Can an old worker overwrite a result?
Conditional acceptance checks the required revisions and authority.
See the evidence boundary
Source-qualified; live recovery remains unqualified.
Reliability
Inspect access, revisions, recovery, and retention. Source-tested controls and live production assurance are different; Kam is not yet running for customers.
Recorded review: 2026-10-07. Live deployment, permissions, performance, and production authorization remain separate gates.
Your questions, explicit controls
Conditional acceptance checks the required revisions and authority.
Source-qualified; live recovery remains unqualified.
The server resolves access. Knowing a record ID is not permission.
Source controls exist; deployed permission review remains separate.
A correction adds a revision. Earlier revisions remain readable while retained.
Implemented in source; exact reads remain subject to access and retention.
An expired required input must remain explicit, not silently become current.
Retention contracts exist; managed context compilation is planned.
How far each part has been proven
As of the recorded review on 2026-10-07, nothing is live-tested. This is a fixed review, not a live monitor.
Design direction. No implementation is claimed.
Implemented in reviewed source with source-level tests. Not executed as a packaged artifact.
Exercised as a packaged or local artifact (CI, local lab, or simulated AWS transports). No live AWS deployment.
A passed live qualification receipt binds this exact package to an isolated AWS deployment.
Live-qualified and authorized for a named, bounded pilot. Not general availability.
Live-qualified and explicitly authorized for production use.
| Component | Commit | Reference | Notes |
|---|---|---|---|
| Source the website claims were reviewed against | 1db8cf00 | main through PR #219 | Every public capability statement is checked against this checkpoint. |
| Reviewed source, packaged and qualified in CI | 1db8cf00 | main · qualification run 37686977815 | Same commit as the reviewed source. Package, SDK and native artifact round trips passed with simulated AWS transports; not a live deployment. |
| Packaged candidate selected for live qualification | 284f26e5 | PR #206 candidate · merged as a215d31f · run 37605352449 | Named by the backend live-AWS approval document at the reviewed checkpoint. No live receipt exists. |
| Native developer toolkit | 1db8cf00 | merged in PR #176 (d5056454) · native artifact round trip in run 37686977815 | Linux x64 only. No public distribution. |
| History and State SDK candidate | 1db8cf00 | SDK 0.36.0 · artifact round trip in run 37686977815 | Not published to npm. The website console vendors this exact tarball. |
Deployment check (2026-10-07). No deployment of the History/State candidate was found in the inspected AWS Regions. Existing Kam resources belong to earlier products and are not evidence for this one. Live qualification receipts recorded: 0.
| 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 | Not deployed. Package coverage of View reconciliation is not confirmed for the website. |
| State queries & Components | Source-implemented | SDK 0.36.0 candidate; whether the SDK artifact round trip exercises queries is not confirmed for the website. |
| Metrics, materialize & watch | Planned · not available | Design preview only. |
| Turn Lifecycle | Locally qualified | Merged native toolkit; reference-only local frames. |
| Context compiler | Planned · not available | Design direction only. |
| 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. |
Reviewed code: 1db8cf00. Package picked for live testing: 284f26e5. Live deployment: none yet.
Exact revisions, pinned daily pages, corrections, rolling windows, and independent 400/730-day synthetic-history checks. Synthetic time is not observed uptime.
State pointers, immutable structured Observations, and change evidence are conditionally persisted. The SDK 0.36.0 candidate reads current Active State and exact retained Observations. No State or Context endpoint is deployed.
Bounded View registration, acyclic reverse-dependency membership, replay-safe cursor/task progress, and bounded same-scope multi-source dependency processing are implemented. Cross-scope joins and a deployed State endpoint remain staged.
The reviewed SDK 0.36.0 baseline, unpublished and undeployed, implements state(), component(), and bounded select stages (where, pick, orderBy, take) with explain() and value() over the admitted evidence of one View's Active State. SDK 0.37.0 merged in PR #220 (not publicly published and not included in the pinned 0.36.0 website qualification) adds bounded operators over that same selected collection. General source-payload queries, managed metrics, calculation caching, graph traversal, materialize(), watch(), and lifecycle integration remain separate planned capabilities.
Validated local Turn Frames, reference preparation, and State profiling exist in the merged native toolkit and run locally only. They do not intercept live AgentCore turns, submit model requests, persist managed Turn Receipts, or authorize external effects.
The product direction is to resolve current operational checkpoints, detect typed changes, compile bounded Observations, bind turns to exact ReadSets, and revalidate consequential effects. No live runtime hook or managed action barrier is claimed.
Native 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.
Bounded 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.
Destination 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.
A versioned long-term summary baseline and automatic S3 archival are not implemented. Checkpoint recovery does not preserve expired contributions as institutional knowledge.
The verification plan replays real Kam Sports history through the unchanged History contract across the 365-UTC-date working window and checks exact reads, corrections, and recovery. Kam Sports grading stays authoritative; Kam records grades, it never computes them. No run has completed yet.
A read-only, Amplify-authenticated console browses workspaces, scopes, UTC days, and exact revisions through existing History API reads. It is not connected to a live History deployment, because none exists yet; without configuration it reads nothing.
Source checks and independent artifact execution do not establish deployed IAM, a Marketplace listing, production SLOs, compliance approval, or measured costs and latency.
Recovery
If a worker restarts, saved work is picked up again. Work based on an older version is rejected, and anything uncertain stays visible instead of being retried blindly.
Retention
Expired contributions are removed from the reducer’s rolling state.
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 | Separate lifecycle policy | AWS documents explicit deletion workflows. Raw-event expiry is not a universal long-term-record deletion policy. |
History, State, and retention
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.
The working window contains today and the previous 364 UTC dates. It advances each day, not through annual resets.
Processing resumes from the persisted checkpoint and applies accepted transitions. Exact reads use published views rather than rebuilding the full history.
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 contractSpeed
No production p99 is published yet. Speed will be measured on a live deployment, step by step, alongside the oldest unfinished work and errors.
Security review
Build, dependency, and test evidence is ready to review. Live permissions, isolation, and data deletion still need live testing.
One project. A clear test.
Tell us what your agents do and what keeps going wrong. We set what success looks like first.