@oh-my-pi/pi-catalog 18.4.1 → 18.4.3

package/CHANGELOG.md

@@ -2,6 +2,39 @@
 
 ## [Unreleased]
 
+## [18.4.3] - 2026-09-28
+
+### Added
+
+- Added Command Code's typesafe/jev decision model for the judge role ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty))
+- Added Command Code's DeepSeek V4.1 Flash Fast model ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty))
+- Added Command Code's Claude Sonnet 5.5 model ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty))
+- Added `trust-forbidden=#true` for optional login `validate` checks, so a key check that answers 403 keeps the pasted key instead of rejecting it ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty))
+- `hosted-image #false` and `image-model #false` now remove a hosted image flag or image model that a class rule grants ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty))
+- Added support for Claude Sonnet 5.5 model with image and text inputs
+- Added new compatibility rules for Anthropic Sonnet family enabling mid‑conversation system features and disabling forced tool choice
+- Added the `web-search-model`, `hosted-image`, and `image-model` catalog axes (`Model.webSearchModel`, `hostedImage`, `imageModel`). `web-search` now comes from the model's lineage and API (GPT-5+ Responses, Claude 4+ Messages, Gemini 2+), so proxies and gateways that expose these models inherit it.
+
+### Changed
+
+- Renamed the Codex image model `openai-codex/gpt-image-1` to `openai-codex/gpt-image-2` to match what the Codex backend runs (`gpt-image-2-codex`); saved `openai-codex/gpt-image-1` selectors resolve to the new id.
+- Routed Command Code's 10 GPT models through the OpenAI Responses API ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty))
+- Command Code login now rejects a key that Command Code answers with 401; a 403 or an unreachable check keeps the pasted key, as the Command Code CLI does ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty))
+- Command Code GPT models no longer advertise hosted image generation or the `gpt-image-2` image model, which Command Code does not serve ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty))
+- Command Code Muse Spark models drop the minimal thinking level, and Muse Spark 1.3 adds max, matching the Command Code CLI ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty))
+- Changed Command Code prices to match the Command Code CLI: DeepSeek V4 Flash and V4 Flash Vision Exp drop from 0.22 / 0.66 to 0.15 / 0.6 per 1M tokens, Step 3.5 Flash input drops from 0.1 to 0.09, and LongCat 2.0 is no longer shown as free (0.3 / 1.2) ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty))
+
+### Fixed
+
+- Fixed missing thinking levels, image input, and prices for Command Code models ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty))
+
+## [18.4.2] - 2026-09-28
+
+### Changed
+
+- Improved model cache invalidation efficiency by implementing deep equality checks on cached rows when database version signals change
+- Optimized read-row cache by enabling granular cache-hit logic across concurrent connection handles
+
 ## [18.4.1] - 2026-09-28
 
 ### Added

package/dist/types/compat/types.d.ts

@@ -350,12 +350,15 @@ export type CompiledAuthValidation = {
     maxTokensField?: "max_tokens" | "max_completion_tokens";
     maxTokens?: number;
     optional?: boolean;
+    /** With `optional`: a 403 also trusts the key; only a 401 rejects it. */
+    trustForbidden?: boolean;
 } | {
     kind: "anthropic-messages";
     label?: string;
     baseUrl: string;
     model: string;
     optional?: boolean;
+    trustForbidden?: boolean;
 } | {
     kind: "models-endpoint";
     label?: string;
@@ -365,6 +368,7 @@ export type CompiledAuthValidation = {
     /** Hook returning extra request headers (may throw a configuration error). */
     headersHook?: string;
     optional?: boolean;
+    trustForbidden?: boolean;
 };
 /** Paste-an-API-key login: optional browser hint, prompt, optional validation. */
 export interface CompiledApiKeyLogin {

package/dist/types/provider-models/openai-compat.d.ts

@@ -648,7 +648,8 @@ export declare function modelsDevCatalogFallback(providerId: string, fetchImpl?:
  * `baseUrl` overrides the Provider API base path for testing; it is
  * normalized to the shared `/provider` root (a trailing `/v1` is stripped)
  * so Claude ids route to the Anthropic-compatible Messages endpoint at the
- * root while every other id uses chat completions under `/v1`.
+ * root, the ten GPT ids listed in the `api-routes` table to the Responses
+ * endpoint under `/v1`, and every other id to chat completions under `/v1`.
  */
 export interface CommandCodeModelManagerConfig {
     apiKey?: string;
@@ -659,12 +660,14 @@ export interface CommandCodeModelManagerConfig {
  * Builds the Command Code model manager: a mixed-protocol OpenAI-compatible
  * discovery client. The public `/v1/models` catalog is fetched once per
  * options instance; `mapModel` pins each row's transport from the
- * `api-routes` table (Claude ids to `anthropic-messages`, everything else to
- * `openai-completions`) and seeds neutral capability defaults. Reviewed
- * Command Code policy (effort ladders, pricing, limits, modalities) is
- * applied later by `buildModel` from `providers/commandcode.kdl` — the
- * mapper never inherits another provider's reasoning, rates, image support,
- * or context window.
+ * `api-routes` table (Claude ids to `anthropic-messages`, the listed GPT ids
+ * to `openai-responses`, everything else to `openai-completions`) and seeds
+ * neutral capability defaults. Reviewed Command Code policy (effort ladders,
+ * pricing, limits, modalities) is applied later by `buildModel` from
+ * `providers/commandcode.kdl` — the mapper never inherits another provider's
+ * reasoning, rates, image support, or context window. A successful fetch also
+ * appends the KDL `seed` rows (typesafe/jev), rebased onto the configured
+ * base, because `dynamicModelsAuthoritative` would prune `staticModels`.
  */
 export declare function commandCodeModelManagerOptions(config?: CommandCodeModelManagerConfig): ModelManagerOptions<Api>;
 /**

package/dist/types/types.d.ts

@@ -986,6 +986,12 @@ export interface Model<TApi extends Api = Api> {
     kind?: ModelKind;
     /** Grounding transport supported by this chat model. */
     webSearch?: WebSearchGrounding;
+    /** Cheaper same-provider model to run hosted web search in this model's place (model id or provider/id). */
+    webSearchModel?: string;
+    /** Whether this chat model can carry the Responses `image_generation` tool itself. */
+    hostedImage?: boolean;
+    /** Same-provider image model to generate images in this model's place (model id or provider/id). */
+    imageModel?: string;
     /**
      * Structured model identity resolved by the compat engine: vendor lineage
      * class, product family, and revision. Baked into models.json rows and

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@oh-my-pi/pi-catalog",
-	"version": "18.4.1",
+	"version": "18.4.3",
 	"description": "Model catalog for omp: bundled model database, provider discovery descriptors, model identity, classification, and equivalence",
 	"keywords": [
 		"ai",
@@ -93,12 +93,12 @@
 		"gen:proto": "bun scripts/generate-protocols.ts"
 	},
 	"dependencies": {
-		"@oh-my-pi/omptype": "18.4.1",
-		"@oh-my-pi/pi-utils": "18.4.1"
+		"@oh-my-pi/omptype": "18.4.3",
+		"@oh-my-pi/pi-utils": "18.4.3"
 	},
 	"devDependencies": {
 		"@bgotink/kdl": "0.4.0",
-		"@oh-my-pi/pi-ai": "18.4.1",
+		"@oh-my-pi/pi-ai": "18.4.3",
 		"@types/bun": "^1.3.14"
 	},
 	"engines": {

package/src/build.ts

@@ -87,6 +87,11 @@ function applyCatalogAssignments<TApi extends Api>(model: Model<TApi>, catalog:
 	) {
 		model.webSearch = webSearch;
 	}
+	if (typeof catalog.webSearchModel === "string") model.webSearchModel = catalog.webSearchModel;
+	if (catalog.hostedImage === true) model.hostedImage = true;
+	else if (catalog.hostedImage === false) delete model.hostedImage;
+	if (typeof catalog.imageModel === "string") model.imageModel = catalog.imageModel;
+	else if (catalog.imageModel === false) delete model.imageModel;
 	const serviceTierCost = objectPayload(catalog.serviceTierCost);
 	if (serviceTierCost !== undefined) {
 		const flex = numberField(serviceTierCost, "flex");

package/src/compat/axes.ts

@@ -343,6 +343,9 @@ export const AXES: Readonly<Record<string, AxisDef>> = {
 		shape: "scalar",
 		values: ["gemini", "anthropic", "codex", "xai", "openrouter", "openai"],
 	},
+	"web-search-model": { key: "webSearchModel", set: "catalog", shape: "scalar" },
+	"hosted-image": { key: "hostedImage", set: "catalog", shape: "scalar", values: [true, false] },
+	"image-model": { key: "imageModel", set: "catalog", shape: "scalar" },
 	"limits-patch": { key: "limitsPatch", set: "catalog", shape: "object" },
 	"long-context-cost": { key: "longContext", set: "catalog", shape: "object" },
 	"prompt-cache": { key: "promptCache", set: "catalog", shape: "object" },

package/src/compat/collapse.ts

@@ -1033,8 +1033,17 @@ function retargetCollapsedModelReferences<TSpec extends VariantSpecLike>(specs:
 			liveIdsByProvider,
 		);
 		const compactionModel = resolveCollapsedModelReference(spec.compactionModel, spec.provider, liveIdsByProvider);
-		if (contextPromotionTarget === spec.contextPromotionTarget && compactionModel === spec.compactionModel) continue;
-		specs[index] = { ...spec, contextPromotionTarget, compactionModel };
+		const webSearchModel = resolveCollapsedModelReference(spec.webSearchModel, spec.provider, liveIdsByProvider);
+		const imageModel = resolveCollapsedModelReference(spec.imageModel, spec.provider, liveIdsByProvider);
+		if (
+			contextPromotionTarget === spec.contextPromotionTarget &&
+			compactionModel === spec.compactionModel &&
+			webSearchModel === spec.webSearchModel &&
+			imageModel === spec.imageModel
+		) {
+			continue;
+		}
+		specs[index] = { ...spec, contextPromotionTarget, compactionModel, webSearchModel, imageModel };
 	}
 }
 

package/src/compat/rules/README.md

@@ -358,7 +358,7 @@ auth "anthropic" {
 
 Login kinds:
 
-- `login "api-key" { auth-url "…"; instructions "…"; prompt "…" placeholder="…"; empty-fallback "…"; normalize "strip-bearer"; validate … }` — `validate "chat-completions" base-url= model= tolerate-model-denied= max-tokens-field= max-tokens=`, `validate "anthropic-messages" base-url= model=`, or `validate "models-endpoint" url= base-url-env= headers-hook=`; all accept `label=` (error-message label, defaults to `name`) and `optional=#true` (only auth failures reject).
+- `login "api-key" { auth-url "…"; instructions "…"; prompt "…" placeholder="…"; empty-fallback "…"; normalize "strip-bearer"; validate … }` — `validate "chat-completions" base-url= model= tolerate-model-denied= max-tokens-field= max-tokens=`, `validate "anthropic-messages" base-url= model=`, or `validate "models-endpoint" url= base-url-env= headers-hook=`; all accept `label=` (error-message label, defaults to `name`), `optional=#true` (only auth failures reject), and `trust-forbidden=#true` (requires `optional=#true`; a 403 no longer rejects, so only a 401 does).
 - `login "oauth-code" { … }` as above; `token`/`refresh` `params` values may use `{code}`, `{state}`, `{redirect_uri}`, `{code_verifier}`, `{client_id}`, `{client_secret}`, `{refresh_token}`, `{scope}`; the standard grant parameters are sent unless `standard=#false`.
 - `login "device-code" { client-id …; base-url "…"; scopes …; headers-hook "…"; device url="{base}/…" body="form" { params {…} headers {…} }; token url="…" url-hook="…"; response user-code= device-code= verification-uri= verification-uri-complete= interval= expires-in=; instructions "Enter code: {user_code}"; credential {…}; userinfo …; after-exchange hook=… }`.
 - `login "custom" hook="name"` — the whole flow is a named `@oh-my-pi/pi-ai` hook (`src/registry/hooks/custom.ts`).

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

@@ -1,7 +1,12 @@
-// No `validate` probe on purpose: GET /provider/v1/models is public (200
-// with no or bogus credentials, verified 2026-09-09), so a models-endpoint
-// probe could never reject a bad key. A chat-completions probe would bill
-// the key and 403 for Go-plan keys that are still valid CLI credentials.
+// `/provider/v1/models` is public: it answers 200 to a missing or bogus key.
+// Login therefore validates against `GET /alpha/whoami`, the identity route
+// that command-code@1.67.0 calls. That route answers 401 to a bad key
+// (verified 2026-09-29) and bills nothing. It is not in the Provider API
+// docs, so the probe is optional and only a 401 rejects the key, matching
+// `validateCommandApiKey` in command-code@1.67.0. A 403, a 404, a 5xx, or a
+// moved route trusts the pasted key.
+// The `models-endpoint` probe only checks for a 2xx answer, so this identity
+// route serves as its target.
 auth "commandcode" {
 	name "Command Code"
 	env "COMMAND_CODE_API_KEY" "COMMANDCODE_API_KEY"
@@ -9,5 +14,6 @@ auth "commandcode" {
 		auth-url "https://commandcode.ai/studio"
 		instructions "Create or copy a Provider API key from Command Code Studio"
 		prompt "Paste your Command Code API key" placeholder="user_..."
+		validate "models-endpoint" label="Command Code" url="https://api.commandcode.ai/alpha/whoami" optional=#true trust-forbidden=#true
 	}
 }

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

@@ -61,6 +61,17 @@ class "anthropic" {
 			supports-forced-tool-choice #false
 		}
 	}
+	// Sonnet 5.5 rejects forced tool selection like Opus 5.5 (400 `tool_choice:
+	// type "tool" and "any" are not supported for this model`); upper-bounded
+	// for the same reason as the Opus rule above.
+	// https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5
+	family "sonnet" {
+		revision ">=5.5 <6" {
+			supports-forced-tool-choice #false
+			// Signed thinking is bound to the exact preceding conversation.
+			thinking-prefix-binding #true
+		}
+	}
 	on "anthropic" "cloudflare-ai-gateway" "google-vertex" {
 		family "fable" {
 			revision ">=5" {
@@ -87,6 +98,15 @@ class "anthropic" {
 				supports-thinking-binding-controls #true
 			}
 		}
+		family "sonnet" {
+			revision ">=5.5" {
+				supports-mid-conversation-system #true
+				supports-mid-conversation-tool-changes #true
+				supports-turn-scoped-system #true
+				supports-per-message-effort #true
+				supports-thinking-binding-controls #true
+			}
+		}
 		family "opus" {
 			revision ">=4.8" {
 				supports-mid-conversation-system #true
@@ -369,3 +389,13 @@ class "anthropic" {
 		antigravity-usage-label "true"
 	}
 }
+
+// Claude 4+ ships the server-side `web_search` tool on any Messages-compatible host.
+class "anthropic" {
+	on-api "anthropic-messages" {
+		revision ">=4" {
+			web-search "anthropic"
+			web-search-model "claude-haiku-4-5"
+		}
+	}
+}

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

@@ -107,3 +107,14 @@ class "gemini" {
 
 	thinking-loop-guard "gemini"
 }
+
+// Google Search grounding is a Gemini 2+ lineage capability on every Gemini transport.
+class "gemini" {
+	on-api "google-generative-ai" "google-gemini-cli" {
+		revision ">=2" {
+			web-search "gemini"
+			web-search-model "gemini-2.5-flash"
+			image-model "gemini-3-pro-image"
+		}
+	}
+}

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

@@ -59,3 +59,25 @@ class "openai" {
 		}
 	}
 }
+
+// Hosted Responses tools are a GPT-5+ lineage capability on any
+// Responses-compatible host, so proxies exposing these ids inherit them. The
+// swap targets resolve on the same provider only; when a host lacks them the
+// session model runs the tool itself.
+class "openai" {
+	on-api "openai-responses" {
+		revision ">=5" {
+			web-search "openai"
+			web-search-model "gpt-5.6-luna"
+			hosted-image #true
+			image-model "gpt-image-2"
+		}
+	}
+	on-api "openai-codex-responses" {
+		revision ">=5" {
+			web-search-model "gpt-5.6-luna"
+			hosted-image #true
+			image-model "gpt-image-2"
+		}
+	}
+}

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

@@ -43,3 +43,9 @@ class "xai" {
 	}
 	thinking-loop-guard "xai"
 }
+
+// Same-provider swap targets for hosted search and image generation.
+class "xai" {
+	web-search-model "grok-4.5"
+	image-model "grok-imagine-image"
+}

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

@@ -28,6 +28,12 @@ provider "anthropic" {
 			cost input=3 output=15 cache-read=0.3 cache-write=3.75
 			limits context=1000000 max-tokens=128000
 		}
+		model "claude-sonnet-5-5" name="Claude Sonnet 5.5" {
+			reasoning #true
+			input "text" "image"
+			cost input=2 output=10 cache-read=0.2 cache-write=2.5
+			limits context=1000000 max-tokens=128000
+		}
 		model "claude-fable-5" name="Claude Fable 5" {
 			reasoning #true
 			input "text" "image"