mohdel 0.119.0 → 0.121.0

package/README.md

@@ -101,6 +101,9 @@ mo ask anthropic/claude-sonnet-4-6 --stream "write a haiku about recursion"
 # With thinking effort
 mo ask anthropic/claude-opus-4-6 --effort high "prove P != NP"
 
+# On a faster service lane, when the model sells one
+mo ask openai/gpt-5.6-luna@fast "triage this alert"
+
 # Speech → text from an audio file
 mo transcribe groq/whisper-large-v3-turbo meeting.mp3
 mo transcribe mistral/voxtral-mini-transcribe interview.wav --language fr
@@ -315,6 +318,8 @@ What each provider supports through mohdel's unified interface:
 
 Adapter capability ≠ model capability — whether a given model accepts images, tools, or thinking effort depends on the model spec in `curated.json`. The adapter passes through what the envelope supplies; the provider rejects unsupported combos.
 
+**Service speeds** are the exception to that pass-through rule. Where a provider sells the same weights at several speeds (OpenAI's `service_tier`, and equivalents elsewhere), the lanes a model sells are declared in its `curated.json` entry under `speeds`, with their own prices and rate limits. Select one with `speed` or the `@lane` id suffix. There is no default lane and no fallback: an undeclared lane fails the call before it is sent, because a model that silently ignores an unsupported lane would otherwise be billed at the lane's rates for standard service. See [docs/CATALOG.md](docs/CATALOG.md#service-speeds).
+
 ## Local Development
 
 ```bash

package/config/curated.schema.json

@@ -2,7 +2,7 @@
   "$schema": "https://json-schema.org/draft/2020-12/schema",
   "$id": "https://github.com/clbrge/mohdel/blob/main/config/curated.schema.json",
   "title": "Mohdel curated.json",
-  "description": "Schema for ~/.config/mohdel/curated.json — see docs/CATALOG.md for the full reference.",
+  "description": "Schema for ~/.config/mohdel/curated.json \u2014 see docs/CATALOG.md for the full reference.",
   "type": "object",
   "propertyNames": {
     "pattern": "^([a-z0-9_-]+/.+|_[a-zA-Z0-9_-]+)$",
@@ -10,16 +10,25 @@
   },
   "additionalProperties": {
     "oneOf": [
-      { "$ref": "#/$defs/deprecatedStub" },
-      { "$ref": "#/$defs/modelEntry" },
-      { "type": "string", "description": "Inline comment value for underscore-prefixed keys." }
+      {
+        "$ref": "#/$defs/deprecatedStub"
+      },
+      {
+        "$ref": "#/$defs/modelEntry"
+      },
+      {
+        "type": "string",
+        "description": "Inline comment value for underscore-prefixed keys."
+      }
     ]
   },
   "$defs": {
     "deprecatedStub": {
       "type": "object",
       "description": "Redirect from a retired model id to its replacement.",
-      "required": ["deprecated"],
+      "required": [
+        "deprecated"
+      ],
       "additionalProperties": true,
       "properties": {
         "deprecated": {
@@ -31,7 +40,11 @@
     "modelEntry": {
       "type": "object",
       "description": "A real model entry. 'model', 'creator', and 'inputFormat' are required.",
-      "required": ["model", "creator", "inputFormat"],
+      "required": [
+        "model",
+        "creator",
+        "inputFormat"
+      ],
       "additionalProperties": true,
       "properties": {
         "model": {
@@ -45,7 +58,15 @@
         "inputFormat": {
           "type": "array",
           "description": "Accepted input modalities. Defaults to ['text'].",
-          "items": { "type": "string", "enum": ["text", "image", "video", "audio"] },
+          "items": {
+            "type": "string",
+            "enum": [
+              "text",
+              "image",
+              "video",
+              "audio"
+            ]
+          },
           "minItems": 1,
           "uniqueItems": true
         },
@@ -53,104 +74,454 @@
           "type": "string",
           "description": "Routing provider. Defaults to the provider segment of the catalog key."
         },
-        "sdk": { "type": "string", "description": "SDK adapter to use (some providers require this)." },
+        "sdk": {
+          "type": "string",
+          "description": "SDK adapter to use (some providers require this)."
+        },
         "type": {
           "type": "string",
-          "enum": ["model", "image", "transcription"],
+          "enum": [
+            "model",
+            "image",
+            "transcription"
+          ],
           "default": "model",
           "description": "'model' for chat/completion, 'image' for image generation, 'transcription' for speech-to-text."
         },
-        "label": { "type": "string", "description": "Human-readable name shown in UIs." },
-        "description": { "type": "string" },
-        "version": { "type": "string" },
-        "createdAt": { "type": "string", "format": "date-time" },
-        "created": { "type": "number", "description": "Unix timestamp (seconds)." },
-
+        "label": {
+          "type": "string",
+          "description": "Human-readable name shown in UIs."
+        },
+        "description": {
+          "type": "string"
+        },
+        "version": {
+          "type": "string"
+        },
+        "createdAt": {
+          "type": "string",
+          "format": "date-time"
+        },
+        "created": {
+          "type": "number",
+          "description": "Unix timestamp (seconds)."
+        },
         "inputPrice": {
           "oneOf": [
-            { "type": "number", "minimum": 0 },
-            { "type": "object", "required": ["default"], "additionalProperties": { "type": "number" }, "properties": { "default": { "type": "number" } } }
+            {
+              "type": "number",
+              "minimum": 0
+            },
+            {
+              "type": "object",
+              "required": [
+                "default"
+              ],
+              "additionalProperties": {
+                "type": "number"
+              },
+              "properties": {
+                "default": {
+                  "type": "number"
+                }
+              }
+            }
           ],
-          "description": "USD per 1M input tokens. Object form is for tiered pricing — must include a 'default' key."
+          "description": "USD per 1M input tokens. Object form is for tiered pricing \u2014 must include a 'default' key."
         },
         "outputPrice": {
           "oneOf": [
-            { "type": "number", "minimum": 0 },
-            { "type": "object", "required": ["default"], "additionalProperties": { "type": "number" }, "properties": { "default": { "type": "number" } } }
+            {
+              "type": "number",
+              "minimum": 0
+            },
+            {
+              "type": "object",
+              "required": [
+                "default"
+              ],
+              "additionalProperties": {
+                "type": "number"
+              },
+              "properties": {
+                "default": {
+                  "type": "number"
+                }
+              }
+            }
           ],
           "description": "USD per 1M output tokens."
         },
         "thinkingPrice": {
           "oneOf": [
-            { "type": "number", "minimum": 0 },
-            { "type": "object", "required": ["default"], "additionalProperties": { "type": "number" }, "properties": { "default": { "type": "number" } } }
+            {
+              "type": "number",
+              "minimum": 0
+            },
+            {
+              "type": "object",
+              "required": [
+                "default"
+              ],
+              "additionalProperties": {
+                "type": "number"
+              },
+              "properties": {
+                "default": {
+                  "type": "number"
+                }
+              }
+            }
           ],
           "description": "USD per 1M thinking/reasoning tokens (when the provider bills these separately)."
         },
-        "cacheWritePrice": { "type": "number", "minimum": 0, "description": "USD per 1M tokens written to provider-side prompt cache." },
-        "cacheReadPrice": { "type": "number", "minimum": 0, "description": "USD per 1M tokens served from provider-side prompt cache." },
-
-        "contextTokenLimit": { "type": "integer", "minimum": 1, "description": "Maximum total tokens (input + output)." },
-        "outputTokenLimit": { "type": "integer", "minimum": 1, "description": "Maximum output tokens per call." },
-        "thinkingTokenLimit": { "type": "integer", "minimum": 1, "description": "Maximum thinking tokens per call (when separate from output)." },
-        "tokenizerHeadroom": { "type": "number", "exclusiveMinimum": 0, "description": "Multiplier applied to local token estimates to account for tokenizer drift." },
-
+        "cacheWritePrice": {
+          "oneOf": [
+            {
+              "type": "number",
+              "minimum": 0
+            },
+            {
+              "type": "object",
+              "required": [
+                "default"
+              ],
+              "additionalProperties": {
+                "type": "number"
+              },
+              "properties": {
+                "default": {
+                  "type": "number"
+                }
+              }
+            }
+          ],
+          "description": "USD per 1M tokens written to provider-side prompt cache. Object form is tiered on input tokens."
+        },
+        "cacheWrite1hPrice": {
+          "oneOf": [
+            {
+              "type": "number",
+              "minimum": 0
+            },
+            {
+              "type": "object",
+              "required": [
+                "default"
+              ],
+              "additionalProperties": {
+                "type": "number"
+              },
+              "properties": {
+                "default": {
+                  "type": "number"
+                }
+              }
+            }
+          ],
+          "description": "USD per 1M tokens written with a 1h TTL, when the provider prices that above the default write rate. Falls back to cacheWritePrice."
+        },
+        "cacheReadPrice": {
+          "oneOf": [
+            {
+              "type": "number",
+              "minimum": 0
+            },
+            {
+              "type": "object",
+              "required": [
+                "default"
+              ],
+              "additionalProperties": {
+                "type": "number"
+              },
+              "properties": {
+                "default": {
+                  "type": "number"
+                }
+              }
+            }
+          ],
+          "description": "USD per 1M tokens served from provider-side prompt cache. Object form is tiered on input tokens."
+        },
+        "contextTokenLimit": {
+          "type": "integer",
+          "minimum": 1,
+          "description": "Maximum total tokens (input + output)."
+        },
+        "outputTokenLimit": {
+          "type": "integer",
+          "minimum": 1,
+          "description": "Maximum output tokens per call."
+        },
+        "thinkingTokenLimit": {
+          "type": "integer",
+          "minimum": 1,
+          "description": "Maximum thinking tokens per call (when separate from output)."
+        },
+        "tokenizerHeadroom": {
+          "type": "number",
+          "exclusiveMinimum": 0,
+          "description": "Multiplier applied to local token estimates to account for tokenizer drift."
+        },
         "thinkingEffortLevels": {
           "oneOf": [
-            { "type": "null" },
+            {
+              "type": "null"
+            },
             {
               "type": "object",
-              "description": "Map effort name → provider-native budget. Standard names: low/medium/high/xhigh/max/none.",
-              "additionalProperties": { "type": "number", "minimum": 0 }
+              "description": "Map effort name \u2192 provider-native budget. Standard names: low/medium/high/xhigh/max/none.",
+              "additionalProperties": {
+                "type": "number",
+                "minimum": 0
+              }
             }
           ]
         },
-        "defaultThinkingEffort": { "type": "string", "description": "Effort level used when the envelope omits 'outputEffort'." },
-
+        "defaultThinkingEffort": {
+          "type": "string",
+          "description": "Effort level used when the envelope omits 'outputEffort'."
+        },
+        "speeds": {
+          "type": "object",
+          "description": "Service speed lanes this model sells, keyed by lane name. A lane is a provider request parameter buying a different speed/price point for the same weights. There is no default lane: omitting 'speed' on the envelope sends no parameter. Only lanes declared here may be requested, and only names the provider's adapter accepts.",
+          "additionalProperties": {
+            "type": "object",
+            "additionalProperties": false,
+            "description": "Lane overlay: the price and rate-limit fields that differ from the base entry. Unnamed fields fall through. Lane names come from the provider's own vocabulary (OpenAI: fast, priority, flex, scale) \u2014 the adapter decides how a name reaches the wire.",
+            "properties": {
+              "inputPrice": {
+                "oneOf": [
+                  {
+                    "type": "number",
+                    "minimum": 0
+                  },
+                  {
+                    "type": "object",
+                    "required": [
+                      "default"
+                    ],
+                    "additionalProperties": {
+                      "type": "number"
+                    },
+                    "properties": {
+                      "default": {
+                        "type": "number"
+                      }
+                    }
+                  }
+                ]
+              },
+              "outputPrice": {
+                "oneOf": [
+                  {
+                    "type": "number",
+                    "minimum": 0
+                  },
+                  {
+                    "type": "object",
+                    "required": [
+                      "default"
+                    ],
+                    "additionalProperties": {
+                      "type": "number"
+                    },
+                    "properties": {
+                      "default": {
+                        "type": "number"
+                      }
+                    }
+                  }
+                ]
+              },
+              "thinkingPrice": {
+                "oneOf": [
+                  {
+                    "type": "number",
+                    "minimum": 0
+                  },
+                  {
+                    "type": "object",
+                    "required": [
+                      "default"
+                    ],
+                    "additionalProperties": {
+                      "type": "number"
+                    },
+                    "properties": {
+                      "default": {
+                        "type": "number"
+                      }
+                    }
+                  }
+                ]
+              },
+              "cacheWritePrice": {
+                "oneOf": [
+                  {
+                    "type": "number",
+                    "minimum": 0
+                  },
+                  {
+                    "type": "object",
+                    "required": [
+                      "default"
+                    ],
+                    "additionalProperties": {
+                      "type": "number"
+                    },
+                    "properties": {
+                      "default": {
+                        "type": "number"
+                      }
+                    }
+                  }
+                ]
+              },
+              "cacheWrite1hPrice": {
+                "oneOf": [
+                  {
+                    "type": "number",
+                    "minimum": 0
+                  },
+                  {
+                    "type": "object",
+                    "required": [
+                      "default"
+                    ],
+                    "additionalProperties": {
+                      "type": "number"
+                    },
+                    "properties": {
+                      "default": {
+                        "type": "number"
+                      }
+                    }
+                  }
+                ]
+              },
+              "cacheReadPrice": {
+                "oneOf": [
+                  {
+                    "type": "number",
+                    "minimum": 0
+                  },
+                  {
+                    "type": "object",
+                    "required": [
+                      "default"
+                    ],
+                    "additionalProperties": {
+                      "type": "number"
+                    },
+                    "properties": {
+                      "default": {
+                        "type": "number"
+                      }
+                    }
+                  }
+                ]
+              },
+              "rpmLimit": {
+                "type": "integer",
+                "minimum": 1
+              },
+              "tpmLimit": {
+                "type": "integer",
+                "minimum": 1
+              }
+            }
+          }
+        },
         "tags": {
           "type": "array",
-          "items": { "type": "string", "pattern": "^[a-zA-Z][a-zA-Z0-9._-]{0,31}$" },
+          "items": {
+            "type": "string",
+            "pattern": "^[a-zA-Z][a-zA-Z0-9._-]{0,31}$"
+          },
           "uniqueItems": true,
           "description": "Free-form classification tags (used by 'mo bench --tag', 'mo rank', and caller-side selection)."
         },
         "aliases": {
           "type": "array",
-          "items": { "type": "string" },
+          "items": {
+            "type": "string"
+          },
           "description": "Alternative ids that should resolve to this entry."
         },
         "replaces": {
           "type": "array",
-          "items": { "type": "string" },
+          "items": {
+            "type": "string"
+          },
           "description": "Older model ids this one supersedes."
         },
         "leaderboard": {
           "type": "array",
-          "items": { "type": "number" },
+          "items": {
+            "type": "number"
+          },
           "minItems": 3,
           "maxItems": 3,
-          "description": "[intelligence, speed, latency] triple — drives 'mo rank'."
-        },
-        "leaderboardNote": { "type": "string" },
-
-        "supportsTools": { "type": "boolean", "description": "Set false to mark a model as tool-less." },
-
-        "imagePrice": { "type": "number", "minimum": 0, "description": "USD per generated image (image-type entries)." },
-        "imageEndpoint": { "type": "string", "description": "Provider-side image endpoint name." },
-        "imageDefaultSize": { "type": "string", "description": "Default size when envelope omits one (e.g. '1024x1024')." },
-        "transcriptionPrice": { "type": "number", "minimum": 0, "description": "USD per audio minute (transcription-type entries). Token-billed transcription models (OpenAI gpt-4o-*-transcribe) use inputPrice/outputPrice instead." },
-
-        "rpmLimit": { "type": "integer", "minimum": 1, "description": "Requests per minute. Overrides provider default." },
-        "tpmLimit": { "type": "integer", "minimum": 1, "description": "Tokens per minute. Overrides provider default." },
+          "description": "[intelligence, speed, latency] triple \u2014 drives 'mo rank'."
+        },
+        "leaderboardNote": {
+          "type": "string"
+        },
+        "supportsTools": {
+          "type": "boolean",
+          "description": "Set false to mark a model as tool-less."
+        },
+        "imagePrice": {
+          "type": "number",
+          "minimum": 0,
+          "description": "USD per generated image (image-type entries)."
+        },
+        "imageEndpoint": {
+          "type": "string",
+          "description": "Provider-side image endpoint name."
+        },
+        "imageDefaultSize": {
+          "type": "string",
+          "description": "Default size when envelope omits one (e.g. '1024x1024')."
+        },
+        "transcriptionPrice": {
+          "type": "number",
+          "minimum": 0,
+          "description": "USD per audio minute (transcription-type entries). Token-billed transcription models (OpenAI gpt-4o-*-transcribe) use inputPrice/outputPrice instead."
+        },
+        "rpmLimit": {
+          "type": "integer",
+          "minimum": 1,
+          "description": "Requests per minute. Overrides provider default."
+        },
+        "tpmLimit": {
+          "type": "integer",
+          "minimum": 1,
+          "description": "Tokens per minute. Overrides provider default."
+        },
         "rateLimitScope": {
           "type": "string",
-          "enum": ["model", "provider"],
+          "enum": [
+            "model",
+            "provider"
+          ],
           "description": "'model' = private budget. 'provider' = shared with provider-level pool."
         },
-
-        "deprecated": { "type": "string", "description": "If present, this entry is treated as a stub (use 'deprecatedStub' shape)." },
-        "suspended": { "type": "string", "description": "Reason this model is temporarily disabled." },
-
-        "displayName": { "type": "string", "deprecated": true, "description": "Deprecated — use 'label'." }
+        "deprecated": {
+          "type": "string",
+          "description": "If present, this entry is treated as a stub (use 'deprecatedStub' shape)."
+        },
+        "suspended": {
+          "type": "string",
+          "description": "Reason this model is temporarily disabled."
+        },
+        "displayName": {
+          "type": "string",
+          "deprecated": true,
+          "description": "Deprecated \u2014 use 'label'."
+        }
       }
     }
   }

package/js/core/envelope.js

@@ -43,6 +43,13 @@
  *   Thinking effort level. Valid keys are per-model — validated at
  *   runtime against the curated entry's `thinkingEffortLevels`.
  *   Default is the model's `defaultThinkingEffort`.
+ * @property {string} [speed]
+ *   Service speed lane. Valid keys are per-model — validated at
+ *   runtime against the curated entry's `speeds`. There is no
+ *   default and no fallback: omitting the field sends no speed
+ *   parameter, while naming a lane the entry does not declare
+ *   (`SESSION_INVALID_SPEED`) or the provider's adapter cannot emit
+ *   (`SESSION_SPEED_NOT_IMPLEMENTED`) fails the call before dispatch.
  *
  * @property {MediaRef[]} [images]
  * @property {MediaRef[]} [videos]
@@ -146,6 +153,7 @@ export const ENVELOPE_FIELDS = Object.freeze([
   'outputType',
   'outputStyle',
   'outputEffort',
+  'speed',
   'images',
   'videos',
   'cache',