Add tags prominence and SIM source grouping features

Database changes:
- Add sim_source_id column to artifacts table for grouping multiple artifacts
- Create Alembic migration (001_add_sim_source_id) for schema update
- Add Alembic env.py for migration support with environment-based DB URLs

API enhancements:
- Add sim_source_id parameter to upload endpoint
- Add sim_source_id filter to query endpoint
- Add new /grouped-by-sim-source endpoint for getting artifacts by group
- Update all API documentation to include sim_source_id

UI improvements:
- Make tags required field and more prominent in upload form
- Add tags display directly in artifacts table (below filename)
- Add SIM Source ID field in upload form with helper text for grouping
- Update table to show sim_source_id (falls back to test_suite if null)
- Tags now displayed as inline badges in main table view

Seed data updates:
- Generate sim_source_id for 70% of artifacts to demonstrate grouping
- Multiple artifacts can share same sim_source_id
- Improved seed data variety with tag combinations

Features:
- Tags are now prominently displayed in both table and detail views
- Multiple artifacts can be grouped by SIM source ID
- Users can filter/query by sim_source_id
- Backward compatible - existing artifacts without sim_source_id still work

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

alembic/env.py

@@ -0,0 +1,84 @@
+from logging.config import fileConfig
+import os
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+# Import your models Base
+from app.models.artifact import Base
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Override sqlalchemy.url from environment variable
+if os.getenv("DATABASE_URL"):
+    config.set_main_option("sqlalchemy.url", os.getenv("DATABASE_URL"))
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+target_metadata = Base.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

app/api/artifacts.py

@@ -1,7 +1,7 @@
 from fastapi import APIRouter, UploadFile, File, Form, Depends, HTTPException, Query
 from fastapi.responses import StreamingResponse
 from sqlalchemy.orm import Session
-from typing import List, Optional
+from typing import List, Optional, Dict
 import uuid
 import json
 import io
@@ -36,6 +36,7 @@ async def upload_artifact(
     test_suite: Optional[str] = Form(None),
     test_config: Optional[str] = Form(None),
     test_result: Optional[str] = Form(None),
+    sim_source_id: Optional[str] = Form(None),
     custom_metadata: Optional[str] = Form(None),
     description: Optional[str] = Form(None),
     tags: Optional[str] = Form(None),
@@ -51,6 +52,7 @@ async def upload_artifact(
     - **test_suite**: Test suite identifier
     - **test_config**: JSON string of test configuration
     - **test_result**: Test result (pass, fail, skip, error)
+    - **sim_source_id**: SIM source ID to group multiple artifacts
     - **custom_metadata**: JSON string of additional metadata
     - **description**: Text description of the artifact
     - **tags**: JSON array of tags (as string)
@@ -88,6 +90,7 @@ async def upload_artifact(
             test_suite=test_suite,
             test_config=test_config_dict,
             test_result=test_result,
+            sim_source_id=sim_source_id,
             custom_metadata=metadata_dict,
             description=description,
             tags=tags_list,
@@ -194,6 +197,7 @@ async def query_artifacts(query: ArtifactQuery, db: Session = Depends(get_db)):
     - **test_name**: Filter by test name
     - **test_suite**: Filter by test suite
     - **test_result**: Filter by test result
+    - **sim_source_id**: Filter by SIM source ID
     - **tags**: Filter by tags (must contain all specified tags)
     - **start_date**: Filter by creation date (from)
     - **end_date**: Filter by creation date (to)
@@ -212,6 +216,8 @@ async def query_artifacts(query: ArtifactQuery, db: Session = Depends(get_db)):
         q = q.filter(Artifact.test_suite == query.test_suite)
     if query.test_result:
         q = q.filter(Artifact.test_result == query.test_result)
+    if query.sim_source_id:
+        q = q.filter(Artifact.sim_source_id == query.sim_source_id)
     if query.tags:
         for tag in query.tags:
             q = q.filter(Artifact.tags.contains([tag]))
@@ -240,3 +246,20 @@ async def list_artifacts(
         Artifact.created_at.desc()
     ).offset(offset).limit(limit).all()
     return artifacts
+
+
+@router.get("/grouped-by-sim-source", response_model=Dict[str, List[ArtifactResponse]])
+async def get_artifacts_grouped_by_sim_source(
+    db: Session = Depends(get_db)
+):
+    """Get all artifacts grouped by SIM source ID"""
+    from collections import defaultdict
+
+    artifacts = db.query(Artifact).order_by(Artifact.created_at.desc()).all()
+    grouped = defaultdict(list)
+
+    for artifact in artifacts:
+        sim_source = artifact.sim_source_id or "ungrouped"
+        grouped[sim_source].append(artifact)
+
+    return dict(grouped)

app/models/artifact.py

@@ -21,6 +21,9 @@ class Artifact(Base):
     test_config = Column(JSON)
     test_result = Column(String(50), index=True)  # pass, fail, skip, error
 
+    # SIM source grouping - allows multiple artifacts per source
+    sim_source_id = Column(String(100), index=True)  # Groups artifacts from same SIM source
+
     # Additional metadata
     custom_metadata = Column(JSON)
     description = Column(Text)

app/schemas/artifact.py

@@ -8,6 +8,7 @@ class ArtifactCreate(BaseModel):
     test_suite: Optional[str] = None
     test_config: Optional[Dict[str, Any]] = None
     test_result: Optional[str] = None
+    sim_source_id: Optional[str] = None  # Groups artifacts from same SIM source
     custom_metadata: Optional[Dict[str, Any]] = None
     description: Optional[str] = None
     tags: Optional[List[str]] = None
@@ -26,6 +27,7 @@ class ArtifactResponse(BaseModel):
     test_suite: Optional[str] = None
     test_config: Optional[Dict[str, Any]] = None
     test_result: Optional[str] = None
+    sim_source_id: Optional[str] = None
     custom_metadata: Optional[Dict[str, Any]] = None
     description: Optional[str] = None
     tags: Optional[List[str]] = None
@@ -44,6 +46,7 @@ class ArtifactQuery(BaseModel):
     test_name: Optional[str] = None
     test_suite: Optional[str] = None
     test_result: Optional[str] = None
+    sim_source_id: Optional[str] = None
     tags: Optional[List[str]] = None
     start_date: Optional[datetime] = None
     end_date: Optional[datetime] = None

static/index.html

@@ -109,6 +109,18 @@
                         </div>
                     </div>
 
+                    <div class="form-row">
+                        <div class="form-group">
+                            <label for="sim-source-id">SIM Source ID (for grouping)</label>
+                            <input type="text" id="sim-source-id" name="sim_source_id" placeholder="e.g., sim_run_20251015_001">
+                            <small>Use same ID for multiple artifacts from same source</small>
+                        </div>
+                        <div class="form-group">
+                            <label for="tags">Tags (comma-separated) *</label>
+                            <input type="text" id="tags" name="tags" placeholder="e.g., regression, smoke, critical" required>
+                        </div>
+                    </div>
+
                     <div class="form-row">
                         <div class="form-group">
                             <label for="test-result">Test Result</label>
@@ -126,11 +138,6 @@
                         </div>
                     </div>
 
-                    <div class="form-group">
-                        <label for="tags">Tags (comma-separated)</label>
-                        <input type="text" id="tags" name="tags" placeholder="e.g., regression, smoke, critical">
-                    </div>
-
                     <div class="form-group">
                         <label for="description">Description</label>
                         <textarea id="description" name="description" rows="3" placeholder="Describe this artifact..."></textarea>

static/js/app.js

@@ -73,11 +73,12 @@ function displayArtifacts(artifacts) {
 
     tbody.innerHTML = displayedArtifacts.map(artifact => `
         <tr>
-            <td>${artifact.test_suite || '-'}</td>
+            <td>${artifact.sim_source_id || artifact.test_suite || '-'}</td>
             <td>
                 <a href="#" onclick="showDetail(${artifact.id}); return false;" style="color: #60a5fa; text-decoration: none;">
                     ${escapeHtml(artifact.filename)}
                 </a>
+                ${artifact.tags && artifact.tags.length > 0 ? `<br><div style="margin-top: 5px;">${formatTags(artifact.tags)}</div>` : ''}
             </td>
             <td>${formatDate(artifact.created_at)}</td>
             <td>${artifact.test_name || '-'}</td>
@@ -289,9 +290,9 @@ async function uploadArtifact(event) {
     formData.append('file', fileInput.files[0]);
 
     // Add optional fields
-    const fields = ['test_name', 'test_suite', 'test_result', 'version', 'description'];
+    const fields = ['test_name', 'test_suite', 'test_result', 'version', 'description', 'sim_source_id'];
     fields.forEach(field => {
-        const value = form.elements[field].value;
+        const value = form.elements[field]?.value;
         if (value) formData.append(field, value);
     });
 

utils/seed_data.py

@@ -112,7 +112,7 @@ def generate_pcap_content() -> bytes:
     return bytes(pcap_header)
 
 
-def create_artifact_data(index: int) -> Dict[str, Any]:
+def create_artifact_data(index: int, sim_source_id: str = None) -> Dict[str, Any]:
     """Generate metadata for an artifact"""
     test_name = random.choice(TEST_NAMES)
     test_suite = random.choice(TEST_SUITES)
@@ -147,6 +147,7 @@ def create_artifact_data(index: int) -> Dict[str, Any]:
         "test_name": test_name,
         "test_suite": test_suite,
         "test_result": test_result,
+        "sim_source_id": sim_source_id,
         "tags": artifact_tags,
         "test_config": test_config,
         "custom_metadata": custom_metadata,
@@ -201,6 +202,9 @@ async def generate_seed_data(num_artifacts: int = 50) -> List[int]:
         print(f"Deployment mode: {settings.deployment_mode}")
         print(f"Storage backend: {settings.storage_backend}")
 
+        # Generate some SIM source IDs that will be reused (simulating multiple artifacts per source)
+        sim_sources = [f"sim_run_{uuid.uuid4().hex[:8]}" for _ in range(max(num_artifacts // 3, 1))]
+
         for i in range(num_artifacts):
             # Randomly choose file type
             file_type_choice = random.choice(['csv', 'json', 'binary', 'pcap'])
@@ -225,8 +229,11 @@ async def generate_seed_data(num_artifacts: int = 50) -> List[int]:
             # Upload to storage
             storage_path = await upload_artifact_to_storage(content, filename)
 
+            # Randomly assign a SIM source ID (70% chance of having one, enabling grouping)
+            sim_source_id = random.choice(sim_sources) if random.random() < 0.7 else None
+
             # Generate metadata
-            artifact_data = create_artifact_data(i)
+            artifact_data = create_artifact_data(i, sim_source_id)
 
             # Create database record
             artifact = Artifact(
@@ -239,6 +246,7 @@ async def generate_seed_data(num_artifacts: int = 50) -> List[int]:
                 test_suite=artifact_data["test_suite"],
                 test_config=artifact_data["test_config"],
                 test_result=artifact_data["test_result"],
+                sim_source_id=artifact_data["sim_source_id"],
                 custom_metadata=artifact_data["custom_metadata"],
                 description=artifact_data["description"],
                 tags=artifact_data["tags"],