Skip to content

Workflow — Sprint execution

Generated from the architecture model

This page is rendered from model/**/*.yaml by tools/docs_model during mkdocs build. Edit the YAML, not this page; hand-written design lives on the linked service, platform and plane pages.
Workflow id sprint-execution · version 1 · Draft (Draft → InReview → Published → Deprecated, BC-04)
Coordinator sprint-execution-coordinator · family Lifecycle Feedback & Governance
Owner service WorkflowEngineService (BC-38) under Run Control (BC-03)
Starts on RunAccepted from RunControlService (event)
Steps 4 · gated 1 · agents 2
Budget per run 5000000 tokens · cap 500.0 USD · 20160 min
Descriptor workflow-definition-v1 · schema
Status target

Runs a sprint's planned items as child runs in order, reviews each item's outcome against its acceptance criteria and closes the sprint with the evidence.

Authored design, Draft (D54, D57)

These definitions were authored on 2026-10-14 from the coordinator cards as design assumptions. None is published, evaluated or has run; agents are named by id as design bindings, not as tested integrations.

Definition

flowchart TD
    start(("RunAccepted"))
    load_plan["Load the sprint plan"]
    run_item[("Run each item")]
    review_item["Review the outcome"]
    close_sprint["Close the sprint"]
    start --> load_plan
    load_plan --> run_item
    run_item --> review_item
    review_item --> close_sprint
    done(("WorkflowRunCompleted"))
    close_sprint --> done
    class review_item gated
    classDef gated stroke:#B45309,stroke-width:2px
Hold "Alt" / "Option" to enable pan & zoom

Shapes: rectangle = agent attempt · double rectangle = tool call · stadium = human decision · diamond = condition evaluated by the engine · parallelogram = fan-out or join · circle = timer · cylinder = sub-workflow · flag = compensation. A thick amber border marks a gated step.

Steps

# Step Kind Runs Gate Class Depends on Retry Timeout Compensation What it does
1 Load the sprint plan
load-plan		 agent work-preparation-orchestrator none read — exponential ×2 PT30M — Validates the plan's items, acceptance criteria and order.
2 Run each item
run-item		 sub-workflow plan-run none sandbox load-plan exponential ×2 P14D — Starts a child run per item through plan-run, in the plan's order, inheriting scope and budget.
3 Review the outcome
review-item		 agent product-owner evaluation read run-item fixed ×1 PT30M — Checks each outcome against the acceptance criteria; a rejected item is re-planned once.
4 Close the sprint
close-sprint		 agent work-preparation-orchestrator none sandbox review-item exponential ×2 PT30M — Records the evidence and the open items as artifacts.

Gates and approvals

No approval is required: every step runs in the read or sandbox class; the agents' own tool calls still carry their classes (D21). Compensation steps run in reverse order of the succeeded steps on failure after the last checkpoint; a step without a compensation leaves its sandbox output in place and the run ends Failed with the evidence (ADR-0014, recovery not replay).

Inputs, outputs and events

Direction Name Descriptor
in sprint-plan artifact-v1
out sprint-evidence artifact-v1

Starts on RunAccepted; emits RunCompleted, WorkflowRunCompleted, plus the engine's WorkflowRunStarted, StepReady, StepRunStateChanged and WorkflowRunCompleted / WorkflowRunFailed and Run Control's run and attempt events (ADR-0014).

Decisions and traceability

FR: FR-03 Idempotent work requests and persisted run stateXL: XL-03 Read-only assessmentFUX: FUX-04 Observable run stateADRs: ADR-0014, ADR-0024 · ADR index

Definition authored 2026-10-14 from the coordinator card sprint-execution-coordinator (D54); Draft until an evaluation gate (ADR-0021) and a review publish it as a BC-04 asset release.