@oh-my-pi/pi-catalog 18.8.0 → 18.8.2

package/CHANGELOG.md

@@ -2,6 +2,19 @@
 
 ## [Unreleased]
 
+## [18.8.2] - 2026-10-07
+
+### Fixed
+
+- Fixed Anthropic requests carrying too many inline screenshot bytes by exposing a provider image-byte budget, applied only on the official endpoint ([#14453](https://github.com/can1357/oh-my-pi/issues/14453)).
+
+## [18.8.1] - 2026-10-07
+
+### Fixed
+
+- Fixed Codex Fast (`priority`) pricing to use OpenAI’s 2.5× included-usage rate for supported models, excluding GPT-5.5 and GPT-6 Astra.
+- Fixed GitHub Copilot models with tier-specific prompt limits incorrectly defaulting to the long-context window.
+
 ## [18.8.0] - 2026-10-07
 
 ### Changed

package/dist/types/compat/request-size.d.ts

@@ -0,0 +1,7 @@
+import type { Model } from "../types.js";
+/**
+ * Maximum encoded inline-image bytes retained per request for a deployment with a documented body-size limit.
+ * The axis is a host contract: a rerouted `baseUrl` (proxy, gateway) imposes its own limit, so the budget
+ * applies only while the model targets its official endpoint.
+ */
+export declare function resolveInlineImageByteBudget(model: Model): number | undefined;

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@oh-my-pi/pi-catalog",
-	"version": "18.8.0",
+	"version": "18.8.2",
 	"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": "18.8.0",
-		"@oh-my-pi/pi-utils": "18.8.0"
+		"@oh-my-pi/omptype": "18.8.2",
+		"@oh-my-pi/pi-utils": "18.8.2"
 	},
 	"devDependencies": {
 		"@bgotink/kdl": "0.4.0",
-		"@oh-my-pi/pi-ai": "18.8.0",
+		"@oh-my-pi/pi-ai": "18.8.2",
 		"@types/bun": "^1.3.14"
 	},
 	"engines": {

package/src/compat/axes.ts

@@ -395,6 +395,7 @@ export const AXES: Readonly<Record<string, AxisDef>> = {
 	/** How the model line bills an input image; shape and formulas in `./image-tokenization`. */
 	"image-tokenization": { key: "imageTokenization", set: "catalog", shape: "object" },
 	"image-model": { key: "imageModel", set: "catalog", shape: "scalar" },
+	"inline-image-byte-budget": { key: "inlineImageByteBudget", 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/request-size.ts

@@ -0,0 +1,25 @@
+import { toModelSpec } from "../provider-models/bundled-references";
+import type { Model } from "../types";
+import { resolveCatalogAxes } from "./resolve";
+
+const imageBudgetCache = new Map<string, number | null>();
+const IMAGE_BUDGET_CACHE_MAX = 8192;
+
+/**
+ * Maximum encoded inline-image bytes retained per request for a deployment with a documented body-size limit.
+ * The axis is a host contract: a rerouted `baseUrl` (proxy, gateway) imposes its own limit, so the budget
+ * applies only while the model targets its official endpoint.
+ */
+export function resolveInlineImageByteBudget(model: Model): number | undefined {
+	const compat = model.compat;
+	if (!compat || !("officialEndpoint" in compat) || !compat.officialEndpoint) return undefined;
+	const key = `${model.provider} ${model.id} ${model.api}`;
+	let budget = imageBudgetCache.get(key);
+	if (budget === undefined) {
+		const value = resolveCatalogAxes(toModelSpec(model)).inlineImageByteBudget;
+		budget = typeof value === "number" && Number.isFinite(value) && value > 0 ? value : null;
+		if (imageBudgetCache.size >= IMAGE_BUDGET_CACHE_MAX) imageBudgetCache.clear();
+		imageBudgetCache.set(key, budget);
+	}
+	return budget ?? undefined;
+}

package/src/compat/rules/README.md

@@ -217,6 +217,8 @@ One object axis carries a computed form: `long-context-cost` accepts either the
 
 `context-window-authoritative #true` preserves a host's supplied context window through runtime model selection instead of applying inferred expansion or reference-price-tier caps. Explicit user context overrides still apply afterward. It applies to rows materialized through `buildModel` (discovery and regenerated bundles). See [`providers/factory-droid.kdl`](providers/factory-droid.kdl).
 
+`inline-image-byte-budget` caps retained base64 image characters for a deployment's request body. It leaves room for tool schemas and text beneath the provider's body-size limit; the coding agent reads it through `resolveInlineImageByteBudget` before sending live history. The budget applies only while `compat.officialEndpoint` holds: a custom `baseUrl` imposes its own body limit.
+
 The routed-subscription registry axes (`upstream-rotation`, `region-upstreams-global|us|eu`, `region-limits-eu`, `credit-rates`, `list-price-from`, `routing-family`, `policy-aliases`, `entitlement`, `default-reasoning-off`) describe a gateway whose proxy fans one model out to several upstreams. They are read through `src/compat/factory-droid.ts` by Factory Droid discovery and its request provider, not materialized by `buildModel`. A provider-wide `region-upstreams-*` rule is the upstream serving table and a model rule replaces it for that region. `list-price-from "<provider>" ["<id>"]` shows a bundled row's list price beside the subscription's own billing; unlike seed values it is resolved at runtime and degrades to the seed's zero cost when the row is gone. See [`providers/factory-droid.kdl`](providers/factory-droid.kdl), whose wire and billing pool per model are `api-routes` and `quota-tiers` rules in `runtime/behavior.kdl`.
 
 ### Time-based pricing

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

@@ -68,6 +68,13 @@ provider "anthropic" {
 	// combines this fact with a per-request effective-URL check, so it never
 	// authorizes a block on its own.
 	first-party-provider #true
+	// Messages requests cap at 32 MB. Reserve 8 MB for text, tools, and JSON
+	// framing when retaining inline base64 images in a long conversation.
+	// Applied only on the official endpoint; a custom baseUrl has its own limit.
+	// https://platform.claude.com/docs/en/api/overview#request-size-limits
+	on-api "anthropic-messages" {
+		inline-image-byte-budget 24000000
+	}
 	class "anthropic" {
 		revision ">=3.7 <4.6" {
 			thinking-efforts "minimal" "low" "medium" "high" "xhigh"

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

@@ -25,9 +25,13 @@ provider "openai-codex" {
 	}
 
 	// Replaces the Codex provider's handwritten flex/priority pricing fallback.
+	// Fast (priority) draws included subscription usage at 2.5x Standard on
+	// every model that supports it; purchased credits and Enterprise
+	// pay-as-you-go bill 2x. See
+	// https://learn.chatgpt.com/docs/agent-configuration/speed.
 	service-tier-cost {
 		flex 0.5
-		priority 2
+		priority 2.5
 	}
 	// Harmony-protocol leak detection/mitigation applies to every Codex model,
 	// current and future; replaces the provider check in harmony-leak.ts.
@@ -133,14 +137,6 @@ provider "openai-codex" {
 		revision "<5.4" {
 			supports-reasoning-summary #false
 		}
-		// Subscription Codex rates the priority service tier at 2.5x for the
-		// GPT-5.5 generation (2x elsewhere).
-		revision "=5.5" {
-			service-tier-cost {
-				flex 0.5
-				priority 2.5
-			}
-		}
 		// Codex discovery reports inconsistent priorities for the GPT-5.4
 		// family; normalize by variant. Mini/nano also keep the lower prompt
 		// budget despite their plain OpenAI ids.