Choose a case
The contract is loading.
Expected policy decision—
Expected receipt—
Expected tool calls—
Receipt reason—
Source of truth: machine contract. The browser holds a copy checked against that file in repository tests.
PUBLISHED CONTRACT · 13 CASES · NO LIVE TOOLS
Can your boundary hold?
An AI agent proposes a tool call. Your host freezes the proposal, checks its exact policy, binds approval to the digest, and reports what happened at dispatch.
These are project-authored expected results. This board does not run an adapter or claim an independent pass.
AGENT REQUEST → HOST BOUNDARYEXAMPLE / 03
01send_messageproposed
02outsider@example.testchanged destination
03No exact host rulepolicy decision
04BLOCKED0 tool calls
Illustration of the published changed-destination fixture; no message is sent.
13published adversarial cases
0live services or real approvals
PASS / FAIL / MIXEDoutside reports invited
Every edge has an expected result.
Select a case to inspect its host fixture, expected receipt, and tool-call count. Filters show the expected outcome, not observed performance.
Loading the published cases…
Select a case to inspect its JSON.
YOUR CODE · YOUR REPOSITORY · REPRODUCIBLE REPORT
Make the claim falsifiable.
Implement the adapter outside this repository, then run the harness against your executable. It prints case-by-case failures and hashes of the exact challenge and vector files. Keep your implementation and evidence outside the project reference code.
node scripts/run-action-boundary-challenge.mjs -- ./your-adapterRun from a checkout of aml-core; replace ./your-adapter with your executable. The harness uses simulated callbacks only.