Synthetic State inspection
Public example · Synthetic browser exampleReviewed 2026-10-15 · Website example. Synthetic records and authored explanations. No engine, AWS, agent, or model execution.
Reliability
Check the controls behind exact, recoverable State.
Review the State boundary for Amazon Bedrock AgentCore: scope authorization, stale authority, exact retained revisions, and bounded work. Source implementation and cloud qualification remain separate.
Current public status
- Public examples
- Recorded NFL snapshot and synthetic State inspector · no model execution
- SDK
- Private 0.40.0 · evaluation access
- Hosted service
- Unavailable · live qualification pending
Source review: 2026-10-14. SDK 0.40.0. Public availability and engineering evidence answer different questions.
Review availability and evidence by capability
Exact History
Evaluation access only · Locally qualifiedReviewed 2026-10-14 · Private SDK 0.40.0. Source and offline artifact evidence. Evaluation requires a supplied SDK artifact and authorized endpoint; retained versions and supported writes only.
Recorded-input inspection
Evaluation access only · Source-implementedReviewed 2026-10-14 · Private SDK 0.40.0. Inspect exact references recorded by the application. This does not infer an agent’s reasons or prove model consumption.
Read permissions
Evaluation access only · Locally qualifiedReviewed 2026-10-14 · Private SDK 0.40.0. Source and offline checks do not establish deployed isolation or a compliance certification.
Accepted-work recovery
Evaluation access only · Source-implementedReviewed 2026-10-14 · Backend e16b81b4. Recover Kam’s accepted work. Agent-task recovery and uncertain external effects remain the application’s responsibility.
Declared dependent Views
Evaluation access only · Source-implementedReviewed 2026-10-14 · Backend e16b81b4. Bounded same-scope dependency reconciliation. General calculation caching, cross-scope joins, and managed workflow recovery are planned.
Conversational inspection
Unavailable · No qualified public releaseReviewed 2026-10-14 · No qualified public conversational interface. Local development does not establish a public model-backed service.
Managed Context preparation
Unavailable · Planned · not availableReviewed 2026-10-14 · Product direction. Exact Context APIs exist in source. Automatic ranking, runtime interception, and managed AgentCore wiring remain planned.
Reviewed 2026-10-14
Inspect the qualification boundary.
Backend e16b81b4 · private SDK 0.40.0. Source implementation, artifact qualification, cloud qualification, and a production commitment establish different facts.
Source implemented
RecordedEvidence and remaining boundary
Reviewed History, State, and exact Context contracts.
Source tests establish implemented behavior; they do not establish deployed controls.
Locally qualified
Selected artifactsEvidence and remaining boundary
Offline service, private SDK, and Linux x64 native artifact receipts.
Simulated AWS and local fixtures. Capability-specific source/local levels remain separate.
Cloud-qualified
Not establishedEvidence and remaining boundary
Requires a passing qualification receipt from an isolated AWS deployment, tied to the exact release.
Passing live qualification receipts recorded for this release combination: 0. Provisioning attempts do not qualify it.
Production commitment
Not offeredEvidence and remaining boundary
Requires cloud qualification and explicit authorization for a defined operating scope.
No public hosted offer, production SLA, or production authorization is established by this review.
Security and authority
Authorize the scope. Recheck the serving boundary.
The reviewed contracts separate identity, scope permission, current authority, and retained evidence.
Principal and scope
The server resolves the workspace and scope authorized for the authenticated principal. A browser-supplied tenant identifier grants no access.
Stale authority
The reviewed read and conditional-commit paths recheck lifecycle status, authorization, and version fences. If those checks fail, the operation is blocked. Retaining data does not extend permission to access it.
Missing required evidence
Exact reads keep unavailable, expired, and unresolved results explicit. Missing required evidence blocks selection of current State or assembly of a complete Context package. A newer revision is never substituted for a requested revision.
Retention and historical access
An earlier revision remains inspectable while retained and authorized. Reads stop at logical expiry, even if background storage cleanup has not finished. Permission to inspect history does not grant permission to act.
These are source and offline test boundaries. Deployed IAM, revocation, tenant isolation, erasure, and restore journeys still require cloud qualification.
Work limits and cloud latency
Bound the operation. Measure the deployed workload.
Rust and fixed work limits are design constraints. They do not establish cloud latency, throughput, or cost.
No measured cloud p99 is published for this release.
Inspect operation limits and measurement requirements
- History
- Up to 32 exact references per read; published membership pages up to 32 references.
- State query
- At most 36 storage reads, 16 stages, and 32 picks or returned items; no table scan.
- Context assembly
- At most 32 exact keys, 16 entries, and a declared evidence budget up to 192 KiB.
A measurement must name the release, AWS configuration, workload, concurrency, and sample window, alongside errors and oldest pending work. Synthetic counts and local timings are not cloud measurements.
Review correctness and failure controls
Can an old worker overwrite a result?
A write is checked against its required versions and permissions.
Check the evidence and limits
Supported by the recorded source checks; live recovery remains unqualified.
Can another workspace read my data?
The server resolves access. Knowing a record ID is not permission.
Check the evidence and limits
Source controls exist; deployed permission review remains separate.
Does a correction erase the first report?
A correction adds a revision. Earlier revisions remain readable while retained.
Check the evidence and limits
Implemented in source; exact reads remain subject to access and retention.
What happens when evidence expires?
An expired required input must remain explicit, not silently become current.
Check the evidence and limits
Retention and bounded exact-reference Context assembly exist in source; required unavailable evidence blocks complete claims.
Inspect the release evidence and exact source checkpoint
What evidence supports each capability
Six levels, from planned to production.
This review was recorded on 2026-10-14. It does not update as new runs finish.
- Planned · not available
Design direction. No implementation is claimed.
- Source-implemented
Implemented in reviewed source with source-level tests. This label does not establish package or live qualification.
- Locally qualified
Exercised as a packaged or local artifact (CI, local lab, or simulated AWS transports). This does not establish live AWS qualification.
- Live-qualified
A passed live qualification receipt binds this exact package to an isolated AWS deployment.
- Pilot only
Live-qualified and authorized for a named, bounded pilot. Not general availability.
- Production-authorized
Live-qualified and explicitly authorized for production use.
Which code and packages were reviewed
| Component | Commit | Reference | Notes |
|---|---|---|---|
| Source the website claims were reviewed against | e16b81b4 | main through PR #267 | Backend capability claims in this review refer to this checkpoint. |
| Reviewed source, packaged and qualified in CI | e16b81b4 | main · qualification run 38541006600 | Same commit and tree as the reviewed source. Service, SDK and native artifact round trips passed; simulated transports and offline consumers do not establish live qualification. |
| Historical package candidate selected for live qualification | 284f26e5 | PR #206 candidate · merged as a215d31f · run 37605352449 | Preserved from the 2026-10-07 review; this older artifact is not the current main package. No matching passed live receipt is recorded here. |
| Native developer toolkit | e16b81b4 | merged in PR #176 (d5056454) · native artifact round trip in run 38541006600 | Linux x64 only. No public distribution. |
| History and State SDK candidate | e16b81b4 | SDK 0.40.0 · artifact round trip in run 38541006600 | Not published to npm. Exact source commit, package hash and offline clean-consumer receipt are recorded in docs/content-evidence.md. |
| Website runtime SDK | 96dff834 | vendored SDK 0.46.0 · local producer 1792452589183 attempt 1 · official offline verification 2026-10-19 | Independently qualified, unpublished SDK candidate pinned for server reads. Exact archive, release receipt, SBOM and official offline verifier retain the actual local producer identity and source branch in vendor/kam-history-sdk. SDK production is separate from hosted source qualification and live authorization. Older 0.45.0, 0.43.0, 0.40.0 and 0.36.0 records remain historical. Native application builds require separate qualification. |
Deployment check (2026-10-14). Reviewed source records isolated AWS qualification attempts, including failures and cleanup. No matched passed live receipt or customer-production authorization was verified for this release combination. The older regional inventory is a historical observation, not evidence of current global absence. Live qualification receipts recorded: 0.
Capability evidence
| Capability | Shown level | Limit |
|---|---|---|
| History | Locally qualified | Package qualification is not a live deployment. |
| Identity & membership | Locally qualified | Covered by the same package qualification as History. |
| Views & current State | Source-implemented | Reviewed View and reconciliation source; no live-qualified or publicly offered hosted State service is established. |
| State queries & Components | Source-implemented | SDK 0.40.0 has a passed offline artifact receipt; the source claim is limited to supported bounded operations, not arbitrary payload queries or live service qualification. |
| Metrics, materialize & watch | Planned · not available | Design preview only. |
| Turn Lifecycle | Locally qualified | Merged native toolkit; reference-only local frames. |
| Versioned Context manifests | Source-implemented | Exact capture, ordered manifests and bounded assembly exist in source. Automatic ranking, managed runtime wiring and live model-consumption proof are not established. |
| Operational durability | Source-implemented | History and reconciliation progress are durable in source; no named checkpoint API. |
| Profiler & developer toolkit | Locally qualified | Merged; Linux x64 only; no public distribution. |
| Optional AgentCore delivery | Locally qualified | Default off; simulated AWS transports only. |
| Export, deletion & restore fence | Source-implemented | Live erasure and restore drills are qualification gates. |
The source checkpoint above lists the exact commits and packages reviewed.
Archived SDK 0.36 qualification → The October 7 receipts keep their original commits and package identities. They do not qualify the current release.
Status of each part, in detail
Ordered, versioned ledger
Source and package testedExact revisions, pinned daily pages, corrections, rolling windows, and independent 400/730-day synthetic-history checks. Synthetic time is not observed uptime.
Rust State and Observations
Source and package testedState pointers, immutable Observations, and change evidence are conditionally persisted. The private SDK reads current Active State and retained exact Observations. Offline checks do not establish production qualification.
State reconciliation
Source implementedBounded View registration, acyclic reverse-dependency membership, durable cursor/task progress, and same-scope multi-source reconciliation are implemented. General cross-scope joins remain planned.
State queries
Source implementedPrivate SDK 0.40.0 implements scoped State, Components, bounded evidence-reference queries, composition, and exact Context APIs (OpenAPI 1.31.0). Its clean offline artifact round trip passed on reviewed main. The SDK is not published to npm or qualified for customer production. Queries operate on admitted evidence references; general source-payload queries, managed metrics, materialize(), watch(), and managed lifecycle integration remain planned capabilities.
Turn Frames and profiler
Merged · locally qualifiedThe Linux x64 native toolkit qualifies reference-only local Turn Frames. Exact Context capture, manifest assembly, and a controlled request-boundary adapter also exist in source. Automatic runtime interception and managed AgentCore wiring remain planned. Model submission, completion, and business acceptance are not observed unless an injected boundary explicitly reports them.
Exact Context and request boundaries
Source implemented · live unqualifiedCapture exact evidence, assemble ordered manifest references, and record hide/restore changes. A controlled injected adapter can report request stages. Automatic interception, provider-wide budgeting, and managed action barriers remain planned.
Native developer toolkit
Merged · locally qualifiedNative toolkit 0.1.0 is merged into the backend (PR #176) and qualified in CI as a network-disabled Linux x64 artifact. No public binary release, macOS/Windows distribution, or live AWS connection is offered here.
Customer lifecycle
Source implemented · live unqualifiedBounded owner export, primary-state deletion, restore fences, and Marketplace entitlement reconciliation are implemented in source. Live buyer, erasure, restore, and revocation journeys remain qualification gates; no deployed completeness is claimed.
AgentCore delivery
Implemented · default offDestination binding, per-generation obligations, scheduling, publication receipts, exact retrieval verification, and metadata-only status are implemented. Optional Memory write-back remains separately qualified with simulated AWS transports.
Carry-forward consolidation
Proposed · not implementedA versioned long-term summary baseline and automatic S3 archival are not implemented. Checkpoint recovery does not preserve expired contributions as institutional knowledge.
Real-history verification (Kam Sports)
365-day plan · not executedA separate bounded closing-ATS replay passed locally with real Rust and simulated storage at an earlier source checkpoint. The full 365-UTC-date real-history plan, live season workload, process-crash recovery, and hosted compatibility remain unqualified. Kam Sports supplies grades; Kam records them.
History console
Implemented in website sourceThe read-only console uses configured Cognito identity and existing History reads to browse authorized workspaces, manually entered scopes, UTC days, and exact revisions. Production History configuration is absent in the reviewed web deployment, so it reads no History data.
Production assurance
Not yet qualifiedSource checks and independent artifact execution do not establish deployed IAM, a Marketplace listing, production SLOs, compliance approval, or measured costs and latency.
Recovery
Inspect retry checks and unfinished work.
Supported retries recover Kam’s accepted work and saved obligations. Required-version checks can reject outdated work. Your application keeps uncertain external effects explicit; AgentCore or your runtime owns agent-task recovery. Live restart drills remain separate.
Retention
Know which versions remain readable.
Inspect the rolling-window diagram
Working history advances one UTC date at a time
Before the working window
Expired contributions are removed from the reducer’s rolling state.
Today − 364 → today
365 UTC dates. Quiet histories also need maintenance as the window moves.
A checkpoint resumes work; it is not a lifetime summary. It preserves the applied sequence and retained rolling state, not all historical meaning.
| Data layer | Policy | Meaning |
|---|---|---|
| Kam working history | 365 UTC dates | Today and the preceding 364 UTC dates. The window advances daily; out-of-window contributions are removed from rolling state, not consolidated into a permanent baseline. |
| Kam supporting evidence | Separate inspection limits | Supporting revisions and references may remain for up to 730 days, with direct-prior-revision extensions for corrections. Inspection ends when its evidence expires; this is not automatic cold-tier archival. |
| AgentCore raw events | Configurable, up to 365 days | AWS applies this retention to raw short-term events. It is separate from Kam’s window and AgentCore long-term records. |
| AgentCore long-term records | Strategy or batch-request policy | AWS supports optional record TTL of at least 31 days and explicit deletion. With no TTL configured, those records do not expire. Raw-event expiry is a separate policy. |
How the History window moves
History, State, and retention
A rolling window. A maintained state.
Kam advances working state as outcomes arrive and time moves forward. A recovery checkpoint keeps processing continuous; it is not a permanent summary of everything the system has seen.
Rolling operational history
The working window contains today and the previous 364 UTC dates. It advances each day, not through annual resets.
Checkpointed rolling state
Processing resumes from the persisted checkpoint and applies accepted transitions. Exact reads use published views rather than rebuilding the full history.
Versioned supporting evidence
Revisions and references support inspection until their deadlines. Supporting evidence may be retained for up to 730 days, with correction-related extensions.
Current boundary: Outcomes older than the working window stop contributing to rolling state. The current reducer does not preserve their meaning in a lifetime summary or move them automatically to S3.
Carry-forward consolidation — Proposed · not implemented. Preserve selected historical meaning in a versioned summary baseline while older evidence follows a separate archive policy. This is a proposed extension, not the behavior of the current rolling reducer.
Read the retention and continuity contractOne application. One workflow.
Evaluate Kam State for your AgentCore application.
Bring one workflow with a correction or retry. Agree the baseline, scope, and success checks before starting.