proxy: add swap matrix with solver-based model swapping (#646)

Add a new swap matrix to supersede groups for running concurrent models.
The matrix uses a solver that picks the lowest cost evictions to make a
requested model available. This simple approach along with a very basic
DSL grammar can enable very complex swapping scenarios.

- add DSL parser for set expressions with & (AND), | (OR), (), +ref
- add MatrixConfig structs, validation, and topological sort for +ref
- add MatrixSolver with cost-minimizing swap decisions
- add Matrix runtime integrating solver with Process lifecycle
- integrate matrix into ProxyManager with if-branches at all endpoints
- update config.example.yaml and config-schema.json with matrix schema
- config enforces groups XOR matrix (cannot use both)

fixes #643

config-schema.json

@@ -325,6 +325,44 @@
             },
             "description": "A dictionary of group settings. Provides advanced controls over model swapping behaviour. Model IDs must be defined in models. A model can only be a member of one group. Behaviour controlled via swap, exclusive, persistent."
         },
+        "matrix": {
+            "type": "object",
+            "description": "Solver-based alternative to groups. Declares valid combinations of concurrent models. The solver minimizes eviction cost when swapping. A config must use either groups or matrix, not both.",
+            "required": [
+                "vars",
+                "sets"
+            ],
+            "properties": {
+                "vars": {
+                    "type": "object",
+                    "description": "Short names for models. Keys must be alphanumeric, 1-8 characters. All sets and evict_costs must use these IDs.",
+                    "minProperties": 1,
+                    "additionalProperties": {
+                        "type": "string"
+                    },
+                    "propertyNames": {
+                        "pattern": "^[a-zA-Z0-9]{1,8}$"
+                    }
+                },
+                "evict_costs": {
+                    "type": "object",
+                    "description": "Relative cost of evicting a running model. Models not listed default to 1. Values must be positive integers.",
+                    "additionalProperties": {
+                        "type": "integer",
+                        "minimum": 1
+                    }
+                },
+                "sets": {
+                    "type": "object",
+                    "description": "Named sets of concurrent model combinations. Values are DSL strings using & (AND), | (OR), () (grouping), and +ref (inline another set). Definition order is used for tie-breaking.",
+                    "minProperties": 1,
+                    "additionalProperties": {
+                        "type": "string"
+                    }
+                }
+            },
+            "additionalProperties": false
+        },
         "hooks": {
             "type": "object",
             "properties": {
@@ -456,5 +494,27 @@
             "default": {},
             "description": "A dictionary of remote peers and models they provide. Peers can be another llama-swap or any server that provides the /v1/ generative API endpoints supported by llama-swap."
         }
-    }
+    },
+    "allOf": [
+        {
+            "if": {
+                "required": ["groups"]
+            },
+            "then": {
+                "not": {
+                    "required": ["matrix"]
+                }
+            }
+        },
+        {
+            "if": {
+                "required": ["matrix"]
+            },
+            "then": {
+                "not": {
+                    "required": ["groups"]
+                }
+            }
+        }
+    ]
 }