Add AI Capabilities to SpacetimeDB

This issue tracks reimplementing the work from stale PR #4589, which has been closed because it is too far out of date to merge directly.

## Original pull request
- PR #4589: [[Draft] Add AI Capabilities to SpacetimeDB](https://github.com/clockworklabs/SpacetimeDB/pull/4589)
- Original author: @definenoob

## What the original PR was trying to do
With this PR, STDB becomes the first AI-enabled database. **Seeking feedback from CWL on this**.

Summary

• Adds native ONNX inference as a host-side capability exposed to WASM modules via the SpacetimeDB ABI (spacetime_10.5)
• Models are loaded by name from {server_data_dir}/models/{name}.onnx on the host filesystem and cached after first use — model bytes never enter WASM memory, only input/output
  tensor data crosses the boundary
• Uses tract-onnx (pure Rust) for inference, no C++ dependencies or WASI required

Design

Single ABI call (spacetime_10.5):

• onnx_run(name_ptr, name_len, input_ptr, input_len, out) -> errno — loads/caches model by name, runs inference, returns output tensors via BytesSource

Crate changes:

• spacetimedb-lib — shared Tensor type (Vec shape + Vec data) with BSATN serialization
• spacetimedb-primitives — ONNX_ERROR errno code
• spacetimedb-bindings-sys — raw ABI declaration + safe wrapper
• spacetimedb-bindings — high-level OnnxClient with single run(name, inputs) method, exposed via ReducerContext::onnx and ProcedureContext::onnx
• spacetimedb-core — host-side OnnxModel using tract-onnx, per-instance model cache (HashMap<String, OnnxModel>) in WasmInstanceEnv, path traversal validation, models_dir wired
  from HostController.data_dir

Usage from a module:

let input = vec![Tensor { shape: vec![1, 10], data: vec![0.0; 10] }];
let output = ctx.onnx.run("bot_brain", &input)?;

Test plan

• Place a .onnx model file in {data_dir}/models/ and verify ctx.onnx.run("model_name", &input) succeeds
• Verify inference produces correct output tensors for known model inputs
• Verify second call to same model uses cache (no re-parse)
• Verify invalid model names (path traversal, empty) return errors
• Verify loading a nonexistent model returns a clear error
• Verify compilation on both native and wasm32-unknown-unknown targets

The onnx feature flag works across all three crates:

• spacetimedb (bindings): features = ["onnx"] — enables ctx.onnx.run(...) API
• spacetimedb-bindings-sys: features = ["onnx"] — enables raw ABI declaration
• spacetimedb-core: features = ["onnx"] — enables host-side inference + tract-onnx dependency

Without the feature, tract-onnx isn't compiled, no ONNX code exists in the binary, and the ABI function isn't registered.

This is ACID-compliant AI inference.

run the model inside the reducer to decide what to write. The inference result feeds directly into the transactional state change — no round-trip to an external service, no eventual consistency, just one atomic unit of "think and act."

## Closure context
- Closed from the `close-stale-pr-create-issue` stale-PR sweep.

## Reimplementation notes
- Reimplement this work on top of current `master` in a new PR.
- Keep the original PR linked as historical context and as a source of useful implementation ideas where still relevant.

Start by reviewing closed PR #4589, then compare its proposed changes with the current spacetimedb-lib, spacetimedb-primitives, spacetimedb-bindings-sys, spacetimedb-bindings, and spacetimedb-core crates. Use the listed test plan as the acceptance checklist, including model loading, inference output, caching, invalid names, missing models, and native and wasm32 compilation.