@oh-my-pi/pi-catalog 18.4.4 → 18.4.6

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

@@ -5,8 +5,8 @@ login-order "openai-codex" "anthropic" "zai" "zai-coding-plan" "kimi-code" "open
 	"cursor" "devin" "google-antigravity" "google-gemini-cli" "openai-codex-device" "xai" "xai-oauth" \
 	"gitlab-duo" "gitlab-duo-agent" "alibaba-coding-plan" "alibaba-token-plan" "aiand" "abliteration" "zhipu-coding-plan" \
 	"umans" "qwen-portal" "sakana" "minimax-code" "minimax-code-cn" "xiaomi" "xiaomi-token-plan-sgp" \
-	"xiaomi-token-plan-ams" "xiaomi-token-plan-cn" "firepass" "cline-pass" "commandcode" "charm-hyper" "deepseek" "stepfun" "muse-code" "meta" "moonshot" \
-	"cerebras" "baseten" "fireworks" "together" "nvidia" "novita" "deepinfra" "huggingface" "perplexity" \
+	"xiaomi-token-plan-ams" "xiaomi-token-plan-cn" "firepass" "cline-pass" "factory-droid" "commandcode" "charm-hyper" "deepseek" "stepfun" "muse-code" "meta" "moonshot" \
+	"cerebras" "baseten" "helmcode" "fireworks" "together" "nvidia" "novita" "deepinfra" "huggingface" "perplexity" \
 	"qianfan" "venice" "siliconflow" "siliconflow-cn" "synthetic" "nanogpt" "wafer-serverless" "coreweave" \
 	"vercel-ai-gateway" "cloudflare-ai-gateway" "litellm" "kilo" "zenmux" "opencode-zen" "opencode-go" \
 	"yolo-auto" "tavily" "kagi" "exa" "parallel" "typesafe" "ollama" "ollama-cloud" "lm-studio" "llama.cpp" "vllm" \

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

@@ -49,8 +49,9 @@ class "anthropic" {
 	// Opus 5.5 rejects forced tool selection the way Fable/Mythos do — a
 	// `tool_choice` of `tool` or `any` fails the request with 400
 	// `invalid_request_error`: `tool_choice: type "tool" and "any" are not
-	// supported for this model`. The transport downgrades the selector to
-	// `auto` so the tool stays offered instead of the turn dying.
+	// supported for this model`. This holds on every route, including Bedrock
+	// Converse (`toolChoice: {any: {}}`). The transports downgrade the selector
+	// to `auto` so the tool stays offered instead of the turn dying.
 	//
 	// Upper-bounded on purpose: separator-collapsed ids parse their revision
 	// as a whole number (`claude-opus-45` is Opus 4.5, revision 45), so an
@@ -108,7 +109,6 @@ 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 +122,15 @@ 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"
 	}
@@ -273,27 +282,11 @@ class "anthropic" {
 			}
 		}
 	}
-	// AWS Bedrock Converse prompt-cache checkpoints, from the AWS model cards
-	// (docs.aws.amazon.com/bedrock/latest/userguide/model-cards.html); cache
-	// pricing is deliberately not used to infer these request shapes.
 	on "amazon-bedrock" {
+		// Model metadata applies to every Bedrock request adapter.
+		// Upstream metadata is stale for cache pricing and context.
 		family "opus" {
-			revision ">=4 <4.5" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 1024
-				prompt-cache-maximum-checkpoints 4
-			}
-			revision "=4.5" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 4096
-				prompt-cache-maximum-checkpoints 4
-				supports-long-prompt-cache-retention #true
-			}
 			revision "=4.6" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 4096
-				prompt-cache-maximum-checkpoints 4
-				// Upstream metadata is stale for cache pricing and context.
 				cost-patch {
 					cache-read 0.5
 					cache-write 6.25
@@ -303,74 +296,196 @@ class "anthropic" {
 					max-tokens 128000
 				}
 			}
-			revision ">=4.7 <5" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 4096
-				prompt-cache-maximum-checkpoints 4
-				supports-long-prompt-cache-retention #true
-			}
-			revision ">=5" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 512
-				prompt-cache-maximum-checkpoints 4
-				supports-long-prompt-cache-retention #true
-			}
 		}
-		family "sonnet" {
-			revision "=3.5" {
-				models "*3-5-sonnet-20241022-v2*" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 1024
-				prompt-cache-maximum-checkpoints 4
-			}
+		// AWS Bedrock Converse prompt-cache checkpoints, from the AWS model cards
+		// (docs.aws.amazon.com/bedrock/latest/userguide/model-cards.html); cache
+		// pricing is deliberately not used to infer these request shapes. Keep the
+		// provider and adapter conjunctive so this policy stays on Converse.
+		on-api "bedrock-converse-stream" {
+			family "opus" {
+				revision ">=4 <4.5" {
+					prompt-cache-mode "explicit"
+					prompt-cache-minimum-tokens 1024
+					prompt-cache-maximum-checkpoints 4
+					prompt-cache {
+						short 300
+					}
+				}
+				revision "=4.5" {
+					prompt-cache-mode "explicit"
+					prompt-cache-minimum-tokens 4096
+					prompt-cache-maximum-checkpoints 4
+					prompt-cache {
+						short 300
+						long 3600
+					}
+					supports-long-prompt-cache-retention #true
+				}
+				revision "=4.6" {
+					prompt-cache-mode "explicit"
+					prompt-cache-minimum-tokens 4096
+					prompt-cache-maximum-checkpoints 4
+					prompt-cache {
+						short 300
+					}
+				}
+				revision ">=4.7 <5" {
+					prompt-cache-mode "explicit"
+					prompt-cache-minimum-tokens 4096
+					prompt-cache-maximum-checkpoints 4
+					supports-long-prompt-cache-retention #true
+					prompt-cache {
+						short 300
+						long 3600
+					}
+				}
+				revision ">=5" {
+					prompt-cache-mode "explicit"
+					prompt-cache-minimum-tokens 512
+					prompt-cache-maximum-checkpoints 4
+					supports-long-prompt-cache-retention #true
+					prompt-cache {
+						short 300
+						long 3600
+					}
+				}
 			}
-			revision "=3.7" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 1024
-				prompt-cache-maximum-checkpoints 4
+			family "sonnet" {
+				revision "=3.5" {
+					models "*3-5-sonnet-20241022-v2*" {
+						prompt-cache-mode "explicit"
+						prompt-cache-minimum-tokens 1024
+						prompt-cache-maximum-checkpoints 4
+						prompt-cache {
+							short 300
+						}
+					}
+				}
+				revision "=3.7" {
+					prompt-cache-mode "explicit"
+					prompt-cache-minimum-tokens 1024
+					prompt-cache-maximum-checkpoints 4
+					prompt-cache {
+						short 300
+					}
+				}
+				revision ">=4 <4.5" {
+					prompt-cache-mode "explicit"
+					prompt-cache-minimum-tokens 1024
+					prompt-cache-maximum-checkpoints 4
+					prompt-cache {
+						short 300
+					}
+				}
+				revision "=4.5" {
+					prompt-cache-mode "explicit"
+					prompt-cache-minimum-tokens 4096
+					prompt-cache-maximum-checkpoints 4
+					supports-long-prompt-cache-retention #true
+					prompt-cache {
+						short 300
+						long 3600
+					}
+				}
+				revision "=4.6" {
+					prompt-cache-mode "explicit"
+					prompt-cache-minimum-tokens 1024
+					prompt-cache-maximum-checkpoints 4
+					prompt-cache {
+						short 300
+					}
+				}
+				revision ">=5" {
+					prompt-cache-mode "explicit"
+					prompt-cache-minimum-tokens 4096
+					prompt-cache-maximum-checkpoints 4
+					supports-long-prompt-cache-retention #true
+					prompt-cache {
+						short 300
+						long 3600
+					}
+				}
 			}
-			revision ">=4 <4.5" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 1024
-				prompt-cache-maximum-checkpoints 4
+			family "haiku" {
+				revision "=3.5" {
+					prompt-cache-mode "explicit"
+					prompt-cache-minimum-tokens 2048
+					prompt-cache-maximum-checkpoints 4
+					prompt-cache {
+						short 300
+					}
+				}
+				revision ">=4.5" {
+					prompt-cache-mode "explicit"
+					prompt-cache-minimum-tokens 4096
+					prompt-cache-maximum-checkpoints 4
+					supports-long-prompt-cache-retention #true
+					prompt-cache {
+						short 300
+						long 3600
+					}
+				}
 			}
-			revision "=4.5" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 4096
-				prompt-cache-maximum-checkpoints 4
-				supports-long-prompt-cache-retention #true
+			family "fable" {
+				revision ">=5" {
+					prompt-cache-mode "explicit"
+					prompt-cache-minimum-tokens 1024
+					prompt-cache-maximum-checkpoints 4
+					supports-long-prompt-cache-retention #true
+					prompt-cache {
+						short 300
+						long 3600
+					}
+				}
 			}
-			revision "=4.6" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 1024
-				prompt-cache-maximum-checkpoints 4
+		}
+	}
+	// Messages routes on Bedrock Runtime and Mantle use the Anthropic five-minute
+	// cache lifetime. Require both the AWS provider and Messages API: model IDs
+	// alone do not distinguish Bedrock from gateways or other API lanes.
+	on "amazon-bedrock" "bedrock-mantle" {
+		on-api "anthropic-messages" {
+			family "opus" {
+				revision ">=4.7" {
+					prompt-cache {
+						short 300
+					}
+				}
 			}
-			revision ">=5" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 4096
-				prompt-cache-maximum-checkpoints 4
-				supports-long-prompt-cache-retention #true
+			family "sonnet" {
+				revision ">=4.6" {
+					prompt-cache {
+						short 300
+					}
+				}
 			}
-		}
-		family "haiku" {
-			revision "=3.5" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 2048
-				prompt-cache-maximum-checkpoints 4
+			family "haiku" {
+				revision ">=4.5" {
+					prompt-cache {
+						short 300
+					}
+				}
 			}
-			revision ">=4.5" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 4096
-				prompt-cache-maximum-checkpoints 4
-				supports-long-prompt-cache-retention #true
+			family "fable" {
+				revision ">=5" {
+					prompt-cache {
+						short 300
+					}
+				}
 			}
-		}
-		family "fable" {
-			revision ">=5" {
-				prompt-cache-mode "explicit"
-				prompt-cache-minimum-tokens 1024
-				prompt-cache-maximum-checkpoints 4
-				supports-long-prompt-cache-retention #true
+			family "mythos" {
+				// The Mythos Preview id has no numeric revision to select.
+				models "*mythos-preview*" {
+					prompt-cache {
+						short 300
+					}
+				}
+
+				revision ">=5" {
+					prompt-cache {
+						short 300
+					}
+				}
 			}
 		}
 	}

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

@@ -54,6 +54,24 @@ provider "commandcode" {
 		supports-eager-tool-input-streaming #false
 		supports-long-cache-retention #false
 	}
+	// Endpoint contract for every id `api-routes provider="commandcode"` sends to
+	// Responses. Responses accepts `reasoning.effort: "none"` while chat
+	// completions rejects it (low|medium|high|xhigh|max only), so thinking-off
+	// disables reasoning instead of clamping to the lowest effort. Ids without
+	// an effort ladder stay inert through provider-level
+	// `supports-reasoning-effort #false`. The Responses endpoint also rejects an
+	// object `tool_choice` (verified 2026-09-29), so named choices degrade to
+	// `"required"`.
+	on-api "openai-responses" {
+		reasoning-disable-mode "none-effort"
+		supports-named-tool-choice #false
+	}
+	// First-party OpenAI grants `none` only to the 5.6 generation
+	// (`providers/openai.kdl`); the gateway may forward `reasoning.effort`
+	// unchanged, so the other GPT ids keep the first-party lowest-effort off.
+	models "gpt-5.3-codex" "gpt-5.4" "gpt-5.4-mini" "gpt-5.5" "gpt-6-astra" "gpt-6-luna" "gpt-6-sol" {
+		reasoning-disable-mode "lowest-effort"
+	}
 	models "typesafe/jev" {
 		kind "judge"
 	}
@@ -154,15 +172,13 @@ provider "commandcode" {
 			max-tokens 65536
 		}
 	}
-	// Command Code's Responses endpoint rejects an object `tool_choice` and returns
-	// no bytes from `image_generation` (verified 2026-09-29), so the openai
-	// class's hosted-image and image-model grants do not apply and named choices
-	// degrade to `"required"`. Hosted web search still works with a string `tool_choice`.
+	// Command Code's Responses endpoint returns no bytes from `image_generation`
+	// (verified 2026-09-29), so the openai class's hosted-image and image-model
+	// grants do not apply. Hosted web search still works with a string `tool_choice`.
 	models "gpt-5.3-codex" "gpt-5.4" "gpt-5.4-mini" "gpt-5.5" "gpt-5.6-luna" "gpt-5.6-sol" \
 		"gpt-5.6-terra" "gpt-6-astra" "gpt-6-luna" "gpt-6-sol" {
 		hosted-image #false
 		image-model #false
-		supports-named-tool-choice #false
 	}
 	// ---------------------------------------------------------------------------
 	// This table prices every model id that GET /provider/v1/models serves.

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