schemaxisTemplate and parameter reference
Reusable recipe reference.
The five-point product explanation
01The agent declares. Schemaxis marshals the data.
In the strict declared-work interface, the agent never runs code or directly handles source data. It declares where the data comes from or how it is generated, which operations it passes through, and how it is output. Schemaxis marshals immutable input captures, sealed execution and outputs retained by digest.
This describes who operates on the inputs: no agent-supplied arbitrary scripts, shell or direct source-filesystem manipulation. The agent can receive bounded observations and receipt content; this does not promise that data is hidden from the model. Sealed container execution requires an explicitly configured, qualified backend. Native applications execute trusted runtime code. The historical local MCP demonstration alone does not establish that isolation.
02The plan is checked before anything executes.
Admission, the declared schema, task scope and budget reservation are checked before execution. A request outside its authority is refused before a native job can run. Planning and inspection can run without launching the applications; native result verification is a separate step that reports the checks actually performed. In the retained MCP demonstration, a NumPy request under a SymPy-only scope returned SCOPE_EXCEEDED. Calls stopped at planning: zero native execution, all four prior NumPy output digests unchanged, and no successful current invocation to claim.
Historical prepared-recipe local MCP demonstration, core 5cfe1b0. It is separate from both the comparative study and the hosted container-isolation proof.
03Smaller models failed alone, then produced passing artifacts.
Haiku 4.5: 22/110 without → 110/110 with Schemaxis; Sonnet 4.6: 22/110 without → 110/110 with Schemaxis; GPT-5.6 Luna: 68/110 without → 110/110 with Schemaxis. Haiku 4.5’s native initial output had 32/32 images rejected, while its retained transcript called the result “production-ready”. The Schemaxis artifacts passed the required checks. The core supplies the verification state and receipt instead of relying on the agent’s success sentence. This records a misleading claim and changed artifact outcomes; it does not measure a general reduction in false-reporting propensity.
29 September 2026: one authoring conversation per model and method, older model versions, 110 checks across an initial task and revision on small, purpose-built serial ParaView fixtures. Checks are not independent tasks. Some historical Schemaxis runs inspected implementation details or used helper code; one revision wrapper was broken despite passing artifacts. These are artifact outcomes, not qualification of the new strict no-shell authoring interface. The Opus native control was excluded after provider substitution.
04Reuse a supported recipe with varied parameters and a new receipt.
A supported declared recipe can be repeated with varied authorised inputs and parameters; each execution produces its own receipt. The reusable document and bounded parameter contract are the mechanism, not a measured advantage for junior staff. Anyone using the supported, configured environment and authorised inputs can repeat it. Compatible runtimes, scope and checks still apply; the record preserves honest failure and unknown states.
The downloadable two-case SymPy example checks local-core binding and host planning only: no native execution or new receipt was created by those preflight checks, and no hosted file-template endpoint is implied.
05Keep the frontier tradeoff and the cheaper-model result together.
Frontier models passed either way in the retained paired studies, and Schemaxis was slower.
GPT-5.6 Luna with Schemaxis passed all 110 checks at about one tenth of Astra’s native historical scored API cost (US$0.0815 versus US$0.8828); n=1 conversation each, older versions and 29 September 2026 prices. This is not current pricing or a total compute/support-cost estimate.
Interactive explanation
Inspect the files that define a job.
Use the same reviewed template with new parameter values. Follow the files on the landing page, then inspect the exact two-case example below.
Follow the files ↗Self-operated core example · host preflight checked
One template. Two parameter files.
Both cases were bound and planned by core 68e139a without launching SymPy. Native execution and fresh verification are separate steps.
Actual bound host plan · selected fields
operation: isolateRealRoots coefficients: ["1", "0", "-2"] maximumIntervalWidth: "1/1000" publications: real-roots.csv + evidence application launches in this check: 0Inspect full recorded host plan ↗
Template excerpt
{
"version": "schemaxis.workflow-template/1",
"id": "website.real-root-family",
"parameters": {
"constant": {
"label": "Constant coefficient c",
"kind": "string",
"default": "-2",
"constraints": {
"minLength": 1,
"maxLength": 8
},
"help": "An exact rational string. Expressions are refused by the SymPy plan.",
"target": {
"scope": "workflow",
"pointer": "/settings/constant"
}
}
}
}Full manifest ↗Separate parameter file
{
"version": "schemaxis.workflow-values/1",
"template": {
"id": "website.real-root-family",
"revision": 1,
"digest": "144083e5590b2e235b73bb1ede4ab3e1612c7930197fbcfa48201ae3066b5d50"
},
"values": {
"constant": "-2"
}
}Second checked case, c = −3 ↗x**2 was refused with SYMPY_INVALID_COEFFICIENT. Those checks do not prove native execution, fresh result verification or hosted file-template admission.Use the operator’s local contract.
schemaxis template inspect template.json schemaxis template bind template.json --values sqrt2-values.json --document-only schemaxis template plan template.json --values sqrt2-values.json
These are self-operated file/CLI entry points. For an untrusted agent, preserve the configured admission/isolation policy; do not switch to trusted-local to bypass it. See the local docs for exact options and boundaries.
Read the implemented template contract ↗A family of jobs is not every workflow.
This example varies a rational polynomial coefficient through the same SymPy root-isolation operation. It does not establish arbitrary app composition, native CFD execution, large hosted uploads or a ready-made customer workflow library.
A maintained workflow family with version compatibility, fixtures, repair and support is a commercial proposal under review. Two support hours in the old hosted draft do not silently include bespoke template development.
Customer workflow logic, supplied examples, outputs and continuing reuse rights need clear final terms. Ephemeral task/upload identities, keys, captures and receipts stay bound to their original environment.