Fix AWS Bedrock tool calling compatibility

chuck_data/commands/add_stitch_report.py

@@ -114,7 +114,7 @@ def handle_command(
 
 
 DEFINITION = CommandDefinition(
-    name="add-stitch-report",
+    name="add_stitch_report",
     description="Create a Stitch report notebook for a unified table",
     handler=handle_command,
     parameters={

chuck_data/commands/bulk_tag_pii.py

@@ -58,7 +58,7 @@ def handle_bulk_tag_pii(client, **kwargs):
     except Exception as e:
         # Always cleanup context on any error
         context = InteractiveContext()
-        context.clear_active_context("bulk-tag-pii")
+        context.clear_active_context("bulk_tag_pii")
         return CommandResult(False, error=e, message=f"Error: {str(e)}")
 
 
@@ -482,7 +482,7 @@ def _report_progress(step_message, tool_output_callback=None):
     """Report progress for both agent integration and direct TUI usage."""
     if tool_output_callback:
         # Agent usage - report via callback
-        tool_output_callback("bulk-tag-pii", {"step": step_message})
+        tool_output_callback("bulk_tag_pii", {"step": step_message})
     else:
         # Direct TUI usage - show progress using console like scan-pii
         console = get_console()
@@ -541,12 +541,12 @@ def _start_interactive_mode(client, **kwargs):
 
         # Store context for interactive workflow
         context = InteractiveContext()
-        context.set_active_context("bulk-tag-pii")
-        context.store_context_data("bulk-tag-pii", "phase", "review")
-        context.store_context_data("bulk-tag-pii", "catalog_name", catalog_name)
-        context.store_context_data("bulk-tag-pii", "schema_name", schema_name)
-        context.store_context_data("bulk-tag-pii", "scan_summary", scan_summary_data)
-        context.store_context_data("bulk-tag-pii", "original_kwargs", kwargs)
+        context.set_active_context("bulk_tag_pii")
+        context.store_context_data("bulk_tag_pii", "phase", "review")
+        context.store_context_data("bulk_tag_pii", "catalog_name", catalog_name)
+        context.store_context_data("bulk_tag_pii", "schema_name", schema_name)
+        context.store_context_data("bulk_tag_pii", "scan_summary", scan_summary_data)
+        context.store_context_data("bulk_tag_pii", "original_kwargs", kwargs)
 
         # Display the formatted preview like stitch setup
         console = get_console()
@@ -578,7 +578,7 @@ def _start_interactive_mode(client, **kwargs):
     except Exception as e:
         # Cleanup context on error
         context = InteractiveContext()
-        context.clear_active_context("bulk-tag-pii")
+        context.clear_active_context("bulk_tag_pii")
         return CommandResult(
             False, message=f"Error during interactive mode setup: {str(e)}"
         )
@@ -590,15 +590,15 @@ def _handle_interactive_input(client, user_input, **kwargs):
     context = InteractiveContext()
     if (
         not context.is_in_interactive_mode()
-        or context.current_command != "bulk-tag-pii"
+        or context.current_command != "bulk_tag_pii"
     ):
         return CommandResult(
             False,
             message="No active bulk-tag-pii session found. Please restart the command.",
         )
 
     # Extract context data
-    context_data = context.get_context_data("bulk-tag-pii")
+    context_data = context.get_context_data("bulk_tag_pii")
     tool_output_callback = kwargs.get("tool_output_callback")
     console = get_console()
 
@@ -622,7 +622,7 @@ def _handle_interactive_input(client, user_input, **kwargs):
         # Check for cancel commands (same as stitch)
         elif user_input_lower in ["cancel", "abort", "stop", "exit", "quit", "no"]:
             # Cancel and cleanup
-            context.clear_active_context("bulk-tag-pii")
+            context.clear_active_context("bulk_tag_pii")
             console.print(f"\n[{INFO_STYLE}]Bulk PII tagging cancelled.[/{INFO_STYLE}]")
             return CommandResult(True, message="Bulk PII tagging cancelled.")
 
@@ -643,7 +643,7 @@ def _handle_interactive_input(client, user_input, **kwargs):
 
     except Exception as e:
         # Cleanup context on error
-        context.clear_active_context("bulk-tag-pii")
+        context.clear_active_context("bulk_tag_pii")
         return CommandResult(
             False, message=f"Error during interactive input handling: {str(e)}"
         )
@@ -657,7 +657,7 @@ def _proceed_with_tagging(client, context_data, tool_output_callback):
 
     # Clear context since we're proceeding
     context = InteractiveContext()
-    context.clear_active_context("bulk-tag-pii")
+    context.clear_active_context("bulk_tag_pii")
 
     try:
         # Get updated statistics after any exclusions
@@ -793,10 +793,10 @@ def _exclude_table(context, context_data, table_name):
     scan_summary["excluded_tables_count"] = excluded_tables_count
 
     # Update context with new scan summary
-    context.store_context_data("bulk-tag-pii", "scan_summary", scan_summary)
+    context.store_context_data("bulk_tag_pii", "scan_summary", scan_summary)
 
     if remaining_tables_with_pii == 0:
-        context.clear_active_context("bulk-tag-pii")
+        context.clear_active_context("bulk_tag_pii")
         return CommandResult(
             True,
             message=f"Table '{table_name}' excluded. No PII tables remaining - nothing to tag.",
@@ -855,7 +855,7 @@ def _handle_modification_request(context, context_data, user_input, console):
 
     # Update stored scan summary
     updated_scan_summary = modify_result["scan_summary"]
-    context.store_context_data("bulk-tag-pii", "scan_summary", updated_scan_summary)
+    context.store_context_data("bulk_tag_pii", "scan_summary", updated_scan_summary)
 
     console.print(f"\n[{SUCCESS_STYLE}]Configuration updated![/{SUCCESS_STYLE}]")
     if modify_result.get("modification_summary"):
@@ -1200,7 +1200,7 @@ def _helper_modify_pii_config(scan_summary, user_request, llm_client):
 
 
 DEFINITION = CommandDefinition(
-    name="bulk-tag-pii",
+    name="bulk_tag_pii",
     description="Scan schema for PII columns and bulk tag them with semantic tags after interactive confirmation",
     handler=handle_bulk_tag_pii,
     parameters={

chuck_data/commands/catalog_selection.py

@@ -158,7 +158,7 @@ def handle_command(client: Optional[DatabricksAPIClient], **kwargs) -> CommandRe
 
 
 DEFINITION = CommandDefinition(
-    name="select-catalog",
+    name="select_catalog",
     description="Set the active catalog for operations by name with fuzzy matching",
     handler=handle_command,
     parameters={

chuck_data/commands/create_volume.py

@@ -79,7 +79,7 @@ def handle_command(
 
 
 DEFINITION = CommandDefinition(
-    name="create-volume",
+    name="create_volume",
     description="Create a new volume in Unity Catalog.",
     handler=handle_command,
     parameters={

chuck_data/commands/create_warehouse.py

@@ -71,7 +71,7 @@ def handle_command(
 
 
 DEFINITION = CommandDefinition(
-    name="create-warehouse",
+    name="create_warehouse",
     description="Create a new SQL warehouse in the Databricks workspace.",
     handler=handle_command,
     parameters={

chuck_data/commands/getting_started.py

@@ -61,7 +61,7 @@ def handle_command(client: Optional[DatabricksAPIClient], **kwargs) -> CommandRe
 
 
 DEFINITION = CommandDefinition(
-    name="getting-started",
+    name="getting_started",
     description="Display helpful tips and examples for using Chuck",
     handler=handle_command,
     parameters={},

chuck_data/commands/job_status.py

@@ -531,7 +531,7 @@ def handle_command(
 
 
 DEFINITION = CommandDefinition(
-    name="job-status",
+    name="job_status",
     description="Check status of a Chuck job via backend or Databricks. "
     "If no parameters provided, uses the last cached job ID.",
     handler=handle_command,

chuck_data/commands/jobs.py

@@ -114,7 +114,7 @@ def handle_job_status(client: Optional[DatabricksAPIClient], **kwargs) -> Comman
 
 
 LAUNCH_JOB_DEFINITION = CommandDefinition(
-    name="launch-job",
+    name="launch_job",
     description="Launch a Databricks job using a config file",
     usage_hint="launch_job --config_path=/path/to/config.json --init_script_path=/init/script.sh",
     parameters={
@@ -136,7 +136,7 @@ def handle_job_status(client: Optional[DatabricksAPIClient], **kwargs) -> Comman
 )
 
 JOB_STATUS_DEFINITION = CommandDefinition(
-    name="job-status",
+    name="job_status",
     description="Get the status of a Databricks job run",
     usage_hint="job_status --run_id=123456",
     parameters={

chuck_data/commands/list_catalogs.py

@@ -108,7 +108,7 @@ def handle_command(
 
 
 DEFINITION = CommandDefinition(
-    name="list-catalogs",
+    name="list_catalogs",
     description="Lists all catalogs in the current workspace. By default returns data without showing table. Use display=true when user asks to see catalogs.",
     handler=handle_command,
     parameters={

chuck_data/commands/list_models.py

@@ -91,7 +91,7 @@ def handle_command(client: Optional[DatabricksAPIClient], **kwargs) -> CommandRe
 
 
 DEFINITION = CommandDefinition(
-    name="list-models",
+    name="list_models",
     description="List available language models from the LLM provider (by default, only shows models with tool calling support)",
     handler=handle_command,
     parameters={

chuck_data/commands/list_schemas.py

@@ -119,7 +119,7 @@ def handle_command(
 
 
 DEFINITION = CommandDefinition(
-    name="list-schemas",
+    name="list_schemas",
     description="Lists all schemas in the current catalog. By default returns data without showing table. Use display=true when user asks to see schemas.",
     handler=handle_command,
     parameters={

chuck_data/commands/list_tables.py

@@ -145,7 +145,7 @@ def handle_command(
 
 
 DEFINITION = CommandDefinition(
-    name="list-tables",
+    name="list_tables",
     description="List tables in a Unity Catalog schema. By default returns data without showing table. Use display=true when user asks to see tables.",
     handler=handle_command,
     parameters={

chuck_data/commands/list_volumes.py

@@ -103,7 +103,7 @@ def handle_command(
 
 
 DEFINITION = CommandDefinition(
-    name="list-volumes",
+    name="list_volumes",
     description="List volumes in a Unity Catalog schema.",
     handler=handle_command,
     parameters={

chuck_data/commands/list_warehouses.py

@@ -88,7 +88,7 @@ def handle_command(
 
 
 DEFINITION = CommandDefinition(
-    name="list-warehouses",
+    name="list_warehouses",
     description="Lists all SQL warehouses in the current Databricks workspace. By default returns data without showing table. Use display=true when user asks to see warehouses.",
     handler=handle_command,
     parameters={

chuck_data/commands/model_selection.py

@@ -68,7 +68,7 @@ def handle_command(client: Optional[DatabricksAPIClient], **kwargs) -> CommandRe
 
 
 DEFINITION = CommandDefinition(
-    name="select-model",
+    name="select_model",
     description="Set the active model for agent operations",
     handler=handle_command,
     parameters={

chuck_data/commands/monitor_job.py

@@ -151,7 +151,7 @@ def _monitor_job_completion(
                 record_count = job_data.get("record-count", 0)
 
                 if normalized_state in ["succeeded", "success"]:
-                    success_msg = f"Job completed successfully!"
+                    success_msg = "Job completed successfully!"
                     if record_count:
                         success_msg += f" Records: {record_count:,}"
                     console.print(f"[{SUCCESS_STYLE}]{success_msg}[/{SUCCESS_STYLE}]")
@@ -369,7 +369,7 @@ def handle_command(
             ):
                 return CommandResult(
                     False,
-                    message=f"Authentication failed. Please authenticate using: chuck auth",
+                    message="Authentication failed. Please authenticate using: chuck auth",
                     error=e,
                 )
             else:
@@ -412,7 +412,7 @@ def handle_command(
 
 
 DEFINITION = CommandDefinition(
-    name="monitor-job",
+    name="monitor_job",
     description="Monitor a Chuck job with real-time progress updates until completion. "
     "Provide either --job-id OR --run-id (not both), or omit both to monitor the last launched job.",
     handler=handle_command,

chuck_data/commands/run_sql.py

@@ -389,7 +389,7 @@ def _format_paginated_results_for_agent(result: CommandResult) -> Dict[str, Any]
 
 
 DEFINITION = CommandDefinition(
-    name="run-sql",
+    name="run_sql",
     description="Execute a SQL query on a Databricks SQL warehouse.",
     handler=handle_command,
     parameters={

chuck_data/commands/scan_pii.py

@@ -69,7 +69,7 @@ def handle_command(client: Optional[DatabricksAPIClient], **kwargs) -> CommandRe
 
 
 DEFINITION = CommandDefinition(
-    name="scan-schema-for-pii",
+    name="scan_schema_for_pii",
     description="Scan all tables in the current schema (or specified catalog/schema) for PII and/or customer data",
     handler=handle_command,
     parameters={

chuck_data/commands/schema_selection.py

@@ -154,7 +154,7 @@ def handle_command(client: Optional[DatabricksAPIClient], **kwargs) -> CommandRe
 
 
 DEFINITION = CommandDefinition(
-    name="select-schema",
+    name="select_schema",
     description="Set the active schema for operations by name with fuzzy matching",
     handler=handle_command,
     parameters={