Astvyr
MISSION OS

A Mission is not a prompt.

It is a unit of work, audit, cost and result. One Mission can carry several agents, environments, approvals and release attempts — and it survives disconnects, retries and restarts.

ANATOMY

What every Mission carries.

Before anything expensive runs, the user sees the plan, the cost estimate, the permissions and the risk class.

Intent

A natural-language request, an issue, a pull request, an alert, a ticket or an API event.

Acceptance Contract

Versioned, measurable pass / fail / unknown criteria with an owner, created before implementation.

Risk Profile

Blast radius, reversibility, data sensitivity, customer impact and the approvals required.

Plan

A dependency-aware plan that can be edited before and during execution.

Execution

Multi-agent work with bounded tools, budgets and human checkpoints.

Verification

Independent checks that rebuild the change from the approved contract and challenge it.

Evidence Bundle

Sealed, signed artifacts that justify a readiness decision.

Release Plan

Strategy, metric gates, observation window and a prepared rollback.

Outcome

What actually happened in production, measured in the observation window.

Economics

Model, compute and storage cost, budget and the estimated infrastructure delta.

ACCEPTANCE CONTRACT

Criteria are fixed before the work starts.

A versioned contract with measurable pass, fail and unknown conditions, a named owner and an evidence source for each criterion. A Verifier cannot edit it after verification begins.

IDCategoryCriterionEvidence source
AC-01FunctionalFunctional behaviour matches the requirementAcceptance tests
AC-02FunctionalOperation is idempotent under retryFault injection run
AC-03BusinessBusiness rules hold for edge inputsProperty-based tests
AC-04CompatibilityAPI stays backward compatibleContract tests
AC-05DataExisting data survives the migrationRestore rehearsal
AC-06AvailabilityNo downtime for the consumerLoad and replay run
AC-07SecurityAuthorisation and audit are enforcedSecurity checks
AC-08ReliabilityRetries and duplicate webhooks are safeIdempotency checks
AC-09PerformanceP95 latency stays inside budgetPerformance regression run
AC-10OperationsDashboards and runbooks are updatedOperational review
AC-11ReleaseCanary does not push error or failure metrics above their approved thresholdLive staged metric evaluation
AC-12RecoveryRecovery path is verifiedRollback rehearsal

This is the shape of a real contract from the product: twelve criteria, each mapped to objective proof. Coverage is 12/12 mapped — and a criterion that needs residual risk approval says so out loud.

LIFECYCLE

Twenty states, with invariants that cannot be skipped.

The state machine is held by deterministic services. A model can propose a transition; it can never quietly make one.

DRAFT → CONTRACTING → AWAITING_APPROVAL → PLANNING → READY → RUNNING → PAUSED → BLOCKED → VERIFYING → REWORK → EVIDENCE_READY → AWAITING_RELEASE → RELEASING → OBSERVING → COMPLETED → FAILED → ROLLED_BACK → CANCELLED → REJECTED → REOPENED

A release candidate is immutable in AWAITING_RELEASE.

The observation window is never shortened silently.

On cancellation, credentials and resources are revoked.

State is preserved: a Mission survives disconnects, retries and restarts.

AGENTS

Nine roles. Separation of duty, not a swarm.

Multi-agent orchestration is used only where separation improves quality, parallelism or verification independence. A simple task takes one cheap path.

Planner

Builds the dependency-aware plan and keeps it honest as facts change.

Builder

Produces the change. Cannot promote it to production without a gate.

Test engineer

Turns acceptance criteria into durable checks.

Reviewer

Reads the change against architecture and standards.

Security

Checks secrets, permissions, dependencies and supply chain.

DevOps

Owns environments, pipelines and the delivery path.

Verifier

Independent. Rebuilds from the contract, runs adversarial and hidden checks.

Incident

Correlates telemetry and proposes bounded remediation.

Coordinator

Deterministic arbiter of state transitions. An LLM never changes authoritative state.

RULES OF ENGAGEMENT
  • Multi-agent orchestration is used only where separation of duty improves quality, parallelism or verification independence. Simple tasks take one cheap path.
  • The author of a change is never its only reviewer.
  • A Verifier cannot edit acceptance criteria after verification has started.
  • Agents communicate through structured artifacts: plan, hypothesis, finding, evidence request, decision proposal. A hidden, unauditable chat is forbidden.
  • Every tool call is schema-bound, policy-checked, quota-limited, time-limited and audited.
CHECKPOINTS

Five places where a person decides.

Autonomy grows inside policy. These gates are where responsibility stays human.

01

Contract approval

The acceptance criteria and risk class are approved before any code is written.

02

Plan approval

The dependency-aware plan and its blast radius are reviewed.

03

Diff review

The change set is reviewable before it is applied, with granular accept and reject.

04

Release approval

The release candidate, gates and rollback plan are approved.

05

Emergency confirmation

Destructive actions and account-level changes require explicit confirmation.

SCHEDULING

Five things the organisation sets, six the scheduler must respect.

Priority, concurrency, deadlines, budgets and maintenance windows are the organisation's to decide. The scheduler's job is to place work around the constraints it cannot argue with.

Priority

Set by the organisation.

Concurrency

Set by the organisation.

Deadlines

Set by the organisation.

Budgets

Set by the organisation.

Maintenance windows

Set by the organisation.

Model capacity

The scheduler must account for scarce model capacity.

Sandbox region

The scheduler must account for the sandbox region.

Data boundary

The scheduler must account for the data boundary.

Repository locks

The scheduler must account for repository locks.

Deployment freeze

The scheduler must account for the deployment freeze.

Human approval availability

The scheduler must account for human availability for approvals.

COLLABORATION

Work on a Mission is shared, not forwarded.

A Mission is a place a team works in: ownership and mentions, review threads bound to a version, handoffs that carry their own context, and decision records that stay readable afterwards.

Shared Mission

Roles, ownership and mentions on one Mission, so it is visible at a glance who decides, who verifies and whose action is awaited.

Threaded review

Discussion on a plan, a change and a piece of evidence stays attached to the versioned object and survives an update.

Tracker and chat integration

Status syncs with issue trackers, chat and documentation systems without losing the source link or the authority behind it.

Decision records

An approved decision becomes an ADR with context, options, decision, consequences, owner and a supersession path.

Organisation standards

A Mission checks the standards and golden paths that apply to it, and explains any deviation.

Grounded documentation

Repository documentation cites the code and configuration behind every fact; a stale page is flagged and updated.

Reusable runbooks

Runbooks and playbooks are versioned, tested, scoped, and tied to an owner and a policy.

Asynchronous handoff

A handoff carries state, completed evidence, open questions, residual risk and the next action.

Conflict log

Disagreements between recommendations and human overrides stay visible for review instead of being smoothed away.

Knowledge export

Documentation, decision records, templates and metadata export in documented formats.

TEMPLATES

Repeatable work, not blank prompts.

Templates carry their own contract shape, checks and risk class — and they improve every time an escape is traced back to a gap.

Feature delivery
Bug fix
Security remediation
Dependency upgrade
Database migration
Cloud migration
Incident recovery
Large-scale refactor
CONTEXT

Seven levels of context, with citations and freshness.

Retrieval returns the minimum relevant set. Stale, conflicting and low-trust knowledge is detected and shown as such, never silently trusted.

Immediate

The open file, the selection, the current task.

Repository

Symbols, dependencies, tests, history and ownership.

Organisation

Standards, decisions, golden paths, runbooks.

Delivery

Pipelines, environments, release state, change calendar.

Production

Telemetry, incidents, alerts, SLO state.

External

Documentation, advisories, dependency and provider status.

Personal

The developer's own preferences and saved context, kept local-first.

OUTCOME GRAPH

Every change keeps its thread.

The Release Outcome Graph links intent to criteria, change, evidence, release, production outcome and, when it happens, the incident — in both directions.

Intent → Acceptance criteria → Context snapshot → Change set → Evidence → Release → Production outcome → Incident → Learning

Deep Wiki

Generated architecture and service maps that stay current.

ADR Library

Proposed, approved and superseded decisions with owners.

Standards

Organisation standards a Mission must follow or explicitly justify deviating from.

Runbooks

Versioned, bounded, dry-run capable automation with approvals and audit.

Incident knowledge

What happened, what was missed, which check changed as a result.

Golden paths

The approved, safe self-service route to production.

UNIT OF WORK

One Mission from intent to outcome.

Pause, resume, cancel, retry or branch from a checkpoint — without losing state or doing anything twice.