@oh-my-pi/pi-catalog 18.4.3 → 18.4.4

package/CHANGELOG.md

@@ -2,6 +2,23 @@
 
 ## [Unreleased]
 
+## [18.4.4] - 2026-09-29
+
+### Added
+
+- Added `compat.bedrockMessagesApi` for `anthropic-messages` models: detected from a Bedrock `/anthropic` base URL under any provider id, it drops tool `strict`, fits `metadata.user_id` to Bedrock's pattern, and enables on-demand compaction; set it in `models.yml` to opt a proxy or an `ANTHROPIC_BASE_URL` reroute in, or `false` to opt out ([#13311](https://github.com/can1357/oh-my-pi/pull/13311)).
+- Added GPT-6.1 Sol pricing for `openai-codex` (`gpt-6.1-sol`, `gpt-6.1-sol-wm`: $2 input, $10 output, $0.10 cached input), so Codex usage shows cost instead of $0 ([#13782](https://github.com/can1357/oh-my-pi/pull/13782) by [@H4vC](https://github.com/H4vC)).
+- Added `Model.serviceTiers`, the service tiers a provider advertises for a model; Codex discovery fills it from `service_tiers` (e.g. `priority`, `ultrafast`) ([#13782](https://github.com/can1357/oh-my-pi/pull/13782) by [@H4vC](https://github.com/H4vC)).
+- Added the documented 922K input maximum for `openai-codex/gpt-6.1-sol` with extended context on (Codex reports a stale 872K), matching GPT-6 Astra; the default window stays 272K ([#13782](https://github.com/can1357/oh-my-pi/pull/13782) by [@H4vC](https://github.com/H4vC)).
+
+### Fixed
+
+- Fixed `openai-codex/gpt-6.1-sol` not appearing in Codex discovery even on accounts where the Codex CLI lists it: the backend hides it from client version 0.155.1, so Codex requests now report 0.159.0, the current Codex CLI release ([#13782](https://github.com/can1357/oh-my-pi/pull/13782) by [@H4vC](https://github.com/H4vC)).
+- Fixed on-demand compaction staying off for Claude models on the `amazon-bedrock` and `bedrock-mantle` providers when they use Bedrock's `/anthropic` routes ([#13311](https://github.com/can1357/oh-my-pi/pull/13311) by [@mustafaabidali](https://github.com/mustafaabidali)).
+- Fixed Claude models on Bedrock's `/anthropic` routes resolving `compat.disableStrictTools: false`, although those routes reject the tool `strict` field ([#13311](https://github.com/can1357/oh-my-pi/pull/13311) by [@mustafaabidali](https://github.com/mustafaabidali)).
+- Fixed Bedrock's FIPS (`bedrock-runtime-fips`) and AWS PrivateLink (`vpce-….vpce.amazonaws.com`) hostnames, and Mantle's documented `/v1` OpenAI base, not being recognized as Bedrock routes, which left them without native compaction and the `/anthropic` request fixes ([#13311](https://github.com/can1357/oh-my-pi/pull/13311) by [@mustafaabidali](https://github.com/mustafaabidali)).
+- Added `supportsBetweenToolsThinking` Anthropic compat flag (`supports-between-tools-thinking` KDL axis), enabled for Claude Sonnet 5.5
+
 ## [18.4.3] - 2026-09-28
 
 ### Added

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

@@ -6,6 +6,12 @@
  * prefix check would accept lookalikes like `https://api.anthropic.com.evil.com`.
  */
 export declare function isOfficialAnthropicApiUrl(baseUrl?: string): boolean;
+/**
+ * Amazon Bedrock's Anthropic Messages API: the `/anthropic` path on the
+ * bedrock-runtime or bedrock-mantle endpoint. It rejects the tool `strict`
+ * field and enforces Anthropic signatures on replay.
+ */
+export declare function isBedrockAnthropicRoute(baseUrl?: string): boolean;
 /**
  * Azure AI Inference / Foundry Anthropic route
  * (`<resource>.inference.ai.azure.com`, `<resource>.services.ai.azure.com`).

package/dist/types/hosts.d.ts

@@ -165,5 +165,18 @@ export declare function isVertexExpressOpenAIUrl(baseUrl: string): boolean;
 export declare function isVertexRawPredictUrl(baseUrl: string): boolean;
 /** Azure OpenAI deployment-scoped path (`…/deployments/<name>/…`). */
 export declare function isAzureDeploymentsUrl(baseUrl: string): boolean;
+/**
+ * Amazon Bedrock API route on a bedrock-runtime or bedrock-mantle endpoint
+ * (public, FIPS, or PrivateLink hostname):
+ * - `anthropic`: the Anthropic Messages API under `/anthropic`.
+ * - `openai`: the OpenAI-compatible APIs under `/openai`, plus Mantle's
+ *   documented `/v1` base (`https://bedrock-mantle.<region>.api.aws/v1`).
+ *
+ * Hostnames are parsed strictly so proxies that embed these hosts in a path
+ * do not match.
+ */
+export declare function isBedrockRouteUrl(baseUrl: string | undefined, route: "openai" | "anthropic"): boolean;
+/** Amazon Bedrock's OpenAI-compatible routes; see {@link isBedrockRouteUrl}. */
+export declare function isBedrockOpenAIUrl(baseUrl: string | undefined): boolean;
 /** Alibaba DashScope consumer `compatible-mode` endpoint (rejects multimodal arrays for some text-only SKUs). */
 export declare function isDashscopeCompatibleModeUrl(baseUrl: string): boolean;

package/dist/types/types.d.ts

@@ -481,6 +481,15 @@ 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`
@@ -508,6 +517,13 @@ 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
@@ -804,9 +820,15 @@ 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
@@ -1143,6 +1165,12 @@ 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/dist/types/wire/codex.d.ts

@@ -7,10 +7,12 @@ export declare 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 declare const CODEX_CLIENT_VERSION = "0.155.1";
+export declare const CODEX_CLIENT_VERSION = "0.159.0";
 export declare const OPENAI_HEADERS: {
     readonly BETA: "OpenAI-Beta";
     /** Codex feature-negotiation header; values identify opt-in wire protocols. */

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@oh-my-pi/pi-catalog",
-	"version": "18.4.3",
+	"version": "18.4.4",
 	"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": "18.4.3",
-		"@oh-my-pi/pi-utils": "18.4.3"
+		"@oh-my-pi/omptype": "18.4.4",
+		"@oh-my-pi/pi-utils": "18.4.4"
 	},
 	"devDependencies": {
 		"@bgotink/kdl": "0.4.0",
-		"@oh-my-pi/pi-ai": "18.4.3",
+		"@oh-my-pi/pi-ai": "18.4.4",
 		"@types/bun": "^1.3.14"
 	},
 	"engines": {

package/src/compat/anthropic.ts

@@ -5,7 +5,7 @@
  * pi-ai both consume these; URL matching is the one detection surface that
  * stays in code.
  */
-import { hostMatchesUrl } from "../hosts";
+import { hostMatchesUrl, isBedrockRouteUrl } from "../hosts";
 
 const OFFICIAL_ANTHROPIC_URL = "https://api.anthropic.com";
 
@@ -27,6 +27,15 @@ const VERTEX_ANTHROPIC_URL_MARKER = /aiplatform\.googleapis\.com\/.+\/publishers
 const BEDROCK_ANTHROPIC_URL_MARKER = /(?:^|\/\/|\.)bedrock-runtime\.[a-z0-9-]+\.amazonaws\.com/i;
 const AZURE_ANTHROPIC_URL_MARKER = /(?:^|\/\/|\.)[a-z0-9-]+\.(?:inference|services)\.ai\.azure\.com/i;
 
+/**
+ * Amazon Bedrock's Anthropic Messages API: the `/anthropic` path on the
+ * bedrock-runtime or bedrock-mantle endpoint. It rejects the tool `strict`
+ * field and enforces Anthropic signatures on replay.
+ */
+export function isBedrockAnthropicRoute(baseUrl?: string): boolean {
+	return isBedrockRouteUrl(baseUrl, "anthropic");
+}
+
 /**
  * Azure AI Inference / Foundry Anthropic route
  * (`<resource>.inference.ai.azure.com`, `<resource>.services.ai.azure.com`).
@@ -53,6 +62,7 @@ export function isAnthropicSigningProxyUrl(baseUrl?: string): boolean {
 			(CLOUDFLARE_ANTHROPIC_GATEWAY_URL_MARKER.test(baseUrl) ||
 				VERTEX_ANTHROPIC_URL_MARKER.test(baseUrl) ||
 				BEDROCK_ANTHROPIC_URL_MARKER.test(baseUrl))) ||
+		isBedrockAnthropicRoute(baseUrl) ||
 		isAzureAnthropicRoute(baseUrl)
 	);
 }

package/src/compat/axes.ts

@@ -190,6 +190,7 @@ export const AXES: Readonly<Record<string, AxisDef>> = {
 	"zai-reasoning-effort-dialect": wire("zaiReasoningEffortDialect", ["openai"]),
 
 	// ── wire: anthropic-messages ──
+	"bedrock-messages-api": wire("bedrockMessagesApi", ["anthropic"]),
 	"allow-anthropic-header-overrides": wire("allowAnthropicHeaderOverrides", ["anthropic"]),
 	"disable-adaptive-thinking": wire("disableAdaptiveThinking", ["anthropic"]),
 	"disable-strict-tools": wire("disableStrictTools", ["anthropic"]),
@@ -209,6 +210,7 @@ export const AXES: Readonly<Record<string, AxisDef>> = {
 	"supports-mid-conversation-tool-changes": wire("supportsMidConversationToolChanges", ["anthropic"]),
 	"supports-per-message-effort": wire("supportsPerMessageEffort", ["anthropic"]),
 	"supports-server-compaction": wire("supportsServerCompaction", ["anthropic"]),
+	"supports-between-tools-thinking": wire("supportsBetweenToolsThinking", ["anthropic"]),
 	"supports-thinking-binding-controls": wire("supportsThinkingBindingControls", ["anthropic"]),
 	"supports-turn-scoped-system": wire("supportsTurnScopedSystem", ["anthropic"]),
 

package/src/compat/resolve.ts

@@ -31,7 +31,12 @@ import type {
 	ResolvedOpenAISharedCompat,
 	ThinkingConfig,
 } from "../types";
-import { isAnthropicSigningProxyUrl, isAzureAnthropicRoute, isOfficialAnthropicApiUrl } from "./anthropic";
+import {
+	isAnthropicSigningProxyUrl,
+	isAzureAnthropicRoute,
+	isBedrockAnthropicRoute,
+	isOfficialAnthropicApiUrl,
+} from "./anthropic";
 import { applyCompatOverrides } from "./apply";
 import { API_COMPAT_RECORDS, AXES, type CompatRecordName } from "./axes";
 import { hasModelScopedEffortsRule, resolveCascade } from "./cascade";
@@ -853,7 +858,9 @@ function resolveAnthropicPolicy(
 	const isCopilot = modelMatchesHost(spec, "githubCopilot");
 	const isZenmux = modelMatchesHost(spec, "zenmux");
 	const requiresThinkingEnabled = modelMatchesHost(spec, "moonshotNative") && facts.kimiMandatoryThinking;
-	const isAzure = isAzureAnthropicRoute(baseUrl);
+	const bedrockMessagesApi = isBedrockAnthropicRoute(baseUrl);
+	// Both routes reject the top-level tool `strict` field.
+	const rejectsStrictTools = isAzureAnthropicRoute(baseUrl) || bedrockMessagesApi;
 	const signingEndpoint = official || isCopilot || isZenmux || isAnthropicSigningProxyUrl(baseUrl);
 	const compat: ResolvedAnthropicCompat = {
 		officialEndpoint: official,
@@ -862,7 +869,9 @@ function resolveAnthropicPolicy(
 		supportsServerCompaction: false,
 		firstPartyProvider: false,
 		supportsOutputEffort: true,
-		disableStrictTools: isAzure,
+		disableStrictTools: rejectsStrictTools,
+		// Present as a key so models.yml `compat` can set it; unset unless detected.
+		bedrockMessagesApi: bedrockMessagesApi || undefined,
 		disableAdaptiveThinking: false,
 		allowAnthropicHeaderOverrides: false,
 		supportsEagerToolInputStreaming: official,
@@ -872,6 +881,7 @@ function resolveAnthropicPolicy(
 		supportsMidConversationToolChanges: false,
 		supportsPerMessageEffort: false,
 		supportsThinkingBindingControls: false,
+		supportsBetweenToolsThinking: false,
 		supportsForcedToolChoice: !requiresThinkingEnabled && !facts.family("fable", "mythos"),
 		supportsSamplingParams: !facts.anthropicAdaptiveGenAtLeast("4.7"),
 		requiresToolResultId: false,

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

@@ -7,11 +7,11 @@ class "anthropic" {
 			thinking-prefix-binding #true
 		}
 	}
-	// On-demand compaction (compact-2026-09-04) is available on the Claude
-	// API and Vertex, not Amazon Bedrock or unverified gateway deployments.
+	// On-demand compaction (compact-2026-09-04) works on the Claude API, Vertex,
+	// and Amazon Bedrock's `/anthropic` routes, not Bedrock Converse.
 	// Foundry / Claude Platform on AWS are first-party Anthropic routes whose
 	// effective URLs are checked at request time.
-	on "anthropic" "google-vertex" {
+	on "anthropic" "google-vertex" "amazon-bedrock" "bedrock-mantle" {
 		family "fable" {
 			revision ">=5" {
 				supports-server-compaction #true
@@ -68,6 +68,10 @@ class "anthropic" {
 	family "sonnet" {
 		revision ">=5.5 <6" {
 			supports-forced-tool-choice #false
+			// `thinking: {type: "disabled"}` is a 400; `between_tools` is the
+			// lowest thinking setting.
+			// https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#turn-off-up-front-thinking
+			supports-between-tools-thinking #true
 			// Signed thinking is bound to the exact preceding conversation.
 			thinking-prefix-binding #true
 		}

package/src/compat/rules/providers/openai-codex.kdl

@@ -89,6 +89,23 @@ provider "openai-codex" {
 			cache-write 0
 		}
 	}
+	// GPT-6.1 Sol keeps GPT-6 Sol's $2/$10 list price but halves cached input
+	// to $0.10 (OpenAI API docs, 2026-09-29). Like Astra, Codex reports a 272K
+	// default and an 872K maximum while OpenAI documents 922K max input (1.05M
+	// total); the curated maximum applies only with extended context on, and a
+	// higher live maximum still wins.
+	models "gpt-6.1-sol" "gpt-6.1-sol-wm" {
+		cost-patch {
+			input 2.0
+			output 10.0
+			cache-read 0.1
+			cache-write 0
+		}
+		limits-patch {
+			context-window 272000
+		}
+		max-context-window 922000
+	}
 	models "gpt-6-luna" "gpt-6-luna-wm" {
 		cost-patch {
 			input 0.1