Skip to content

clarify conformance ownership #7

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jothsnapraveena merged 1 commit into from
Aug 8, 2026
Merged

clarify conformance ownership #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 16 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,9 @@ The **AI Operations Specification (AIOS)** is a vendor-neutral contract for desc
It gives instrumentation, observability, evaluation, safety, and reliability tools a shared vocabulary and portable JSON artifacts for Runs, Steps, model interactions, tool calls, retrieval, memory, evaluations, signals, and incidents.

This repository defines the contract. It does **not** run agents, collect telemetry, host dashboards, or provide an SDK.
It also does **not** own the primary end-user CLI for conformance checks;
implementation repositories may provide that convenience on top of the
normative rules defined here.

## Why it exists

Expand Down Expand Up @@ -37,6 +40,13 @@ The work is cumulative, not four competing formats:

Later layers depend on earlier ones. They are available for design feedback and prototype implementations; acceptance of a later layer does not bypass open review gates in an earlier layer.

Conformance should be understood in two layers:

- **AIOS defines the normative rules**: schemas, conformance requirements,
canonical fixtures, and expected validation behavior
Comment thread
jothsnapraveena marked this conversation as resolved.
- **implementations may provide tooling**: for example, AgenticLens can expose
a practical `conformance` CLI over those rules without owning the standard

## Choose a path

- **Understand the model:** read the [v0.1 overview](specification/v0.1/README.md), [core concepts](specification/v0.1/core-concepts.md), and [conceptual examples](specification/v0.1/examples.md).
Expand Down Expand Up @@ -94,6 +104,10 @@ uv run pytest

AIOS defines shared meaning, relationships, events, and exchange artifacts. SDK behavior, dashboards, provider catalogs, recommendation logic, storage, and transport exporters belong in implementation repositories.

That same boundary applies to conformance: the specification owns the rules
and expected behavior, while implementation repositories may offer user-facing
commands that execute those checks.

See [SPECIFICATION.md](SPECIFICATION.md) for the complete reading order and maturity rules, or [CONTRIBUTING.md](CONTRIBUTING.md) to propose a change.

## What's Next
Expand All @@ -103,7 +117,8 @@ Upcoming specification work (see [ROADMAP.md](ROADMAP.md)):
- **Provenance and evidence concepts** — standardize source references,
evidence lineage, and derived findings as first-class spec objects
- **Conformance test suite** — producers can validate artifacts against the
spec independently
spec independently, while implementation repositories can expose convenient
CLIs on top
- **Naming conventions** — lock down field naming rules, casing, and
abbreviation policy
- **Migration guides** — clear upgrade paths between spec versions
11 changes: 10 additions & 1 deletion ROADMAP.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,6 +91,11 @@ Success means implementers can determine whether they may safely consume an arti

Publish minimal and advanced canonical artifacts, namespace rules, third-party extension guidance, and conformance expectations.

The specification should define what conformance means, but it should not
require the specification repository itself to be the primary end-user entry
point for running those checks. Implementation repositories may expose
convenient CLIs as long as they follow the normative rules defined here.

### Phase 6.x — Provenance, Evidence & Operational Artifacts

Formalize concepts proven in implementation repositories.
Expand All @@ -101,6 +106,9 @@ Formalize concepts proven in implementation repositories.
lineage, and derived findings as first-class spec objects
- conformance test suite — so producers can validate their artifacts against
the spec without importing a DeepAgentLabs package
- conformance requirements, canonical fixtures, and expected validation
behavior — so implementations such as AgenticLens can offer user-facing
`conformance` commands without owning the standard
- naming conventions document — lock down field naming rules, casing,
singular/plural, abbreviation policy

Expand Down Expand Up @@ -142,7 +150,8 @@ Specification milestone documents live under `specification/` and clearly state
## Package roles

- `ai-operations-spec` defines the standard.
- `agenticlens` instruments and exports the standard.
- `agenticlens` instruments and exports the standard, and may provide
user-facing conformance tooling over AIOS-defined rules.
- `agentic-chaos` adds resilience and fault-testing evidence using the same model.
- `deep-agentic-core-mcp` reads, exposes, and transforms conforming artifacts.

Expand Down
Loading