flexinference 1.5.2 → 1.5.3

package/CHANGELOG.md

@@ -1,5 +1,18 @@
 # Changelog
 
+## 1.5.3
+
+Relaxes Messages `max_tokens` on the FlexInference side. The SDK no longer requires or
+runtime-validates it before sending a `/messages` request; FlexInference forwards it when
+set and lets Anthropic return its own request error when it is omitted.
+
+## 1.5.2
+
+Adds zero-dependency runtime request validation matching the Python SDK: a request is now
+checked for `model` and the per-endpoint required fields before it is sent, with the two SDKs
+held to identical behavior by shared parity fixtures. The generated `Error` type also gains a
+`doc_url` field, so an error now carries a link to its documentation.
+
 ## 1.5.1
 
 Small robustness fixes for the transport, no API changes. A non-streaming request that hits

package/README.md

@@ -34,7 +34,7 @@ FlexInference routes to **OpenAI**, **Google Gemini**, and **Anthropic**. Send t
 
 - **OpenAI:** `default` (the standard tier), `priority`, `auto`, and flex on flex-capable models. You reach flex by passing a duration.
 - **Gemini:** `default` maps to Gemini's standard tier. You also get `priority` and flex on the Gemini flex models (`gemini-3.5-flash`, `gemini-3.1-flash-lite`, `gemini-3.1-pro-preview`, `gemini-3-flash-preview`, `gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2.5-flash-lite`). Gemini has no `auto` tier, so `start_within: "auto"` on a Gemini model returns `400`.
-- **Anthropic (Claude):** proxy-only. `default`, `priority`, and `auto` work; there is **no flex tier**, so a duration `start_within` on a `claude-*` model returns `400 flex_unsupported_for_anthropic`. Anthropic requires a token cap, so set `max_output_tokens` (`max_completion_tokens` on Chat, `max_tokens` on Messages) or you get `400 missing_max_tokens`. You keep the unified API and tier control, and draw down your own Anthropic credits.
+- **Anthropic (Claude):** proxy-only. `default`, `priority`, and `auto` work; there is **no flex tier**, so a duration `start_within` on a `claude-*` model returns `400 flex_unsupported_for_anthropic`. Anthropic requires an output-token field upstream. FlexInference forwards `max_output_tokens` (`max_completion_tokens` on Chat, `max_tokens` on Messages) when set and does not synthesize a default, so omitting it returns Anthropic's own request error. You keep the unified API and tier control, and draw down your own Anthropic credits.
 
 Add the provider key you'll use (OpenAI, Gemini, and/or Anthropic) in the [dashboard](https://www.flexinference.com/dashboard). Text, streaming, structured outputs, function calling, image input, and web search work across providers (send a Responses `web_search` tool; we map it to Gemini's `google_search`).
 
@@ -85,7 +85,7 @@ console.log(interactionText(res));
 
 ## Messages (Anthropic shape)
 
-Speak Anthropic's Messages shape and reach any model. `max_tokens` is required (Anthropic requires it). `messageText(res)` pulls the assistant text out of the message `content`.
+Speak Anthropic's Messages shape and reach any model. Anthropic requires `max_tokens` upstream. FlexInference forwards it when set and does not synthesize a default, so omitting it returns Anthropic's own request error. `messageText(res)` pulls the assistant text out of the message `content`.
 
 ```ts
 import { messageText } from "flexinference";

package/dist/index.js

@@ -162,9 +162,7 @@ function parseStartWithin(value) {
     const match = DURATION_RE.exec(value);
     if (match === null)
         return { kind: "invalid", reason: "malformed", value };
-    const seconds = Number(match[1]) * SECONDS_PER_HOUR +
-        Number(match[2]) * SECONDS_PER_MINUTE +
-        Number(match[3]);
+    const seconds = Number(match[1]) * SECONDS_PER_HOUR + Number(match[2]) * SECONDS_PER_MINUTE + Number(match[3]);
     return { kind: "duration", value, seconds };
 }
 // Runtime guard so plain-JS callers (who get no compile-time check) still fail
@@ -191,7 +189,7 @@ function assertStartWithin(body) {
 }
 // Per-endpoint required fields beyond the model/start_within envelope. Mirrors the Python
 // _RequestSpec table in _validation.py: responses/interactions require `input` (presence only);
-// chat requires `messages` (array); messages requires `messages` (array) + `max_tokens` (number).
+// chat/messages require `messages` (array).
 const RESPONSES_REQUEST_SPEC = {
     required: [{ name: "input", kind: "present" }],
 };
@@ -202,10 +200,7 @@ const INTERACTIONS_REQUEST_SPEC = {
     required: [{ name: "input", kind: "present" }],
 };
 const MESSAGES_REQUEST_SPEC = {
-    required: [
-        { name: "messages", kind: "array" },
-        { name: "max_tokens", kind: "finiteNumber" },
-    ],
+    required: [{ name: "messages", kind: "array" }],
 };
 // Read one field by reference off the raw body without copying it. `undefined` (or a non-object
 // body) is treated as missing; `null` counts as present, matching Python's `name in body`

package/dist/types.d.ts

@@ -90,7 +90,7 @@ export interface paths {
         };
         get?: never;
         put?: never;
-        /** Create a message. The fourth FlexInference caller format (Anthropic Messages shape in and out); works for any model via the canonical Responses path. Send start_within and do not send service_tier. max_tokens is required. */
+        /** Create a message. The fourth FlexInference caller format (Anthropic Messages shape in and out); works for any model via the canonical Responses path. Send start_within and do not send service_tier. Anthropic requires max_tokens upstream. FlexInference forwards it when set and does not synthesize a default, so omitting it returns Anthropic's own request error. */
         post: operations["createMessage"];
         delete?: never;
         options?: never;
@@ -5794,11 +5794,11 @@ export interface components {
         };
         /**
          * Message Create Params
-         * @description Request body for POST /v1/messages (Anthropic Messages shape). Works for any model via the canonical Responses path. max_tokens is required (Anthropic requires it and the router rejects a claude-* request that reaches the Anthropic upstream without a canonical max_output_tokens). Does not accept service_tier (the router owns the tier). start_within is required at runtime but left optional here.
+         * @description Request body for POST /v1/messages (Anthropic Messages shape). Works for any model via the canonical Responses path. Anthropic requires max_tokens upstream. FlexInference forwards it when set and does not synthesize a default, so omitting it returns Anthropic's own request error. Does not accept service_tier (the router owns the tier). start_within is required at runtime but left optional here.
          */
         MessageCreateParams: {
             model: string;
-            max_tokens: number;
+            max_tokens?: number;
             /** @description System prompt as a string or an array of text blocks. */
             system?: string | components["schemas"]["MessageTextBlock"][];
             messages: components["schemas"]["Message"][];
@@ -6136,7 +6136,7 @@ export interface operations {
                     "text/event-stream": components["schemas"]["MessageStreamEvent"];
                 };
             };
-            /** @description Bad request. A FlexInference-layer rejection (type flexinference_error, e.g. missing_start_within, invalid_start_within, model_not_flex_capable, flex_unsupported_for_anthropic, missing_max_tokens, service_tier_not_allowed) or an upstream provider rejection passed through unchanged. */
+            /** @description Bad request. A FlexInference-layer rejection (type flexinference_error, e.g. missing_start_within, invalid_start_within, model_not_flex_capable, flex_unsupported_for_anthropic, service_tier_not_allowed) or an upstream provider rejection passed through unchanged. */
             400: {
                 headers: {
                     [name: string]: unknown;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "flexinference",
-  "version": "1.5.2",
+  "version": "1.5.3",
   "description": "Official TypeScript SDK for FlexInference - a deadline-aware, OpenAI-compatible inference router.",
   "license": "MIT",
   "author": "Aditya Perswal <adityaperswal@gmail.com>",