@oh-my-pi/pi-ai 18.12.4 → 18.12.6

package/CHANGELOG.md

@@ -2,6 +2,16 @@
 
 ## [Unreleased]
 
+## [18.12.5] - 2026-10-21
+
+### Added
+
+- Added OpenAI 12-hour prompt caching for GPT-5.6+ on the Responses API: `cacheRetention: "long"` now requests `prompt_cache_options.ttl: "12h"` (instead of the ignored legacy `prompt_cache_retention: "24h"`), and `promptCache.ttl` accepts `"12h"`
+
+### Fixed
+
+- Fixed every OpenAI Codex request failing with HTTP 404 `{"detail":"Not Found"}` on personal ChatGPT accounts whose token is not region-pinned ([#16493](https://github.com/can1357/oh-my-pi/issues/16493))
+
 ## [18.12.4] - 2026-10-20
 
 ### Added
@@ -2303,21 +2313,4 @@
 - Fixed OAuth refresh persisting the rotated token by a positional index captured before the refresh `await`. A concurrent disable could reorder or shrink a provider's credential array while the refresh was in flight, landing the new token on the wrong row (or silently dropping it) and leaving accounts with a stale refresh token that failed — and was then disabled — on the next cycle. Refresh persistence, selection-index resync, and CAS-disable now address the row by id across `forceRefreshCredentialById`, candidate preflight, and in-stream selection (`#replaceCredentialById` / `#disableCredentialByIdIfMatches`).
 - Fixed `isDefinitiveOAuthFailure` treating a bare HTTP 403 (and generic `unauthorized` / access-token-expired wording) as a definitive credential failure, which permanently disabled healthy OAuth accounts on WAF, egress rate-limit, permission, and account-verification responses. Bare 403, rate limits (429), gateway/5xx, and more network errors (`ECONNRESET`, `ETIMEDOUT`, `EAI_AGAIN`, …) are now classified transient; only explicit dead-grant errors (`invalid_grant`, `invalid_token`, `unauthorized_client`, revoked, `refresh token … expired`) or a bare 401 tear the credential down.
 
-## [16.1.17] - 2026-06-24
-
-### Added
-
-- Added provider-level `notes?: string[]` field to `UsageReport` for disclaimers that apply to every limit (e.g. "OMP-observed spend only"). The field is declared in both the `usage.ts` schema and the auth-broker wire schema copy so it survives the `"+": "reject"` deserialization gate. ([#3268](https://github.com/can1357/oh-my-pi/issues/3268))
-
-### Fixed
-
-- Moved the OpenCode Go "OMP-observed spend only" disclaimer from per-limit `notes` to provider-level `notes`, so it renders once per provider instead of duplicating across every account × window. ([#3268](https://github.com/can1357/oh-my-pi/issues/3268))
-- Fixed Anthropic rate-limit header usage cache entries retaining legacy missing account metadata after refresh.
-- Fixed Anthropic-compatible budget-effort models dropping the selected effort before request serialization, so `output_config.effort` is emitted alongside `thinking.budget_tokens` when model metadata declares `mode: "anthropic-budget-effort"`.
-- Fixed `anthropic-messages` silently dropping caller-supplied `Authorization` / `X-Api-Key` from `model.headers` and `ANTHROPIC_CUSTOM_HEADERS`, blocking custom proxy auth schemes. Non-OAuth requests now honor the caller's value (matching `openai-responses`); the lower-level client also suppresses its `X-Api-Key` add when a custom `Authorization` is supplied for a non-official endpoint so the proxy receives a single credential. OAuth bearer + Cloudflare AI Gateway keep their pre-existing enforced auth headers. ([#3391](https://github.com/can1357/oh-my-pi/issues/3391))
-- Fixed Ollama Cloud `num_predict` ignoring the provider's 65536 output-token cap so stale `models.db` rows (or custom `modelOverrides` re-enabling output caps) that carried `maxTokens: 1048576` from a pre-omitMaxOutputTokens catalog 400'd every request with `max_tokens (1048576) exceeds model's maximum output tokens (65536) for model deepseek-v4-pro`. The Ollama provider now clamps `num_predict` for any `ollama-cloud` request at the documented 65536 cap before sending, independent of the cached spec's `maxTokens` and on top of the existing `omitMaxOutputTokens` policy — so the request stays valid even when the load-time policy never normalized the spec. Self-hosted `ollama` traffic is unaffected. ([#3392](https://github.com/can1357/oh-my-pi/issues/3392))
-- Fixed OpenRouter Anthropic models on the Responses path omitting `cache_control`, so prompt caching engages without forcing Chat Completions. ([#3397](https://github.com/can1357/oh-my-pi/issues/3397))
-- Fixed OpenRouter Anthropic Responses follow-up requests replaying prior reasoning items with stale signatures, which caused HTTP 400 `Invalid signature in thinking block` errors after a thinking turn. ([#3399](https://github.com/can1357/oh-my-pi/issues/3399))
-- Fixed OpenRouter Anthropic models on the Responses path omitting `cache_control`, so prompt caching engages without forcing Chat Completions. `cacheRetention: "long"` now upgrades the breakpoint to `ttl: "1h"`. ([#3397](https://github.com/can1357/oh-my-pi/issues/3397))
-
-Older entries are archived in [packages/ai/CHANGELOG.md@47e6af055a17](https://github.com/can1357/oh-my-pi/blob/47e6af055a17862bc1cab6b5ebedd3db75ac2573/packages/ai/CHANGELOG.md).
+Older entries are archived in [packages/ai/CHANGELOG.md@7a5f1425b9bd](https://github.com/can1357/oh-my-pi/blob/7a5f1425b9bd79c3c74ae1d8946782b0494c8aa9/packages/ai/CHANGELOG.md).

package/dist/types/providers/openai-responses-wire.d.ts

@@ -5680,10 +5680,10 @@ export interface ResponseCreateParamsBase {
      *   `prompt_cache_retention` is not specified.
      */
     prompt_cache_retention?: "in_memory" | "24h" | null;
-    /** Explicit prompt-cache mode and minimum lifetime for GPT-5.6+ models. */
+    /** Explicit prompt-cache mode and minimum lifetime (`12h` is Responses-only) for GPT-5.6+ models. */
     prompt_cache_options?: {
         mode: "implicit" | "explicit";
-        ttl?: "30m";
+        ttl?: "30m" | "12h";
     } | null;
     /**
      * **gpt-5 and o-series models only**

package/dist/types/types.d.ts

@@ -240,8 +240,12 @@ export interface AnthropicCompactionRequest {
 export interface OpenAIPromptCacheOptions {
     /** `explicit` disables OpenAI's automatic latest-message breakpoint. */
     mode: "implicit" | "explicit";
-    /** The only currently supported minimum breakpoint lifetime. */
-    ttl?: "30m";
+    /**
+     * Minimum cache lifetime. `30m` is OpenAI's default; `12h` (Responses API only)
+     * bills writes at 2.5× input instead of 1.25×. Defaults to `12h` when
+     * `cacheRetention` resolves to `long`, otherwise `30m`.
+     */
+    ttl?: "30m" | "12h";
     /** By default, mark one existing block from stable history; `none` suppresses that marker. */
     breakpoint?: "latest-stable-message" | "none";
 }

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@oh-my-pi/pi-ai",
-	"version": "18.12.4",
+	"version": "18.12.6",
 	"description": "Unified LLM API with automatic model discovery and provider configuration",
 	"keywords": [
 		"ai",
@@ -155,11 +155,11 @@
 		"fmt": "oxfmt --no-error-on-unmatched-pattern 'src/**/*.{ts,tsx}' '{test,bench,examples,scripts}/**/*.ts' '*.ts'"
 	},
 	"dependencies": {
-		"@oh-my-pi/omptype": "18.12.4",
-		"@oh-my-pi/pi-catalog": "18.12.4",
-		"@oh-my-pi/pi-natives": "18.12.4",
-		"@oh-my-pi/pi-utils": "18.12.4",
-		"@oh-my-pi/pi-wire": "18.12.4"
+		"@oh-my-pi/omptype": "18.12.6",
+		"@oh-my-pi/pi-catalog": "18.12.6",
+		"@oh-my-pi/pi-natives": "18.12.6",
+		"@oh-my-pi/pi-utils": "18.12.6",
+		"@oh-my-pi/pi-wire": "18.12.6"
 	},
 	"devDependencies": {
 		"@types/bun": "^1.3.14"

package/src/providers/openai-completions.ts

@@ -2006,6 +2006,12 @@ function applyOpenAIChatCompletionsPromptCachePolicy(
 		return;
 	}
 
+	if (promptCache.ttl === "12h") {
+		throw new AIError.ConfigurationError(
+			`OpenAI 12h prompt caching is only available on the Responses API; ${model.provider}/${model.id} uses Chat Completions.`,
+		);
+	}
+
 	params.prompt_cache_key = promptCacheKey;
 	params.prompt_cache_options = {
 		mode: promptCache.mode,

package/src/providers/openai-responses-wire.ts

@@ -5897,8 +5897,8 @@ export interface ResponseCreateParamsBase {
 	 *   `prompt_cache_retention` is not specified.
 	 */
 	prompt_cache_retention?: "in_memory" | "24h" | null;
-	/** Explicit prompt-cache mode and minimum lifetime for GPT-5.6+ models. */
-	prompt_cache_options?: { mode: "implicit" | "explicit"; ttl?: "30m" } | null;
+	/** Explicit prompt-cache mode and minimum lifetime (`12h` is Responses-only) for GPT-5.6+ models. */
+	prompt_cache_options?: { mode: "implicit" | "explicit"; ttl?: "30m" | "12h" } | null;
 	/**
 	 * **gpt-5 and o-series models only**
 	 *

package/src/providers/openai-responses.ts

@@ -1564,10 +1564,11 @@ function applyOpenAIResponsesPromptCachePolicy(
 	options: OpenAIResponsesOptions | undefined,
 	statefulCacheBaseline?: ResponseInput,
 ): void {
+	const cacheRetention = resolveCacheRetention(options?.cacheRetention);
+	if (cacheRetention === "none") return;
 	const promptCache = options?.promptCache;
-	if (!promptCache || resolveCacheRetention(options?.cacheRetention) === "none") return;
 	if (!model.compat.supportsPromptCacheBreakpoints) {
-		if (promptCache.mode === "explicit") {
+		if (promptCache?.mode === "explicit") {
 			throw new AIError.ConfigurationError(
 				`OpenAI explicit prompt caching is unsupported for ${model.provider}/${model.id}; enable compat.supportsPromptCacheBreakpoints only for a compatible endpoint.`,
 			);
@@ -1575,11 +1576,15 @@ function applyOpenAIResponsesPromptCachePolicy(
 		return;
 	}
 
+	// GPT-5.6+ replaces `prompt_cache_retention` with `prompt_cache_options.ttl`;
+	// long retention selects the 12h minimum lifetime even without an explicit policy.
+	const ttl = promptCache?.ttl ?? (cacheRetention === "long" ? "12h" : undefined);
+	if (!promptCache && ttl === undefined) return;
 	params.prompt_cache_options = {
-		mode: promptCache.mode,
-		ttl: promptCache.ttl ?? model.compat.promptCacheBreakpointTtl,
+		mode: promptCache?.mode ?? "implicit",
+		ttl: ttl ?? model.compat.promptCacheBreakpointTtl,
 	};
-	if (promptCache.mode === "explicit" && promptCache.breakpoint !== "none")
+	if (promptCache?.mode === "explicit" && promptCache.breakpoint !== "none")
 		markLatestStableResponsesCacheBreakpoint(params.input, statefulCacheBaseline);
 }
 
@@ -1661,11 +1666,14 @@ export function buildParams(
 		instructions: systemInstructions,
 		stream: true,
 		prompt_cache_key: promptCacheKey,
-		prompt_cache_retention: promptCacheKey
-			? cacheRetention === "long" && model.compat.supportsLongPromptCacheRetention
+		// GPT-5.6+ ignores the legacy retention field; its lifetime rides `prompt_cache_options.ttl`.
+		prompt_cache_retention:
+			promptCacheKey &&
+			cacheRetention === "long" &&
+			model.compat.supportsLongPromptCacheRetention &&
+			!model.compat.supportsPromptCacheBreakpoints
 				? "24h"
-				: undefined
-			: undefined,
+				: undefined,
 		// Gateway routing: OpenRouter-only Responses wire field for sticky upstream
 		// routing + observability grouping; no equivalent on direct OpenAI.
 		session_id: model.compat.isOpenRouterHost ? getOpenRouterResponsesSessionId(options) : undefined,

package/src/types.ts

@@ -461,8 +461,12 @@ export interface AnthropicCompactionRequest {
 export interface OpenAIPromptCacheOptions {
 	/** `explicit` disables OpenAI's automatic latest-message breakpoint. */
 	mode: "implicit" | "explicit";
-	/** The only currently supported minimum breakpoint lifetime. */
-	ttl?: "30m";
+	/**
+	 * Minimum cache lifetime. `30m` is OpenAI's default; `12h` (Responses API only)
+	 * bills writes at 2.5× input instead of 1.25×. Defaults to `12h` when
+	 * `cacheRetention` resolves to `long`, otherwise `30m`.
+	 */
+	ttl?: "30m" | "12h";
 	/** By default, mark one existing block from stable history; `none` suppresses that marker. */
 	breakpoint?: "latest-stable-message" | "none";
 }