@oh-my-pi/pi-catalog 15.10.11

package/CHANGELOG.md

@@ -0,0 +1,38 @@
+# Changelog
+
+## [Unreleased]
+
+## [15.10.11] - 2026-06-10
+
+### Added
+
+- Added `hostMatchesUrl`, `modelMatchesHost`, and endpoint-shape helpers in the new `hosts` module for consistent provider/baseUrl matching
+- `buildModel(spec)` (`build.ts`) is now the single Model constructor: it materializes the fully-resolved compat record and canonical thinking metadata exactly once (compat first, thinking derived from identity + resolved compat), so `Model.compat` is a required, complete `CompatOf<TApi>` (`ResolvedOpenAICompat`/`ResolvedOpenAIResponsesCompat`/`ResolvedAnthropicCompat`) and request-path code reads fields with zero URL parsing and zero per-request allocation. Sparse user/config overrides live on the new `ModelSpec<TApi>` input shape and survive on `Model.compatConfig` for introspection.
+- Added `ResolvedAnthropicCompat.supportsSamplingParams` (Opus 4.7+/Fable/Mythos reject `temperature`/`top_p`/`top_k` with a 400), baked at build time from model identity so the request path stops re-parsing model ids.
+- Compat detection gained model-time flags so handlers stop sniffing baseUrl: completions `supportsReasoningParams`, `alwaysSendMaxTokens`, `isOpenRouterHost`, `isVercelGatewayHost`, `streamIdleTimeoutMs`, and a precomputed `whenThinking` alternate view (OpenCode `reasoning_content` gating, #1071/#1484); responses `strictResponsesPairing`, `supportsLongPromptCacheRetention`, `supportsReasoningEffort`; anthropic `officialEndpoint`, `requiresToolResultId`, `replayUnsignedThinking`.
+- New `@oh-my-pi/pi-catalog` package: the model catalog extracted from `@oh-my-pi/pi-ai`. Owns the bundled `models.json` and its generation pipeline (`scripts/generate-models.ts`), the core model data types (`Model`, `Api`, `ThinkingConfig`, `Effort`, `Usage`, compat interfaces), thinking metadata enrichment and generated policies (`model-thinking.ts`), the SQLite model cache and model manager, per-provider discovery factories (`provider-models/`), the discovery protocol clients (`discovery/`), and the new `CATALOG_PROVIDERS` table — the single source of truth for provider ids, default models, and discovery wiring (`KnownProvider`, `PROVIDER_DESCRIPTORS`, and `DEFAULT_MODEL_PER_PROVIDER` are derived from it).
+- New `identity/` module centralizing model-identity concerns that were previously duplicated across packages: family classification and version parsing (`identity/classify.ts`, extracted from pi-ai's `model-thinking` internals), canonical model equivalence with injected reference data (`identity/equivalence.ts`, from coding-agent's `model-equivalence`), proxy/reseller reference lookup (`identity/reference.ts`, from coding-agent's `model-registry`), bracket-affix and id-segment helpers (`identity/id.ts`), a single trailing-marker vocabulary with canonical vs reference flavors (`identity/markers.ts` — `search` stays reference-only so Perplexity's `sonar-pro-search` remains canonical-distinct), and provider priority ordering (`identity/priority.ts`).
+- Memoized bundled-reference accessors (`getBundledCanonicalReferenceData` / `getBundledModelReferenceIndex` in `identity/bundled.ts`): one lazy walk of the bundled catalog feeds both canonical equivalence and proxy-reference lookup, so consumers no longer hand-roll the glue.
+- `identity/selection.ts`: pure canonical-variant selection (`resolveCanonicalVariant`, `buildCanonicalModelOrder`, `CanonicalVariantPreferences`) extracted from the coding-agent registry — provider rank, then exact-id match, variant source, id length, and candidate order.
+
+### Changed
+
+- Changed OpenAI compatibility detection to use shared host classifiers (`modelMatchesHost`/`hostMatchesUrl`) with normalized matching instead of raw URL substring checks
+- Changed `hostMatchesUrl`/`modelMatchesHost` usage in compatibility detection to reduce mismatches across case variants and provider alias hosts
+- Provider catalog entries now carry the runtime API-key env fallback as an ordered `envVars` list; `catalogDiscovery.envVars` became an optional generation-time override (only `cursor` and `vercel-ai-gateway` differ) and `PROVIDER_DESCRIPTORS` materializes the resolved list for `generate-models.ts`.
+- `Model`'s api parameter now defaults to `Api` instead of `any` (`Model<TApi extends Api = Api>`), so bare `Model` no longer behaves as `Model<any>` at call sites.
+- `ThinkingConfig` is now explicit and total: an ordered `efforts` array replaces the `minLevel`/`maxLevel`/`levels` range encoding, and the wire facts are baked alongside it — `effortMap` (anthropic-adaptive 4-tier vs 5-tier scale, shared with the OpenRouter completions remap) and `supportsDisplay` (adaptive `display` field support). Explicit spec thinking owns the capability surface (`mode`/`efforts`/`defaultLevel`) and wins over inference; missing wire facts are backfilled from identity so configs never need to know Anthropic's tier tables. Reasoning models that reject the wire effort param (`compat.supportsReasoningEffort: false` on openai-responses*) are encoded as `thinking: undefined` ("thinks, no control surface") instead of the removed `modelOmitsReasoningEffort` special case. `models.json` was re-baked in the new vocabulary behind a 3196-model behavioral parity gate, and the model cache schema bumped to v4 to invalidate old-shape rows.
+- `mapEffortToGoogleThinkingLevel(effort)` is now a static map (model parameter dropped — validation stays at the `requireSupportedEffort` call sites), and `mapEffortToAnthropicAdaptiveEffort` reads the baked `thinking.effortMap` instead of re-classifying the model id per request.
+- Generator-only policy code moved out of the runtime bundle into `scripts/generated-policies.ts`: `applyGeneratedModelPolicies` (now policy fixups + thinking re-bake via the shared deriver), `linkOpenAIPromotionTargets`, the Copilot context-window table, minimax/opencode-go compat fixups, and `CLOUDFLARE_FALLBACK_MODEL`. The anthropic id predicates (`hasOpus47ApiRestrictions`, `supportsMidConversationSystemMessages`, `isAnthropicFableOrMythosModel`) moved to `identity/family` for build-time use by the compat/thinking derivers only.
+
+### Fixed
+
+- Fixed Anthropic official-endpoint detection to require strict HTTPS hostname matching so non-official or lookalike URLs are no longer treated as official Anthropic hosts
+- Fixed Ollama Cloud dynamic discovery so same-id matches from other providers no longer supply context-window or max-output-token limits for discovered models.
+- Wired `@oh-my-pi/pi-catalog` into the release publish package list, tarball install smoke test, and root `bun generate-models` script.
+- Fixed `supportsAdaptiveThinkingDisplay` only matching dash-form version ids: dotted ids (`claude-opus-4.7`) now classify through `identity/classify` like every other anthropic predicate, so six bundled dotted Opus 4.7/4.8 entries (github-copilot, vercel-ai-gateway, zenmux) regain adaptive `display` support; bare dated ids (`claude-opus-4-20250514` = Opus 4.0) stay excluded.
+- Fixed the OpenRouter anthropic adaptive-effort map misclassifying bare dated Opus ids (`claude-opus-4-20250514` parsed as version 4.20 → wrongly adaptive); the map now derives from the shared classifier and the shared 4-/5-tier tables.
+
+### Removed
+
+- Removed the runtime enrichment layer: `enrichModelThinking` (and its non-enumerable memo-slot cache), `refreshModelThinking`, `modelOmitsReasoningEffort`, and the `model-thinking` re-exports of generator-only policies. Thinking metadata is resolved exactly once inside `buildModel`; runtime helpers (`getSupportedEfforts`, `clampThinkingLevelForModel`, `requireSupportedEffort`, the effort mappers) are pure field reads.

package/dist/types/build.d.ts

@@ -0,0 +1,3 @@
+import type { Api, CompatOf, Model, ModelSpec } from "./types";
+export declare function buildModel<TApi extends Api>(spec: ModelSpec<TApi>): Model<TApi>;
+export declare function buildCompat(spec: ModelSpec<Api>): CompatOf<Api>;

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

@@ -0,0 +1,11 @@
+import type { ModelSpec, ResolvedAnthropicCompat } from "../types";
+/**
+ * Official first-party Anthropic API. A missing baseUrl is official on purpose:
+ * request dispatch falls back to `https://api.anthropic.com`. This is the one
+ * auth-sensitive host check — OAuth credentials are attached based on it — so
+ * it requires the exact origin or a path boundary (`/`) after it; a bare
+ * prefix check would accept lookalikes like `https://api.anthropic.com.evil.com`.
+ */
+export declare function isOfficialAnthropicApiUrl(baseUrl?: string): boolean;
+/** Build the resolved anthropic-messages compat record for a model spec. */
+export declare function buildAnthropicCompat(spec: ModelSpec<"anthropic-messages">): ResolvedAnthropicCompat;

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

@@ -0,0 +1,7 @@
+/**
+ * Assign defined override values onto a freshly-built resolved compat record,
+ * in place. Keys the record doesn't declare are ignored (loosely-typed config
+ * may carry junk). `buildModel` is the only intended caller — the record being
+ * mutated is the single per-model allocation; nothing here runs per request.
+ */
+export declare function applyCompatOverrides(compat: object, overrides: object | undefined): void;

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

@@ -0,0 +1,21 @@
+import type { ModelSpec, OpenAICompat, ResolvedOpenAICompat, ResolvedOpenAIResponsesCompat } from "../types";
+/**
+ * Build the resolved chat-completions compat record for a model spec.
+ * Provider takes precedence over URL-based detection since it's explicitly configured.
+ */
+export declare function buildOpenAICompat(spec: ModelSpec<"openai-completions">): ResolvedOpenAICompat;
+interface OpenAIResponsesSpecLike {
+    provider: string;
+    baseUrl: string;
+    compat?: OpenAICompat;
+}
+/**
+ * Build the resolved Responses-API compat record. The Responses flavor
+ * deliberately differs from chat-completions: GitHub Copilot's responses
+ * endpoint accepts the `developer` role, while strict tool mode is scoped to
+ * first-party OpenAI/Azure/Copilot providers. Developer-role and prompt-cache
+ * detection are URL-only on purpose — the historical call sites never
+ * consulted the provider id for them.
+ */
+export declare function buildOpenAIResponsesCompat(spec: OpenAIResponsesSpecLike): ResolvedOpenAIResponsesCompat;
+export {};

package/dist/types/discovery/antigravity.d.ts

@@ -0,0 +1,61 @@
+import type { ModelSpec } from "../types";
+/**
+ * Raw model metadata returned by Antigravity's `fetchAvailableModels` endpoint.
+ */
+export interface AntigravityDiscoveryApiModel {
+    displayName?: string;
+    supportsImages?: boolean;
+    supportsThinking?: boolean;
+    thinkingBudget?: number;
+    recommended?: boolean;
+    maxTokens?: number;
+    maxOutputTokens?: number;
+    model?: string;
+    apiProvider?: string;
+    modelProvider?: string;
+    isInternal?: boolean;
+    supportsVideo?: boolean;
+}
+/**
+ * Grouping metadata used by Antigravity to surface recommended model ids.
+ */
+export interface AntigravityDiscoveryAgentModelGroup {
+    modelIds?: string[];
+}
+/**
+ * Sort/group metadata used by Antigravity to surface recommended model ids.
+ */
+export interface AntigravityDiscoveryAgentModelSort {
+    groups?: AntigravityDiscoveryAgentModelGroup[];
+}
+/**
+ * Response payload returned by Antigravity's `fetchAvailableModels` endpoint.
+ */
+export interface AntigravityDiscoveryApiResponse {
+    models?: Record<string, AntigravityDiscoveryApiModel>;
+    agentModelSorts?: AntigravityDiscoveryAgentModelSort[];
+}
+/**
+ * Options for fetching Antigravity discovery models.
+ */
+export interface FetchAntigravityDiscoveryModelsOptions {
+    /** OAuth access token used as `Authorization: Bearer <token>`. */
+    token: string;
+    /** Optional endpoint override. Defaults to Antigravity fallback endpoints. */
+    endpoint?: string;
+    /** Deprecated and ignored for antigravity discovery parity. */
+    project?: string;
+    /** Optional user agent override. */
+    userAgent?: string;
+    /** Optional abort signal for request cancellation. */
+    signal?: AbortSignal;
+    /** Optional fetch implementation override for tests. */
+    fetcher?: typeof fetch;
+}
+/**
+ * Fetches discoverable Antigravity models and normalizes them into canonical model entries.
+ *
+ * Returns `null` on network/payload/auth failures.
+ * Returns `[]` only when the endpoint responds successfully with no usable models.
+ */
+export declare function fetchAntigravityDiscoveryModels(options: FetchAntigravityDiscoveryModelsOptions): Promise<ModelSpec<"google-gemini-cli">[] | null>;

package/dist/types/discovery/codex.d.ts

@@ -0,0 +1,38 @@
+import type { ModelSpec } from "../types";
+/**
+ * Fetch options for OpenAI Codex model discovery.
+ */
+export interface CodexModelDiscoveryOptions {
+    /** OAuth access token used for `Authorization: Bearer ...`. */
+    accessToken: string;
+    /** ChatGPT account id value used for `chatgpt-account-id` header. */
+    accountId?: string;
+    /** Base URL for Codex backend. Defaults to `https://chatgpt.com/backend-api`. */
+    baseUrl?: string;
+    /** Optional client version attached as `client_version` query parameter. */
+    clientVersion?: string;
+    /** Optional endpoint path candidates. Defaults to `/codex/models`, then `/models`. */
+    paths?: readonly string[];
+    /** Additional headers merged on top of required Codex headers. */
+    headers?: Record<string, string>;
+    /** Abort signal for network request cancellation. */
+    signal?: AbortSignal;
+    /** Optional fetch implementation override for tests. */
+    fetchFn?: typeof fetch;
+    /** Optional registry fetch implementation override for client version lookup. */
+    registryFetchFn?: typeof fetch;
+}
+/**
+ * Normalized Codex discovery response.
+ */
+export interface CodexModelDiscoveryResult {
+    models: ModelSpec<"openai-codex-responses">[];
+    etag?: string;
+}
+/**
+ * Fetches model metadata from Codex backend and normalizes it for pi model management.
+ *
+ * Returns `null` when no supported model-list route can be fetched/parsed.
+ * Returns `{ models: [] }` when a route succeeds but yields no usable models.
+ */
+export declare function fetchCodexModels(options: CodexModelDiscoveryOptions): Promise<CodexModelDiscoveryResult | null>;