@oh-my-pi/pi-catalog 18.4.2 → 18.4.4

package/src/provider-models/openai-compat.ts

@@ -7296,7 +7296,8 @@ export function modelsDevCatalogFallback(
  * `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;
@@ -7315,12 +7316,14 @@ function normalizeCommandCodeBasePath(baseUrl: string | undefined): string {
  * 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 function commandCodeModelManagerOptions(config?: CommandCodeModelManagerConfig): ModelManagerOptions<Api> {
 	const basePath = normalizeCommandCodeBasePath(config?.baseUrl);
@@ -7332,8 +7335,8 @@ export function commandCodeModelManagerOptions(config?: CommandCodeModelManagerC
 			baseUrl: discoveryBaseUrl,
 		}),
 		dynamicModelsAuthoritative: true,
-		fetchDynamicModels: () => {
-			return fetchOpenAICompatibleModels<Api>({
+		fetchDynamicModels: async () => {
+			const discovered = await fetchOpenAICompatibleModels<Api>({
 				api: "openai-completions",
 				provider: "commandcode",
 				baseUrl: discoveryBaseUrl,
@@ -7342,8 +7345,9 @@ export function commandCodeModelManagerOptions(config?: CommandCodeModelManagerC
 				// inference. The helper only sends Authorization when set.
 				apiKey: config?.apiKey,
 				mapModel: (entry, defaults) => {
-					const route = apiRouteFor("commandcode", defaults.id);
-					const api = route?.api === "anthropic-messages" ? route.api : "openai-completions";
+					const route = apiRouteFor("commandcode", defaults.id)?.api;
+					const api =
+						route === "anthropic-messages" || route === "openai-responses" ? route : "openai-completions";
 					return {
 						...defaults,
 						name: toModelName(entry.name, defaults.name),
@@ -7373,6 +7377,10 @@ export function commandCodeModelManagerOptions(config?: CommandCodeModelManagerC
 				},
 				fetch: config?.fetch,
 			});
+			if (!discovered) return null;
+			const seeds = seedModels("commandcode").map(seed => ({ ...seed, baseUrl: basePath }));
+			const seedIds = new Set(seeds.map(seed => seed.id));
+			return [...discovered.filter(model => !seedIds.has(model.id)), ...seeds];
 		},
 	};
 }

package/src/types.ts

@@ -560,6 +560,15 @@ export interface AnthropicCompat {
 	 * `tools.<n>.custom.strict: Extra inputs are not permitted`.
 	 */
 	disableStrictTools?: boolean;
+	/**
+	 * The endpoint is Amazon Bedrock's Anthropic Messages API (`/anthropic` on
+	 * bedrock-runtime or bedrock-mantle). Requests drop tool `strict`, fit
+	 * `metadata.user_id` to Bedrock's request-metadata pattern, and may use
+	 * on-demand compaction. Detected from the model `baseUrl`; set it in
+	 * models.yml `compat` for a route the URL check cannot see (a proxy, an
+	 * `ANTHROPIC_BASE_URL` reroute) or to `false` to opt out.
+	 */
+	bedrockMessagesApi?: boolean;
 	/**
 	 * Map adaptive thinking (`thinking: { type: "adaptive" }`) to
 	 * `{ type: "enabled", budget_tokens }`. Vertex AI rejects the `adaptive`
@@ -587,6 +596,13 @@ export interface AnthropicCompat {
 	 * `input_transformations` under the thinking-binding-controls beta.
 	 */
 	supportsThinkingBindingControls?: boolean;
+	/**
+	 * Whether the model replaces `thinking: { type: "disabled" }` with
+	 * `thinking: { type: "between_tools" }` (Claude Sonnet 5.5). The disabled
+	 * form is rejected with a 400; `between_tools` skips up-front thinking and
+	 * only allows progress updates between tool calls.
+	 */
+	supportsBetweenToolsThinking?: boolean;
 	/**
 	 * Whether the model accepts a forced `tool_choice` (`{ type: "any" }` or
 	 * `{ type: "tool", name }`). Claude Fable/Mythos 5 reject forced tool use
@@ -960,9 +976,17 @@ export interface ResolvedOpenAIResponsesCompat extends ResolvedOpenAISharedCompa
 export type ResolvedOpenRouterCompat = ResolvedOpenAICompat & ResolvedOpenAIResponsesCompat;
 
 /** Fully-resolved anthropic-messages compat view (same contract as `ResolvedOpenAICompat`). */
-export type ResolvedAnthropicCompat = Required<Omit<AnthropicCompat, "streamIdleTimeoutMs" | "thinkingLoopGuard">> & {
+export type ResolvedAnthropicCompat = Required<
+	Omit<AnthropicCompat, "streamIdleTimeoutMs" | "thinkingLoopGuard" | "bedrockMessagesApi">
+> & {
 	/** Thinking-loop watchdog guard family applied to streamed reasoning. */
 	thinkingLoopGuard?: AnthropicCompat["thinkingLoopGuard"];
+	/**
+	 * Bedrock's Anthropic Messages API (see {@link AnthropicCompat.bedrockMessagesApi}).
+	 * `true` when detected or configured; otherwise unset, so rows baked before
+	 * this field keep matching.
+	 */
+	bedrockMessagesApi?: boolean;
 	/**
 	 * Stream-watchdog idle-timeout fallback in ms for slow reasoning hosts; 0 disables the idle watchdog.
 	 * Undefined defers to `PI_STREAM_IDLE_TIMEOUT_MS`, then the legacy
@@ -1201,6 +1225,12 @@ 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
@@ -1352,6 +1382,12 @@ export interface Model<TApi extends Api = Api> {
 	useResponsesLite?: boolean;
 	/** Codex Code Mode restriction: model expects tools routed through a programmatic exec surface (mirrors codex-rs `tool_mode`). */
 	toolMode?: "code_mode_only";
+	/**
+	 * Service-tier ids the provider advertises for this model (Codex discovery
+	 * `service_tiers[].id`, e.g. `priority`, `ultrafast`). Absent when the
+	 * provider publishes no per-model tier list.
+	 */
+	serviceTiers?: readonly string[];
 	/** Preferred model to switch to when context promotion is triggered (model id or provider/id). */
 	contextPromotionTarget?: string;
 	/** Preferred model to use only for compaction (model id or provider/id); the active session model is unchanged. */

package/src/wire/codex.ts

@@ -9,10 +9,12 @@ export const CODEX_BASE_URL = "https://chatgpt.com/backend-api";
  * Updated from npm by `bun run check-spoofed-versions --update`.
  *
  * The backend version-gates model availability against this value on both
- * `/models?client_version=` and `/responses`; 0.155.1 exposes GPT-6 Sol and Luna.
- * An older pin silently hides newer SKUs from discovery.
+ * `/models?client_version=` and `/responses`, independently of a model's
+ * declared `minimal_client_version`: GPT-6.1 Sol declares 0.153.0 yet is
+ * omitted from `/models` at 0.155.1 and listed at 0.159.0. An older pin
+ * silently hides newer SKUs from discovery.
  */
-export const CODEX_CLIENT_VERSION = "0.155.1";
+export const CODEX_CLIENT_VERSION = "0.159.0";
 
 export const OPENAI_HEADERS = {
 	BETA: "OpenAI-Beta",