Add utilization diagnostics and correction ledger
This commit is contained in:
@@ -811,6 +811,17 @@ Improve operational observability so Audita runs can be debugged and performance
|
||||
|
||||
This phase should follow the registry/prompt work so diagnostics can include stable module, validator, prompt, and schema identifiers.
|
||||
|
||||
## Implementation status (2026-05-13)
|
||||
|
||||
This workstream is now implemented:
|
||||
- run diagnostics include `utilization-diagnostics.json` with run-level and module-level timing/utilization data;
|
||||
- utilization diagnostics include per-validator timing summaries keyed by stable validator keys;
|
||||
- process reports include diagnostics references for utilization and correction-ledger artifacts;
|
||||
- run diagnostics include `correction-ledger.json` with flattened correction disposition records (`applied`, `rejected`, `skipped`, `failed`) keyed by stable module instance and proposal index;
|
||||
- successful runs emit both artifacts; failure paths emit partial artifacts when runner state exists.
|
||||
|
||||
This status update applies only to utilization diagnostics and correction-ledger artifacts. Release-hardening evaluation fixtures and later roadmap items remain planned.
|
||||
|
||||
## Scheduler utilization diagnostics
|
||||
|
||||
Add module-level and run-level metrics for LLM scheduling and execution.
|
||||
|
||||
Reference in New Issue
Block a user