Goal Runs
Runs
Every time a goal executes—whether triggered manually, by schedule, or through automation—Cod3x logs it as a Run.
Runs capture the full execution lifecycle, performance metrics, tool usage, and reasoning trail behind every decision the agent makes.
Viewing All Runs
The Runs tab displays a chronological list of all past executions.
Each entry includes:
Run Number – Sequential identifier (e.g., Run #20).
Status – Completed, Failed, or In Progress.
Duration – Total runtime.
Credits Used – Compute credits consumed during execution.
Timestamp – Exact start time in your configured timezone.
Click View beside any run to open its detailed breakdown.
This high-level view helps you track stability and cost efficiency over time—for instance, noticing that your “Execute Short on RSI Overbought” goal consistently completes within 8 minutes using ~750 credits.
Run Details
Inside a specific run, you’ll find a full diagnostic overview divided into several parts:
Summary
At the top, you’ll see:
Overall Score & Success Rate – Measures how efficiently the run executed.
Execution Time & Resource Efficiency – Evaluate runtime performance relative to prior runs.
Status, Start/End Time, and Credits Used – Key metadata for accountability.
Efficiency Analysis
Each run automatically computes performance ratios:
Time Efficiency – Measures how well runtime was utilized.
Tool Utilization – Percentage of available tools used effectively.
Resource Efficiency – How optimized compute usage was.
Data Collection Effectiveness – Success rate of data retrieval operations.
These metrics help you identify slow or inefficient workflows, especially when comparing similar goals or model configurations.
Step Details
Clicking on a step expands its full technical view:
Required Tools – Tools invoked and their configuration.
Tool Executions – The exact inputs and outputs sent to the tool.
Success Criteria – What condition had to be met for the step to pass.
Step Assessment – A short reasoning note explaining what the agent evaluated and why it proceeded or exited.
For example:
GetGMXPositionsTool fetched all active GMX positions. The returned array was empty, which met the success criteria. Workflow exited early with “No positions/orders to review.”
This makes debugging simple — you can trace exactly which tools ran, what data they received, and how each decision was made.
Reviewing Failures
If a run fails, Cod3x highlights the failed step in red and logs the tool output for inspection. Common failure causes include:
Missing or invalid wallet data
Empty or rate-limited API responses
Incompatible tool chains
Failures don’t halt learning — they improve the next run. You can update the goal, adjust tools, or re-run directly from the interface to test improvements.
Practical Uses
Audit how an agent interpreted your trading logic.
Compare run times and credit usage after changing models.
Debug step-by-step logic for complex execution chains.
Validate whether each trigger and tool behaved as intended.
Every run is fully reproducible, ensuring transparency and accountability in automated decision-making.
Last updated