Logging and Cost Calculation

Agent Forge provides comprehensive logging for workflow executions and automatic cost calculation for AI model usage.

Logging System

Agent Forge offers two complementary logging interfaces:

Real-Time Console (Manual Executions)

During manual workflow execution, logs appear in real-time in the Console panel on the right side of the workflow editor:

The console shows:

• Block execution progress with active block highlighting
• Real-time outputs as blocks complete
• Execution timing for each block
• Success/error status indicators

Logs Page (All Executions)

All workflow executions—whether triggered manually, via API, Chat, Schedule, or Webhook—are logged to the dedicated Logs page:

Screenshot

The Logs page provides:

• Comprehensive filtering by time range, status, trigger type, folder, and workflow
• Search functionality across all logs
• Live mode for real-time updates
• 7-day log retention (upgradeable for longer retention)

Log Details Sidebar

Clicking on any log entry opens a detailed sidebar view:

Screenshot

Block Input/Output

View the complete data flow for each block with tabs to switch between:

Execution Timeline

For workflow-level logs, view detailed execution metrics:

• Start and end timestamps
• Total workflow duration
• Individual block execution times
• Performance bottleneck identification

Model Breakdown

For workflows using AI blocks, expand the Model Breakdown section to see:

Screenshot

• Token Usage: Input and output token counts for each model
• Cost Breakdown: Individual costs per model and operation
• Model Distribution: Which models were used and how many times
• Total Cost: Aggregate cost for the entire workflow execution

Workflow Snapshot

For any logged execution, click "View Snapshot" to see the exact workflow state at execution time:

Screenshot

The snapshot provides:

• Frozen canvas showing the workflow structure
• Block states and connections as they were during execution
• Click any block to see its inputs and outputs
• Useful for debugging workflows that have since been modified

Programmatic Log Access

List and fetch execution logs over HTTP using a personal API key from Settings → API Keys. Pass the key in the X-API-Key header. Session cookies from the web UI continue to work for the Logs page.

List logs — GET /api/logs

Returns paginated logs from every workspace you can access. Optionally narrow the scope:

# All accessible logs
curl "https://your-host/api/logs?details=full&limit=10" \
  -H "X-API-Key: sk-forge-..."

# Logs for one workspace
curl "https://your-host/api/logs?workspaceId=WS_ID&triggers=webhook" \
  -H "X-API-Key: sk-forge-..."

# Poll a specific execution (e.g. after webhook)
curl "https://your-host/api/logs?executionId=EXEC_UUID&details=full" \
  -H "X-API-Key: sk-forge-..."

Response shape: { data: [...], total, page, pageSize, totalPages }.

Fetch log details — GET /api/logs/by-id/{id}

Returns full execution output for a single log row, including data.executionData.finalOutput and data.executionData.traceSpans. Use the log id from the list response (not the executionId).

curl "https://your-host/api/logs/by-id/LOG_UUID" \
  -H "X-API-Key: sk-forge-..."

Webhook polling flow

1. Trigger the webhook (returns immediately with { "message": "Webhook processed" }).
2. Poll GET /api/logs?executionId=...&details=full or filter by workflowIds until the run appears.
3. Call GET /api/logs/by-id/{id} for the complete finalOutput.