Adds activity call stack support

[sfmskywalker]

Adds support for tracking the activity call stack during workflow execution. This allows for better debugging and understanding of workflow execution flow.

• Adds new fields to ActivityExecutionRecord and ActivityExecutionSummaryRecord for tracking scheduling activity information and call stack depth.
• Introduces a GetExecutionChainAsync method to retrieve the chain of activity executions, enabling traversal of the call stack.
• Includes a database migration to add the new fields to the ActivityExecutionRecords table.
• Fixes an infinite loop issue that could occur during activity execution chain traversal.

[Copilot]

Pull request overview

This PR adds support for tracking the activity call stack during workflow execution to enable better debugging and understanding of workflow execution flow.

Changes:

• Introduces new database fields (SchedulingActivityExecutionId, SchedulingActivityId, SchedulingWorkflowInstanceId, CallStackDepth, SerializedMetadata, AggregateFaultCount) to track activity scheduling relationships and call stack depth
• Implements GetExecutionChainAsync method in both MongoDB and Dapper persistence stores to retrieve the execution chain with infinite loop protection using a visited set
• Updates activity providers to handle the new return type from CreateActivity, which now returns a result object containing the activity and additional metadata

Reviewed changes

Copilot reviewed 9 out of 9 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
src/modules/persistence/Elsa.Persistence.Dapper.Migrations/Runtime/V3_7.cs	Adds database migration to create new columns for activity execution tracking
src/modules/persistence/Elsa.Persistence.Dapper/Modules/Runtime/Records/ActivityExecutionRecord.cs	Adds new properties for scheduling context, metadata, fault count, and call stack depth
src/modules/persistence/Elsa.Persistence.Dapper/Modules/Runtime/Records/ActivityExecutionSummaryRecord.cs	Adds metadata and aggregate fault count to summary record
src/modules/persistence/Elsa.Persistence.Dapper/Modules/Runtime/Stores/DapperActivityExecutionRecordStore.cs	Implements GetExecutionChainAsync, updates filter criteria, and adds mapping for new fields
src/modules/persistence/Elsa.Persistence.MongoDb/Modules/Runtime/ActivityExecutionLogStore.cs	Implements GetExecutionChainAsync with pagination and cross-workflow chain traversal support
src/modules/servicebus/Elsa.ServiceBus.MassTransit/Services/MassTransitActivityTypeProvider.cs	Updates activity constructors to handle new CreateActivity return type
src/modules/http/Elsa.Http.Webhooks/ActivityProviders/WebhookEventActivityProvider.cs	Updates activity constructor to handle new CreateActivity return type
src/modules/cms/Elsa.OrchardCore/ActivityProviders/OrchardContentItemsEventActivityProvider.cs	Updates activity constructor to handle new CreateActivity return type
src/modules/agents/Elsa.Agents.Activities/ActivityProviders/AgentActivityProvider.cs	Updates activity constructor to handle new CreateActivity return type

Comments suppressed due to low confidence (1)

src/modules/persistence/Elsa.Persistence.MongoDb/Modules/Runtime/ActivityExecutionLogStore.cs:102

• The logic for stopping at workflow boundaries appears to be incorrect. The current condition stops traversal whenever SchedulingWorkflowInstanceId is not null, even if it's the same workflow instance. This would incorrectly stop the traversal within the same workflow when one activity schedules another. The condition should compare SchedulingWorkflowInstanceId with WorkflowInstanceId to detect actual cross-workflow boundaries. Consider changing the condition to: if (!includeCrossWorkflowChain && record.SchedulingWorkflowInstanceId != null && record.SchedulingWorkflowInstanceId != record.WorkflowInstanceId)

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[sfmskywalker]

@copilot open a new pull request to apply changes based on the comments in this thread. Make sure you understand & agree with the feedback before making changes.

[Copilot]

@sfmskywalker I've opened a new pull request, #120, to work on those changes. Once the pull request is ready, I'll request review from you.

[lukhipolito-nexxbiz]

Build step is failing

[gitguardian]

⚠️ GitGuardian has uncovered 1 secret following the scan of your pull request.

Please consider investigating the findings and remediating the incidents. Failure to do so may lead to compromising the associated services or software components.

🔎 Detected hardcoded secret in your pull request

GitGuardian id	GitGuardian status	Secret	Commit	Filename
13223926	Triggered	Generic Password	b13f55a	src/modules/scheduling/Elsa.Scheduling.Quartz.EFCore.PostgreSql/ShellFeatures/QuartzPostgreSqlFeature.cs	View secret

🛠 Guidelines to remediate hardcoded secrets

1. Understand the implications of revoking this secret by investigating where it is used in your code.
2. Replace and store your secret safely. Learn here the best practices.
3. Revoke and rotate this secret.
4. If possible, rewrite git history. Rewriting git history is not a trivial act. You might completely break other contributing developers' workflow and you risk accidentally deleting legitimate data.

To avoid such incidents in the future consider

• following these best practices for managing and storing secrets including API keys and other credentials
• install secret detection on pre-commit to catch secret before it leaves your machine and ease remediation.

---

^{🦉 GitGuardian detects secrets in your source code to help developers and security teams secure the modern development process. You are seeing this because you or someone else with access to this repository has authorized GitGuardian to scan your pull request.}