@oh-my-pi/pi-catalog 18.4.4 → 18.4.5

package/src/compat/rules/auth/factory-droid.kdl

@@ -0,0 +1,28 @@
+auth "factory-droid" {
+	name "Factory Droid"
+	org-scoped-identity #true
+	// WorkOS public client: the access token authorizes the Factory LLM proxy.
+	login "device-code" {
+		client-id "client_01HNM792M5G5G1A2THWPXKFMXB"
+		device url="https://api.workos.com/user_management/authorize/device" timeout-ms=15000 {
+			headers { Accept "application/json" }
+		}
+		token url="https://api.workos.com/user_management/authenticate" timeout-ms=15000 {
+			headers { Accept "application/json" }
+		}
+		credential {
+			expires "jwt" skew-ms=0 fallback-ms=86400000
+			email "user.email" claim="email"
+			account-id "user.id" claim="sub"
+			// WorkOS organization_id is internal; only this claim can be used as X-Factory-Org-Id.
+			org-id claim="external_org_id"
+		}
+		after-exchange hook="factory-droid-region"
+	}
+	refresh {
+		token url="https://api.workos.com/user_management/authenticate" timeout-ms=15000 {
+			headers { Accept "application/json" }
+		}
+		after-refresh hook="factory-droid-region"
+	}
+}

package/src/compat/rules/auth/helmcode.kdl

@@ -0,0 +1,9 @@
+auth "helmcode" {
+	name "Helmcode"
+	login "api-key" {
+		auth-url "https://cloud.helmcode.com"
+		instructions "Copy your API key from the Helmcode dashboard"
+		prompt "Paste your Helmcode API key" placeholder="sk-..."
+		validate "models-endpoint" label="Helmcode" url="https://api.helmcode.com/v1/models"
+	}
+}

package/src/compat/rules/classes/anthropic.kdl

@@ -108,7 +108,6 @@ class "anthropic" {
 				supports-mid-conversation-tool-changes #true
 				supports-turn-scoped-system #true
 				supports-per-message-effort #true
-				supports-thinking-binding-controls #true
 			}
 		}
 		family "opus" {
@@ -122,6 +121,15 @@ class "anthropic" {
 			}
 		}
 	}
+	// Vertex rejects `thinking.block_binding` on Sonnet 5.5 with 400
+	// `thinking.adaptive.block_binding: Extra inputs are not permitted`.
+	on "anthropic" "cloudflare-ai-gateway" {
+		family "sonnet" {
+			revision ">=5.5" {
+				supports-thinking-binding-controls #true
+			}
+		}
+	}
 	on "aimlapi" "gitlab-duo" "kilo" "nanogpt" "venice" {
 		thinking-efforts "minimal" "low" "medium" "high" "xhigh"
 	}

package/src/compat/rules/providers/cursor.kdl

@@ -8,6 +8,11 @@ provider "cursor" {
 	}
 
 	thinking-mode "effort"
+	// Cursor's default route selects a differently priced backing model per request.
+	models "default" {
+		pricing-status "variable"
+	}
+
 	class "anthropic" {
 		family "fable" {
 			requires-cursor-tool-schema-projection #true
@@ -211,9 +216,10 @@ provider "cursor" {
 		}
 	}
 	// Claude Opus 5 Fast: the docs name the fast wire ids but publish no
-	// fast multiplier, so fast bills at the base Opus 5 card.
+	// fast rate. Discovery applies AvailableModels' declared fast multiplier
+	// (2x); the base card only seeds rows discovery left unpriced.
 	models "claude-opus-5-high-fast" "claude-opus-5-low-fast" "claude-opus-5-medium-fast" "claude-opus-5-thinking-max-fast" "claude-opus-5-thinking-xhigh-fast" {
-		cost-patch {
+		cost-fallback {
 			input 5.0
 			output 25.0
 			cache-read 0.5
@@ -231,9 +237,10 @@ provider "cursor" {
 		}
 	}
 	// Claude Opus 5.5 Fast: the docs name the fast wire id but publish no
-	// fast multiplier, so fast bills at the base Opus 5.5 card.
+	// fast rate. Discovery prices it from AvailableModels' declared fast
+	// multiplier; the base card only seeds rows discovery left unpriced.
 	models "claude-opus-5-5-fast" {
-		cost-patch {
+		cost-fallback {
 			input 4.0
 			output 20.0
 			cache-read 0.2
@@ -267,8 +274,9 @@ provider "cursor" {
 			cache-write 0
 		}
 	}
-	// Grok 4.5: $2/$6, cache read $0.50, no write fee.
-	models "cursor-grok-4.5" {
+	// Grok 4.5: $2/$6, cache read $0.50, no write fee. Legacy id plus the
+	// per-effort wire slugs AvailableModels serves.
+	models "cursor-grok-4.5" "cursor-grok-4.5-low" "cursor-grok-4.5-medium" "cursor-grok-4.5-high" {
 		cost-patch {
 			input 2.0
 			output 6.0
@@ -277,7 +285,7 @@ provider "cursor" {
 		}
 	}
 	// Grok 4.5 Fast: $4/$18, cache read $1.00. Output is 3x base per docs.
-	models "cursor-grok-4.5-fast" {
+	models "cursor-grok-4.5-fast" "cursor-grok-4.5-low-fast" "cursor-grok-4.5-medium-fast" "cursor-grok-4.5-high-fast" {
 		cost-patch {
 			input 4.0
 			output 18.0
@@ -285,8 +293,9 @@ provider "cursor" {
 			cache-write 0
 		}
 	}
-	// Grok 4.6: $2/$6, cache read $0.50, no write fee.
-	models "cursor-grok-4.6" {
+	// Grok 4.6: $2/$6, cache read $0.50, no write fee. Legacy id plus the
+	// per-effort wire slugs AvailableModels serves.
+	models "cursor-grok-4.6" "cursor-grok-4.6-low" "cursor-grok-4.6-medium" "cursor-grok-4.6-high" "cursor-grok-4.6-xhigh" {
 		cost-patch {
 			input 2.0
 			output 6.0
@@ -295,7 +304,8 @@ provider "cursor" {
 		}
 	}
 	// Grok 4.6 Fast: $4/$12, cache read $1.00.
-	models "cursor-grok-4.6-fast" {
+	models "cursor-grok-4.6-fast" "cursor-grok-4.6-low-fast" "cursor-grok-4.6-medium-fast" "cursor-grok-4.6-high-fast" \
+		"cursor-grok-4.6-xhigh-fast" {
 		cost-patch {
 			input 4.0
 			output 12.0
@@ -448,10 +458,10 @@ provider "cursor" {
 			cache-write 0
 		}
 	}
-	// GPT-5.2 Fast: the docs publish no fast multiplier, so fast bills at
-	// the base GPT-5.2 card.
+	// GPT-5.2 Fast: the docs publish no fast rate. Discovery applies the
+	// declared fast multiplier; the base card only seeds unpriced rows.
 	models "gpt-5.2-fast" "gpt-5.2-high-fast" "gpt-5.2-low-fast" "gpt-5.2-xhigh-fast" {
-		cost-patch {
+		cost-fallback {
 			input 1.75
 			output 14.0
 			cache-read 0.175
@@ -486,9 +496,10 @@ provider "cursor" {
 			cache-write 0
 		}
 	}
-	// GPT-5.3 Codex Fast: no fast multiplier published; base card applies.
+	// GPT-5.3 Codex Fast: no fast rate published; discovery applies the
+	// declared multiplier, and the base card only seeds unpriced rows.
 	models "gpt-5.3-codex-fast" "gpt-5.3-codex-high-fast" "gpt-5.3-codex-low-fast" "gpt-5.3-codex-xhigh-fast" {
-		cost-patch {
+		cost-fallback {
 			input 1.75
 			output 14.0
 			cache-read 0.175
@@ -543,9 +554,10 @@ provider "cursor" {
 			cache-write 0
 		}
 	}
-	// GPT-5.5 Fast: higher fast rates are unpublished; base card applies.
+	// GPT-5.5 Fast: fast rates are unpublished; discovery applies the declared
+	// multiplier, and the base card only seeds unpriced rows.
 	models "gpt-5.5-fast" {
-		cost-patch {
+		cost-fallback {
 			input 5.0
 			output 30.0
 			cache-read 0.5