What this type of data looks like
Water utility ledger and report data sources include water supply pump stations, pipe network monitoring terminals, SCADA systems for wastewater treatment plants, residential water meter metering nodes, and more. Update rhythms are layered:
- Real-time monitoring data (such as pump station operating voltage, pipe network pressure) updates every 15 seconds
- Metering data (such as residential water consumption) syncs every 15 minutes
- Monthly ledger consolidation data is generated daily at midnight
Each individual data document includes site code, monitoring timestamp, physical quantity value and corresponding unit. Fields include instantaneous flow (m³/h), cumulative water supply (m³), water turbidity (NTU), pH value, and others. Ledger files are archived by region and month.
What constraints these characteristics impose on workflow orchestration
Decentralized data sources require workflows to configure multi-source data pull nodes to connect to different types of water utility equipment systems. Layered update rhythms require setting differentiated trigger times for different nodes to avoid invalid pulls or data lag. Fields with standardized units require configuring unit conversion rules during data cleaning to unify measurement calibers. The need to aggregate ledgers by region and month requires preset grouping fields and aggregation logic to ensure summary results align with water utility management statistical dimensions. The need to pass parameters such as site ID and statistical cycle across nodes requires configuring global variables to store intermediate results, supporting data association in subsequent report generation steps.
How to set configurations
Reference only; verify against the target FastGPT release and deployment documentation.
| Configuration Item | Recommended Setting | Rationale |
|---|---|---|
| Data source trigger timing | Real-time nodes trigger every 15 seconds, daily ledger nodes trigger at 2 AM daily | Matches the actual update rhythms of different water utility data sources, reduces invalid requests |
| Field mapping rules | Convert instantaneous flow to m³/h, convert cumulative water supply to ten thousand m³ | Unifies measurement calibers for water utility data, eliminates unit ambiguity |
| Global variable storage | Enable the variables configuration to store site ID, statistical cycle, and token | Used to pass key parameters across nodes, supports calls from downstream modules |
| Tool call trigger | Automatically trigger based on consolidation completion status | Implements the logic for the model to independently select and call tools, aligns with business requirements |
| Failure retry configuration | Retry 3 times for single node failures, with a 60-second interval | Addresses pull failures caused by water utility network fluctuations or temporary equipment offline status |
| Node ID binding | Configure a unique nodeId for each data source node | Facilitates troubleshooting cross-node variable transfer issues, fixes problems where global variables cannot be used across modules |
Three Common Mistakes
- Downstream modules cannot retrieve global variables after workflow runs, with corresponding fields empty. Cause: The parameters that need to be passed across nodes were not declared in the
variablesconfiguration, or a uniquenodeIdwas not configured for the node. - MCP tool calls return a 401 unauthorized error, and the preset token parameter is not retrieved. Cause: The token was not stored in a global variable, or the token field in
variableswas not associated in the tool call configuration. - Ledger consolidation results include data from incomplete time periods, with incorrect statistical scope. Cause: No data time range filtering rules were configured for data source nodes, and the trigger timing does not match the data update cycle.
How to Confirm the Configuration Is Correct
- Check the trigger time configuration of each data source node to confirm it matches the update frequency of the corresponding water utility equipment.
- Review the global variable configuration items to confirm that required parameters such as site ID, statistical cycle, and token have been correctly declared.
- Run a test workflow, then check the input parameters of the downstream module to confirm that the global variable values passed from upstream nodes can be obtained.
- Trigger a tool call, then review the tool's input parameter configuration to confirm that the corresponding fields in the global variables have been associated.
The values provided here are common starting points and should be evaluated against the reader's own samples.
Question material comes from public community discussions. Configuration values are common starting points and should be measured against your own samples. Verified on 2026-09-28.