Skip to content

docs: rewrite runtime and evals/testing references#10

Merged
victorchimakanu merged 1 commit into
mainfrom
aron/docs-runtime-evals-updates
Jun 14, 2026
Merged

docs: rewrite runtime and evals/testing references#10
victorchimakanu merged 1 commit into
mainfrom
aron/docs-runtime-evals-updates

Conversation

@victorchimakanu

@victorchimakanu victorchimakanu commented Jun 14, 2026

Copy link
Copy Markdown
Contributor

Rewrites the runtime and evals docs to match how Aomi actually runs an App today.

reference/runtime.mdx

Documents the public execution model: what the runtime owns, the turn lifecycle, the model and tool loop, App tools vs host capabilities, user state, the transaction harness (stage to simulate to commit), simulation before signing, wallet callbacks, and SSE streaming.

guides/evals-testing.mdx

Documents the four testing layers: tool unit tests, test.json App e2e journeys, forked chain validation, and AomiBench. Clarifies when a model provider key is and is not needed.

Verified accurate against the SDK contract (DynAomiTool, stage_tx, simulate_batch, commit_txs). Cross links resolve.

Authored by @arixon.eth.

Closes #11

Copilot AI review requested due to automatic review settings June 14, 2026 10:50
@victorchimakanu victorchimakanu merged commit 171dd85 into main Jun 14, 2026
3 checks passed

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Updates the documentation to reflect the current public execution model of the hosted Aomi runtime and clarifies the recommended testing/evaluation layers for Apps, including wallet-aware flows.

Changes:

  • Rewrote reference/runtime.mdx to document the turn lifecycle, model/tool loop, transaction harness, simulation-before-signing, wallet callbacks, and SSE + snapshot patterns.
  • Rewrote guides/evals-testing.mdx to describe the testing ladder (unit → e2e → fork validation → AomiBench) and clarify when provider keys are required.
  • Updated cross-references and index/README blurbs to match the new structure and anchors.

Reviewed changes

Copilot reviewed 7 out of 8 changed files in this pull request and generated 2 comments.

Show a summary per file
File Description
reference/runtime.mdx Replaces architecture/session-manager-centric content with the public runtime execution model and wallet/tx flow docs.
guides/evals-testing.mdx Reframes testing guidance into layers and adds guidance on provider keys, e2e specs, and smoke tests.
reference/index.mdx Updates the Runtime card description to match the rewritten runtime page.
README.md Updates the docs map blurbs for runtime and evals/testing.
guides/custom-tools.mdx Updates link text to the renamed “Evals and testing” page.
concepts/use-cases.mdx Updates the SSE streaming anchor to the new runtime section heading.
package.json Adds a Node manifest (currently minimal).
.gitignore Adds Node/macOS ignores for local development artifacts.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread package.json
Comment on lines +1 to +3
{
"dependencies": {}
} No newline at end of file
Comment thread concepts/use-cases.mdx
### Alert and Execution Bot

Instead of simple notifications, build agents that act. A user sets "alert me and buy $50 if this crosses 60%", and the agent both notifies and prepares the transaction, cutting the delay between signal and action. Uses [SSE streaming](/reference/runtime#streaming--events) for real time triggers.
Instead of simple notifications, build agents that act. A user sets "alert me and buy $50 if this crosses 60%", and the agent both notifies and prepares the transaction, cutting the delay between signal and action. Uses [SSE streaming](/reference/runtime#streaming-and-session-snapshots) for real time triggers.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Runtime and evals/testing docs rewrite (Arixon)

3 participants