput, null, 2)
+        }
+      } else {
+        // For base prompts, use output directly
+        content = typeof result.output === 'string' ? result.output : JSON.stringify(result.output, null, 2)
+      }
+
+      setNewResult({ scope: slug, content })
       await loadAll()
       setTab('run')
     } catch(e) {

frontend/src/utils/api.js

@@ -307,9 +307,10 @@ export const api = {
   executePipeline:        (configId=null) => req('/insights/pipeline' + (configId ? `?config_id=${configId}` : ''), json({})),
 
   // Unified Prompt System (Issue #28 Phase 2)
-  executeUnifiedPrompt:   (slug, modules=null, timeframes=null, debug=false) => {
+  executeUnifiedPrompt:   (slug, modules=null, timeframes=null, debug=false, save=false) => {
     const params = new URLSearchParams({ prompt_slug: slug })
     if (debug) params.append('debug', 'true')
+    if (save) params.append('save', 'true')
     const body = {}
     if (modules) body.modules = modules
     if (timeframes) body.timeframes = timeframes