docs: define modular local agent contracts
This commit is contained in:
1 parent
7fb257095f
commit
dd359642ff
12 files changed
+412
-27
No files matched your search
@@ -20,7 +20,7 @@ Every implementation task names its owning module, public boundary and affected
|
||||
| HTTP/MCP | Validate inputs and map outputs/errors; expose only operations in the allowlisted catalog. No duplicate business rules. |
|
||||
| Frontend | Read API data, route state and render evidence. No canonical mutation route or hidden browser proposal client. |
|
||||
| Local skills | Reason and propose using public contracts. No direct canonical edits, SQL tools or assumed human authority. |
|
||||
| Local agent runtime | Own bounded pipeline execution, model/tool dispatch and resumable client checkpoints. Use the service through public MCP contracts; never import its persistence or owner-credential internals. |
|
||||
| Local agent profile and pipelines | Own research-role routing, stage procedures, budgets and resumable checkpoint guidance. The existing host supplies model/tool execution. Use public MCP contracts; never depend on service persistence or owner-credential internals. |
|
||||
|
||||
The operation catalog declares name/version, request/response schemas, handler, capabilities, permitted transports, idempotency semantics and limits. Test the generated route/tool surfaces, including forbidden exposure. An MCP `readOnlyHint` is documentation, not enforcement.
|
||||
|
||||
|
||||
Reference in new issue
Block a user