Replace supervisor with agentrun worker service
Move agent-run orchestration from the legacy supervisor path into the new agentrun worker/service package and wire it through coredata, server, policies, and GraphQL resolvers. This consolidates run lifecycle handling around lease-aware workers and aligns API surface with the new agent-run domain model so reviewers can follow one coherent execution path. Signed-off-by: Bryan Frimin <bryan@probo.com>
This commit is contained in:
@@ -63,9 +63,9 @@ type (
|
||||
Result ToolResult
|
||||
}
|
||||
|
||||
// Checkpointer is supervisor-internal. Implementations may use raw
|
||||
// Checkpointer is worker-internal. Implementations may use raw
|
||||
// run IDs because public API/service methods perform tenant scoping and
|
||||
// authorization before a run reaches the supervisor.
|
||||
// authorization before a run reaches the worker.
|
||||
Checkpointer interface {
|
||||
Save(ctx context.Context, runID string, cp *Checkpoint) error
|
||||
Load(ctx context.Context, runID string) (*Checkpoint, error)
|
||||
@@ -76,7 +76,7 @@ type (
|
||||
}
|
||||
|
||||
SuspendedError struct {
|
||||
RunID string // Set when the outer loop has a store+runID (supervisor-managed).
|
||||
RunID string // Set when the outer loop has a store+runID (worker-managed).
|
||||
Checkpoint *Checkpoint // Set when returning from an inner agent-as-tool (no store).
|
||||
}
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user