robosystems-client 0.2.21__tar.gz → 0.2.23__tar.gz

{robosystems_client-0.2.21 → robosystems_client-0.2.23}/.github/workflows/tag-release.yml

@@ -71,31 +71,31 @@ jobs:
 
           if [ -z "$LAST_TAG" ]; then
             echo "No previous release found, analyzing all commits"
-            COMMIT_RANGE="$(git rev-list --max-parents=0 HEAD)..HEAD"
             LAST_TAG="initial"
+            # For initial release, use different commands that don't require a range
+            FILES_CHANGED=$(git ls-files | wc -l)
+            COMMITS_COUNT=$(git rev-list --count HEAD)
+            # Get stats by diffing empty tree against HEAD
+            EMPTY_TREE=$(git hash-object -t tree /dev/null)
+            ADDITIONS=$(git diff --shortstat "$EMPTY_TREE" HEAD | grep -oE '[0-9]+ insertions?' | grep -oE '[0-9]+' || echo "0")
+            DELETIONS=$(git diff --shortstat "$EMPTY_TREE" HEAD | grep -oE '[0-9]+ deletions?' | grep -oE '[0-9]+' || echo "0")
+            COMMIT_MESSAGES=$(git log --oneline --no-color HEAD | head -30)
+            DETAILED_CHANGES=$(git diff --name-status --no-color "$EMPTY_TREE" HEAD | head -50)
+            PR_REFS=$(git log --oneline --no-color HEAD | grep -oE '#[0-9]+' | sort -u | head -10 || echo "")
           else
-            COMMIT_RANGE="$LAST_TAG..HEAD"
             echo "Analyzing changes since last release: $LAST_TAG"
+            # Use explicit two-commit diff syntax instead of range syntax
+            FILES_CHANGED=$(git diff --name-only "$LAST_TAG" HEAD | wc -l)
+            COMMITS_COUNT=$(git rev-list --count "$LAST_TAG"..HEAD)
+            ADDITIONS=$(git diff --shortstat "$LAST_TAG" HEAD | grep -oE '[0-9]+ insertions?' | grep -oE '[0-9]+' || echo "0")
+            DELETIONS=$(git diff --shortstat "$LAST_TAG" HEAD | grep -oE '[0-9]+ deletions?' | grep -oE '[0-9]+' || echo "0")
+            COMMIT_MESSAGES=$(git log --oneline --no-color "$LAST_TAG"..HEAD | head -30)
+            DETAILED_CHANGES=$(git diff --name-status --no-color "$LAST_TAG" HEAD | head -50)
+            PR_REFS=$(git log --oneline --no-color "$LAST_TAG"..HEAD | grep -oE '#[0-9]+' | sort -u | head -10 || echo "")
           fi
 
-          # Get change statistics
-          FILES_CHANGED=$(git diff --name-only $COMMIT_RANGE | wc -l)
-          COMMITS_COUNT=$(git rev-list --count $COMMIT_RANGE)
-          ADDITIONS=$(git diff --shortstat $COMMIT_RANGE | grep -oE '[0-9]+ insertions?' | grep -oE '[0-9]+' || echo "0")
-          DELETIONS=$(git diff --shortstat $COMMIT_RANGE | grep -oE '[0-9]+ deletions?' | grep -oE '[0-9]+' || echo "0")
-
-          # Get commit messages (limit to prevent memory issues)
-          COMMIT_MESSAGES=$(git log --oneline --no-color $COMMIT_RANGE | head -30)
-
-          # Get file changes (limit to prevent memory issues)
-          DETAILED_CHANGES=$(git diff --name-status --no-color $COMMIT_RANGE | head -50)
-
-          # Get PR references from commit messages
-          PR_REFS=$(git log --oneline --no-color $COMMIT_RANGE | grep -oE '#[0-9]+' | sort -u | head -10 || echo "")
-
           # Save outputs
           echo "last_tag=$LAST_TAG" >> $GITHUB_OUTPUT
-          echo "commit_range=$COMMIT_RANGE" >> $GITHUB_OUTPUT
           echo "files_changed=$FILES_CHANGED" >> $GITHUB_OUTPUT
           echo "commits_count=$COMMITS_COUNT" >> $GITHUB_OUTPUT
           echo "additions=$ADDITIONS" >> $GITHUB_OUTPUT

{robosystems_client-0.2.21 → robosystems_client-0.2.23}/.gitignore

@@ -93,11 +93,6 @@ ipython_config.py
 #   install all needed dependencies.
 Dockerfile
 
-# celery beat schedule file
-celerybeat-schedule.db
-celerybeat-schedule
-celerybeat.pid
-
 # SageMath parsed files
 *.sage.py
 

{robosystems_client-0.2.21 → robosystems_client-0.2.23}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: robosystems-client
-Version: 0.2.21
+Version: 0.2.23
 Summary: Python Client for RoboSystems financial graph database API
 Author: RFS LLC
 License: MIT

{robosystems_client-0.2.21 → robosystems_client-0.2.23}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "robosystems-client"
-version = "0.2.21"
+version = "0.2.23"
 description = "Python Client for RoboSystems financial graph database API"
 readme = "README.md"
 requires-python = ">=3.10"

{robosystems_client-0.2.21 → robosystems_client-0.2.23}/pytest.ini

@@ -5,7 +5,6 @@ python_classes = Test*
 python_functions = test_*
 
 markers =
-    celery: marks tests that require celery
     integration: marks integration tests
     unit: marks unit tests
     asyncio: marks tests that use asyncio

{robosystems_client-0.2.21 → robosystems_client-0.2.23}/robosystems_client/api/agent/auto_select_agent.py

@@ -134,7 +134,7 @@ def sync_detailed(
   **Execution Strategies (automatic):**
   - Fast operations (<5s): Immediate synchronous response
   - Medium operations (5-30s): SSE streaming with progress updates
-  - Long operations (>30s): Async Celery worker with operation tracking
+  - Long operations (>30s): Background queue with operation tracking
 
   **Response Mode Override:**
   Use query parameter `?mode=sync|async` to override automatic strategy selection.
@@ -228,7 +228,7 @@ def sync(
   **Execution Strategies (automatic):**
   - Fast operations (<5s): Immediate synchronous response
   - Medium operations (5-30s): SSE streaming with progress updates
-  - Long operations (>30s): Async Celery worker with operation tracking
+  - Long operations (>30s): Background queue with operation tracking
 
   **Response Mode Override:**
   Use query parameter `?mode=sync|async` to override automatic strategy selection.
@@ -317,7 +317,7 @@ async def asyncio_detailed(
   **Execution Strategies (automatic):**
   - Fast operations (<5s): Immediate synchronous response
   - Medium operations (5-30s): SSE streaming with progress updates
-  - Long operations (>30s): Async Celery worker with operation tracking
+  - Long operations (>30s): Background queue with operation tracking
 
   **Response Mode Override:**
   Use query parameter `?mode=sync|async` to override automatic strategy selection.
@@ -409,7 +409,7 @@ async def asyncio(
   **Execution Strategies (automatic):**
   - Fast operations (<5s): Immediate synchronous response
   - Medium operations (5-30s): SSE streaming with progress updates
-  - Long operations (>30s): Async Celery worker with operation tracking
+  - Long operations (>30s): Background queue with operation tracking
 
   **Response Mode Override:**
   Use query parameter `?mode=sync|async` to override automatic strategy selection.

{robosystems_client-0.2.21 → robosystems_client-0.2.23}/robosystems_client/api/agent/execute_specific_agent.py

@@ -124,7 +124,7 @@ def sync_detailed(
   **Execution Strategies (automatic):**
   - Fast operations (<5s): Immediate synchronous response
   - Medium operations (5-30s): SSE streaming with progress updates
-  - Long operations (>30s): Async Celery worker with operation tracking
+  - Long operations (>30s): Background queue with operation tracking
 
   **Response Mode Override:**
   Use query parameter `?mode=sync|async` to override automatic strategy selection.
@@ -179,7 +179,7 @@ def sync(
   **Execution Strategies (automatic):**
   - Fast operations (<5s): Immediate synchronous response
   - Medium operations (5-30s): SSE streaming with progress updates
-  - Long operations (>30s): Async Celery worker with operation tracking
+  - Long operations (>30s): Background queue with operation tracking
 
   **Response Mode Override:**
   Use query parameter `?mode=sync|async` to override automatic strategy selection.
@@ -229,7 +229,7 @@ async def asyncio_detailed(
   **Execution Strategies (automatic):**
   - Fast operations (<5s): Immediate synchronous response
   - Medium operations (5-30s): SSE streaming with progress updates
-  - Long operations (>30s): Async Celery worker with operation tracking
+  - Long operations (>30s): Background queue with operation tracking
 
   **Response Mode Override:**
   Use query parameter `?mode=sync|async` to override automatic strategy selection.
@@ -282,7 +282,7 @@ async def asyncio(
   **Execution Strategies (automatic):**
   - Fast operations (<5s): Immediate synchronous response
   - Medium operations (5-30s): SSE streaming with progress updates
-  - Long operations (>30s): Async Celery worker with operation tracking
+  - Long operations (>30s): Background queue with operation tracking
 
   **Response Mode Override:**
   Use query parameter `?mode=sync|async` to override automatic strategy selection.

{robosystems_client-0.2.21 → robosystems_client-0.2.23}/robosystems_client/api/files/update_file.py

@@ -103,7 +103,7 @@ def sync_detailed(
   **What Happens (status='uploaded'):**
   1. File validated in S3
   2. Row count calculated
-  3. DuckDB staging triggered immediately (Celery task)
+  3. DuckDB staging triggered immediately (background task)
   4. If ingest_to_graph=true, graph ingestion queued
   5. File queryable in DuckDB within seconds
 
@@ -165,7 +165,7 @@ def sync(
   **What Happens (status='uploaded'):**
   1. File validated in S3
   2. Row count calculated
-  3. DuckDB staging triggered immediately (Celery task)
+  3. DuckDB staging triggered immediately (background task)
   4. If ingest_to_graph=true, graph ingestion queued
   5. File queryable in DuckDB within seconds
 
@@ -222,7 +222,7 @@ async def asyncio_detailed(
   **What Happens (status='uploaded'):**
   1. File validated in S3
   2. Row count calculated
-  3. DuckDB staging triggered immediately (Celery task)
+  3. DuckDB staging triggered immediately (background task)
   4. If ingest_to_graph=true, graph ingestion queued
   5. File queryable in DuckDB within seconds
 
@@ -282,7 +282,7 @@ async def asyncio(
   **What Happens (status='uploaded'):**
   1. File validated in S3
   2. Row count calculated
-  3. DuckDB staging triggered immediately (Celery task)
+  3. DuckDB staging triggered immediately (background task)
   4. If ingest_to_graph=true, graph ingestion queued
   5. File queryable in DuckDB within seconds
 

{robosystems_client-0.2.21 → robosystems_client-0.2.23}/robosystems_client/extensions/README.md

@@ -1,6 +1,6 @@
 # RoboSystems Python Client Extensions
 
-🚀 **Production-Ready Extensions** for the RoboSystems Financial Knowledge Graph API
+**Production-Ready Extensions** for the RoboSystems Financial Knowledge Graph API
 
 [![Python 3.7+](https://img.shields.io/badge/python-3.7+-blue.svg)](https://www.python.org/downloads/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
@@ -17,7 +17,7 @@ The RoboSystems Python Client Extensions provide enhanced functionality for the
 - **Caching** with TTL and LRU eviction
 - **Full Async/Await Support** throughout
 
-## 🚀 Quick Start
+## Quick Start
 
 ### Installation
 
@@ -84,7 +84,7 @@ async def main():
 asyncio.run(main())
 ```
 
-## 🔐 Authentication
+## Authentication
 
 ### API Key Authentication (Recommended)
 
@@ -139,7 +139,7 @@ dev_ext = create_extensions(
 )
 ```
 
-## 🛠 Advanced Features
+## Advanced Features
 
 ### Query Builder
 
@@ -182,7 +182,7 @@ print(f"Complexity: {cost['complexity_category']} (score: {cost['complexity_scor
 
 # Get optimization recommendations  
 for rec in cost['recommendations']:
-    print(f"💡 {rec}")
+    print(f"Tip: {rec}")
 ```
 
 ### Result Processing
@@ -271,7 +271,7 @@ client.connect("operation_id")
 client.close()
 ```
 
-## 📊 Examples
+## Examples
 
 ### Financial Data Analysis
 
@@ -332,7 +332,7 @@ if final_batch:
     process_transaction_batch(final_batch)
     total_processed += len(final_batch)
 
-print(f"✅ Processed {total_processed:,} transactions total")
+print(f"Processed {total_processed:,} transactions total")
 ```
 
 ### Error Handling
@@ -361,7 +361,7 @@ except Exception as e:
     print(f"Query failed: {e}")
 ```
 
-## ⚡ Performance Optimization
+## Performance Optimization
 
 ### Connection Pooling
 
@@ -391,21 +391,21 @@ query = "MATCH (c:Company) WHERE c.revenue > 1000000 RETURN c"
 # Check syntax
 validation = validate_cypher_query(query)
 if not validation['valid']:
-    print("❌ Query has syntax errors:", validation['issues'])
+    print("Query has syntax errors:", validation['issues'])
     
 # Estimate cost
 cost = estimate_query_cost(query)
-print(f"📊 Query complexity: {cost['complexity_category']}")
+print(f"Query complexity: {cost['complexity_category']}")
 
 # Follow recommendations
 for rec in cost['recommendations']:
-    print(f"💡 Optimization tip: {rec}")
+    print(f"Optimization tip: {rec}")
 
 # Execute only if reasonable complexity
 if cost['complexity_category'] in ['low', 'medium']:
     result = extensions.execute_query("graph_id", query)
 else:
-    print("⚠️ Query may be too expensive - consider optimization")
+    print("Query may be too expensive - consider optimization")
 ```
 
 ### Caching Strategy
@@ -425,7 +425,7 @@ else:
     cache = results_cache
 ```
 
-## 🧪 Testing
+## Testing
 
 Run the test suite:
 
@@ -457,7 +457,7 @@ def test_query_execution():
         assert result["data"] == [{"count": 100}]
 ```
 
-## 🔧 Configuration
+## Configuration
 
 ### Environment Variables
 
@@ -492,7 +492,7 @@ config = RoboSystemsExtensionConfig(
 extensions = RoboSystemsExtensions(config)
 ```
 
-## 📚 API Reference
+## API Reference
 
 ### Core Classes
 
@@ -528,7 +528,7 @@ extensions = RoboSystemsExtensions(config)
 - **`format_duration(milliseconds)`** - Human-readable time formatting
 - **`create_extensions(method, **kwargs)`** - Extensions factory
 
-## 🐛 Troubleshooting
+## Troubleshooting
 
 ### Common Issues
 
@@ -545,9 +545,9 @@ pip install pandas # For DataFrame conversion (optional)
 extensions = AuthenticatedExtensions("your-api-key")
 try:
     result = extensions.execute_query("graph_id", "MATCH (n) RETURN count(n) LIMIT 1")
-    print("✅ Authentication successful")
+    print("Authentication successful")
 except Exception as e:
-    print(f"❌ Auth failed: {e}")
+    print(f"Auth failed: {e}")
 ```
 
 **Connection Issues**
@@ -585,11 +585,7 @@ logging.basicConfig(level=logging.DEBUG)
 extensions = AuthenticatedExtensions("your-key")
 ```
 
-## 📄 License
-
-MIT License - see [LICENSE](LICENSE) file for details.
-
-## 🤝 Contributing
+## Contributing
 
 1. Fork the repository
 2. Create a feature branch
@@ -597,7 +593,7 @@ MIT License - see [LICENSE](LICENSE) file for details.
 4. Run the test suite: `python run_tests.py`
 5. Submit a pull request
 
-## 📞 Support
+## Support
 
 - **API Reference**: [api.robosystems.ai](https://api.robosystems.ai)
 - **Issues**: [GitHub Issues](https://github.com/RoboFinSystems/robosystems-python-client/issues)

{robosystems_client-0.2.21 → robosystems_client-0.2.23}/robosystems_client/extensions/agent_client.py

@@ -177,7 +177,7 @@ class AgentClient:
               else datetime.now().isoformat(),
             )
 
-        # Check if this is a queued response (async Celery execution)
+        # Check if this is a queued response (async background task execution)
         is_queued = False
         queued_response = None
 

{robosystems_client-0.2.21 → robosystems_client-0.2.23}/robosystems_client/extensions/extensions.py

@@ -25,6 +25,7 @@ class RoboSystemsExtensionConfig:
   max_retries: int = 5
   retry_delay: int = 1000
   timeout: int = 30
+  s3_endpoint_url: Optional[str] = None  # Override S3 endpoint (e.g., for LocalStack)
 
 
 class RoboSystemsExtensions:
@@ -41,6 +42,7 @@ class RoboSystemsExtensions:
       "max_retries": config.max_retries,
       "retry_delay": config.retry_delay,
       "timeout": config.timeout,
+      "s3_endpoint_url": config.s3_endpoint_url,
     }
 
     # Extract token from headers if it was set by auth classes

{robosystems_client-0.2.21 → robosystems_client-0.2.23}/robosystems_client/extensions/file_client.py

@@ -37,7 +37,6 @@ class FileUploadOptions:
   """Options for file upload operations"""
 
   on_progress: Optional[Callable[[str], None]] = None
-  fix_localstack_url: bool = True
   ingest_to_graph: bool = False
 
 
@@ -78,6 +77,9 @@ class FileClient:
     self.base_url = config["base_url"]
     self.headers = config.get("headers", {})
     self.token = config.get("token")
+    self.s3_endpoint_url = config.get(
+      "s3_endpoint_url"
+    )  # Optional S3 endpoint override
     self._http_client = httpx.Client(timeout=120.0)
 
   def upload(
@@ -171,9 +173,23 @@ class FileClient:
       upload_url = upload_data.upload_url
       file_id = upload_data.file_id
 
-      # Fix LocalStack URL if needed
-      if options.fix_localstack_url and "localstack:4566" in upload_url:
-        upload_url = upload_url.replace("localstack:4566", "localhost:4566")
+      # Override S3 endpoint if configured (e.g., for LocalStack)
+      if self.s3_endpoint_url:
+        from urllib.parse import urlparse, urlunparse
+
+        parsed_url = urlparse(upload_url)
+        override_parsed = urlparse(self.s3_endpoint_url)
+        # Replace scheme, host, and port with the override endpoint
+        upload_url = urlunparse(
+          (
+            override_parsed.scheme or parsed_url.scheme,
+            override_parsed.netloc,
+            parsed_url.path,
+            parsed_url.params,
+            parsed_url.query,
+            parsed_url.fragment,
+          )
+        )
 
       # Step 2: Upload file to S3
       if options.on_progress:

{robosystems_client-0.2.21 → robosystems_client-0.2.23}/robosystems_client/extensions/materialization_client.py

@@ -15,6 +15,7 @@ from ..api.materialize.get_materialization_status import (
   sync_detailed as get_materialization_status,
 )
 from ..models.materialize_request import MaterializeRequest
+from .operation_client import OperationClient, OperationProgress, MonitorOptions
 
 logger = logging.getLogger(__name__)
 
@@ -27,6 +28,7 @@ class MaterializationOptions:
   rebuild: bool = False
   force: bool = False
   on_progress: Optional[Callable[[str], None]] = None
+  timeout: Optional[int] = 600  # 10 minute default timeout
 
 
 @dataclass
@@ -66,6 +68,14 @@ class MaterializationClient:
     self.base_url = config["base_url"]
     self.headers = config.get("headers", {})
     self.token = config.get("token")
+    self._operation_client = None
+
+  @property
+  def operation_client(self) -> OperationClient:
+    """Get or create the operation client for SSE monitoring."""
+    if self._operation_client is None:
+      self._operation_client = OperationClient(self.config)
+    return self._operation_client
 
   def materialize(
     self,
@@ -75,13 +85,13 @@ class MaterializationClient:
     """
     Materialize graph from DuckDB staging tables.
 
-    Rebuilds the complete graph database from the current state of DuckDB
-    staging tables. Automatically discovers all tables, materializes them in
-    the correct order (nodes before relationships), and clears the staleness flag.
+    Submits a materialization job to Dagster and monitors progress via SSE.
+    The operation runs asynchronously on the server but this method waits
+    for completion and returns the final result.
 
     Args:
         graph_id: Graph database identifier
-        options: Materialization options (ignore_errors, rebuild, force)
+        options: Materialization options (ignore_errors, rebuild, force, timeout)
 
     Returns:
         MaterializationResult with detailed execution information
@@ -96,7 +106,7 @@ class MaterializationClient:
 
     try:
       if options.on_progress:
-        options.on_progress("Starting graph materialization...")
+        options.on_progress("Submitting materialization job...")
 
       request = MaterializeRequest(
         ignore_errors=options.ignore_errors,
@@ -125,6 +135,7 @@ class MaterializationClient:
 
       response = materialize_graph(**kwargs)
 
+      # Handle non-200 status codes
       if response.status_code != 200 or not response.parsed:
         error_msg = f"Materialization failed: {response.status_code}"
         if hasattr(response, "content"):
@@ -148,25 +159,68 @@ class MaterializationClient:
           error=error_msg,
         )
 
+      # Get the operation_id from the queued response
       result_data = response.parsed
+      operation_id = result_data.operation_id
 
       if options.on_progress:
-        options.on_progress(
-          f"✅ Materialization complete: {len(result_data.tables_materialized)} tables, "
-          f"{result_data.total_rows:,} rows in {result_data.execution_time_ms:.2f}ms"
-        )
-
-      return MaterializationResult(
-        status=result_data.status,
-        was_stale=result_data.was_stale,
-        stale_reason=result_data.stale_reason,
-        tables_materialized=result_data.tables_materialized,
-        total_rows=result_data.total_rows,
-        execution_time_ms=result_data.execution_time_ms,
-        message=result_data.message,
-        success=True,
+        options.on_progress(f"Materialization queued (operation: {operation_id})")
+
+      # Monitor the operation via SSE until completion
+      def on_sse_progress(progress: OperationProgress):
+        if options.on_progress:
+          msg = progress.message
+          if progress.percentage is not None:
+            msg += f" ({progress.percentage:.0f}%)"
+          options.on_progress(msg)
+
+      monitor_options = MonitorOptions(
+        on_progress=on_sse_progress,
+        timeout=options.timeout,
       )
 
+      op_result = self.operation_client.monitor_operation(operation_id, monitor_options)
+
+      # Convert operation result to materialization result
+      if op_result.status.value == "completed":
+        # Extract details from SSE completion event result
+        sse_result = op_result.result or {}
+
+        if options.on_progress:
+          tables = sse_result.get("tables_materialized", [])
+          rows = sse_result.get("total_rows", 0)
+          time_ms = sse_result.get("execution_time_ms", 0)
+          options.on_progress(
+            f"✅ Materialization complete: {len(tables)} tables, "
+            f"{rows:,} rows in {time_ms:.2f}ms"
+          )
+
+        return MaterializationResult(
+          status="success",
+          was_stale=sse_result.get("was_stale", False),
+          stale_reason=sse_result.get("stale_reason"),
+          tables_materialized=sse_result.get("tables_materialized", []),
+          total_rows=sse_result.get("total_rows", 0),
+          execution_time_ms=sse_result.get(
+            "execution_time_ms", op_result.execution_time_ms or 0
+          ),
+          message=sse_result.get("message", "Graph materialized successfully"),
+          success=True,
+        )
+      else:
+        # Operation failed or was cancelled
+        return MaterializationResult(
+          status=op_result.status.value,
+          was_stale=False,
+          stale_reason=None,
+          tables_materialized=[],
+          total_rows=0,
+          execution_time_ms=op_result.execution_time_ms or 0,
+          message=op_result.error or f"Operation {op_result.status.value}",
+          success=False,
+          error=op_result.error,
+        )
+
     except Exception as e:
       logger.error(f"Materialization failed: {e}")
       return MaterializationResult(