Skip to content

feat(agent): integrate expert collaboration and L4 skill policy runtime - #37

Merged
1-ztc merged 9 commits into
mainfrom
codex/expert-collaboration-runtime
Aug 5, 2026
Merged

feat(agent): integrate expert collaboration and L4 skill policy runtime#37
1-ztc merged 9 commits into
mainfrom
codex/expert-collaboration-runtime

Conversation

@1-ztc

@1-ztc 1-ztc commented Aug 5, 2026

Copy link
Copy Markdown
Contributor

What this merges

  • bounded approved expert collaboration runtime and host contracts
  • host observability span processors and run correlation
  • deterministic L4 Skill experiment evaluator and policy provider
  • portable preflight tests that load built package output

Validation

Dependency

RDK Studio develop already consumes this Moss API surface through its submodule; merging this PR makes that dependency available from Moss main.

d-robotics and others added 9 commits July 30, 2026 21:41
…d correlation

- initObservability accepts extraSpanProcessors so embedding hosts (e.g. RDK
  Studio) can collect spans in-process without their own OTel SDK; their
  presence alone starts the SDK even with OTLP/file/console tracing off.
- MOSS_OTEL_SAMPLE_RATIO head-samples OTLP export; host collectors do their
  own tail sampling and see every span.
- moss.session span records host-supplied runId (options.runId) when present,
  falling back to sessionKey, so host trace stores can correlate to runs.
feat(skill-learning): add trusted experiment policy evaluator
@1-ztc
1-ztc merged commit 553ac58 into main Aug 5, 2026
3 checks passed
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.

2 participants