One Semantic Model, Multiple Representations
MRS is a semantic score model plus protocols for safe, bounded editing. It is commonly represented in two complementary forms:
An implementation may keep canonical state in a database/graph form for performance, then export MRS-S as needed.
Agents read MRS-S content in Working Set Envelopes. Agents write MRS-Ops operations. The orchestrator validates and applies operations to canonical state.
File Types
- MRS-S:
.mrsor.mrs-s—application/vnd.mrs+sexpr - MRS-Ops:
.mrs-ops—application/vnd.mrs-ops+sexpr - Encoding: UTF-8 (no BOM)
/MRS-Specification-RFC#16-mime-types-and-file-extensions
Minimal MRS-S Score
- Every measure has
:id(UUID) and:number(display) - Every event has
:id(UUID) — no:atrequired in storage (orchestrator computes it) - Players own instruments; instruments appear in measure content
Working Set Envelope
For agent tasks, the orchestrator extracts a Working Set Envelope:- Scope uses UUIDs — not measure numbers
:bundlegrants lane permissions:context-viewsprovide task-relevant information:contentis valid MRS-S the agent can read
Agent Output: MRS-Ops
Agents write typed operations, not complete fragments:- Explicit operations:
create-event, not “here’s the whole fragment” - Temporary IDs:
"e1","s1"— orchestrator assigns UUIDs - No derived fields: No
:atrequired — orchestrator computes it - Spans reference tmp-ids:
"e1"in same envelope is valid
Orchestrator Response
The Workflow
Why This Works
See:
/MRS-Specification-RFC#5-mrs-ops-the-mutation-protocol