@rei-standard/amsg-shared 0.4.0-next.3 → 0.4.0-next.5

package/dist/index.cjs

@@ -264,7 +264,10 @@ async function callLlm(payload, options = {}) {
 }
 function buildLlmRequestBody(payload, options = {}) {
   const llmMessages = Array.isArray(payload.messages) && payload.messages.length > 0 ? payload.messages : [{ role: "user", content: payload.completePrompt }];
+  const extraBody = payload.llmExtraBody && typeof payload.llmExtraBody === "object" && !Array.isArray(payload.llmExtraBody) ? payload.llmExtraBody : null;
   const requestBody = {
+    // 先展开 extra body，核心字段随后写入（撞键时核心字段赢）。
+    ...extraBody || {},
     model: payload.primaryModel,
     messages: llmMessages
   };
@@ -511,7 +514,7 @@ async function verifyVapidJwt(jwt, publicKey) {
     utf8(`${h}.${p}`)
   );
   if (!ok) throw new Error("VAPID JWT: signature mismatch");
-  const payload = JSON.parse(new TextDecoder().decode(base64UrlToBytes(p)));
+  const payload = JSON.parse(utf8Decode(base64UrlToBytes(p)));
   if (!payload.exp || payload.exp <= Math.floor(Date.now() / 1e3)) {
     throw new Error("VAPID JWT: expired");
   }
@@ -836,12 +839,20 @@ function buildSessionContext({
   scratch
 }) {
   const llmOutputText = readLlmOutputText(llmResponse);
+  const usage = llmResponse && typeof llmResponse === "object" && /** @type {any} */
+  llmResponse.usage && typeof /** @type {any} */
+  llmResponse.usage === "object" ? (
+    /** @type {Record<string, unknown>} */
+    /** @type {any} */
+    llmResponse.usage
+  ) : null;
   const ctx = {
     sessionId,
     charId,
     messages,
     llmResponse,
     llmOutputText,
+    usage,
     iteration,
     metadata: metadata && typeof metadata === "object" ? metadata : {},
     contactName,

package/dist/index.d.cts

@@ -296,6 +296,7 @@ export function stripReasoningTags(content: string): string;
  * @property {ChatMessage[]}            messages       - Including the just-appended assistant turn.
  * @property {unknown}                  llmResponse    - Full LLM response (choices, usage, …).
  * @property {string}                   llmOutputText  - May be '' for pure tool-call responses.
+ * @property {Record<string, unknown>|null} usage      - `llmResponse.usage` 的直接引用（prompt/completion/total tokens）。响应没带 usage → null。llmResponse 里本来就有，单独提出来是让「记本轮用量」不必依赖响应对象的具体形状。
  * @property {number}                   iteration      - 0-indexed: the round that just finished.
  * @property {Record<string, unknown>}  metadata
  * @property {string}                   contactName
@@ -690,6 +691,10 @@ export type SessionContext = {
      * - May be '' for pure tool-call responses.
      */
     llmOutputText: string;
+    /**
+     * - `llmResponse.usage` 的直接引用（prompt/completion/total tokens）。响应没带 usage → null。llmResponse 里本来就有，单独提出来是让「记本轮用量」不必依赖响应对象的具体形状。
+     */
+    usage: Record<string, unknown> | null;
     /**
      * - 0-indexed: the round that just finished.
      */

package/dist/index.d.ts

@@ -296,6 +296,7 @@ export function stripReasoningTags(content: string): string;
  * @property {ChatMessage[]}            messages       - Including the just-appended assistant turn.
  * @property {unknown}                  llmResponse    - Full LLM response (choices, usage, …).
  * @property {string}                   llmOutputText  - May be '' for pure tool-call responses.
+ * @property {Record<string, unknown>|null} usage      - `llmResponse.usage` 的直接引用（prompt/completion/total tokens）。响应没带 usage → null。llmResponse 里本来就有，单独提出来是让「记本轮用量」不必依赖响应对象的具体形状。
  * @property {number}                   iteration      - 0-indexed: the round that just finished.
  * @property {Record<string, unknown>}  metadata
  * @property {string}                   contactName
@@ -690,6 +691,10 @@ export type SessionContext = {
      * - May be '' for pure tool-call responses.
      */
     llmOutputText: string;
+    /**
+     * - `llmResponse.usage` 的直接引用（prompt/completion/total tokens）。响应没带 usage → null。llmResponse 里本来就有，单独提出来是让「记本轮用量」不必依赖响应对象的具体形状。
+     */
+    usage: Record<string, unknown> | null;
     /**
      * - 0-indexed: the round that just finished.
      */

package/dist/index.mjs

@@ -186,7 +186,10 @@ async function callLlm(payload, options = {}) {
 }
 function buildLlmRequestBody(payload, options = {}) {
   const llmMessages = Array.isArray(payload.messages) && payload.messages.length > 0 ? payload.messages : [{ role: "user", content: payload.completePrompt }];
+  const extraBody = payload.llmExtraBody && typeof payload.llmExtraBody === "object" && !Array.isArray(payload.llmExtraBody) ? payload.llmExtraBody : null;
   const requestBody = {
+    // 先展开 extra body，核心字段随后写入（撞键时核心字段赢）。
+    ...extraBody || {},
     model: payload.primaryModel,
     messages: llmMessages
   };
@@ -433,7 +436,7 @@ async function verifyVapidJwt(jwt, publicKey) {
     utf8(`${h}.${p}`)
   );
   if (!ok) throw new Error("VAPID JWT: signature mismatch");
-  const payload = JSON.parse(new TextDecoder().decode(base64UrlToBytes(p)));
+  const payload = JSON.parse(utf8Decode(base64UrlToBytes(p)));
   if (!payload.exp || payload.exp <= Math.floor(Date.now() / 1e3)) {
     throw new Error("VAPID JWT: expired");
   }
@@ -758,12 +761,20 @@ function buildSessionContext({
   scratch
 }) {
   const llmOutputText = readLlmOutputText(llmResponse);
+  const usage = llmResponse && typeof llmResponse === "object" && /** @type {any} */
+  llmResponse.usage && typeof /** @type {any} */
+  llmResponse.usage === "object" ? (
+    /** @type {Record<string, unknown>} */
+    /** @type {any} */
+    llmResponse.usage
+  ) : null;
   const ctx = {
     sessionId,
     charId,
     messages,
     llmResponse,
     llmOutputText,
+    usage,
     iteration,
     metadata: metadata && typeof metadata === "object" ? metadata : {},
     contactName,

package/dist/llm-call.d.cts

@@ -79,6 +79,11 @@ export function callLlm(payload: any, options?: {
  * non-empty payload.tools. An empty array is treated as "no tools"
  * because some OpenAI-compatible relays reject `tools: []`.
  *
+ * `payload.llmExtraBody`（可选，普通对象）：原样展开进请求体，给上游中转的
+ * 非标准参数用（thinking / reasoning_effort 之类库不认识也不该认识的字段）。
+ * 先展开它、再写核心字段——model / messages / temperature / max_tokens /
+ * tools 永远以库的口径为准，extra body 撞了这些键也盖不掉。
+ *
  * @param {Object} payload
  * @param {{ stream?: boolean, forwardTools?: boolean }} [options]
  *   stream — set to include an explicit `stream` field in the body

package/dist/llm-call.d.ts

@@ -79,6 +79,11 @@ export function callLlm(payload: any, options?: {
  * non-empty payload.tools. An empty array is treated as "no tools"
  * because some OpenAI-compatible relays reject `tools: []`.
  *
+ * `payload.llmExtraBody`（可选，普通对象）：原样展开进请求体，给上游中转的
+ * 非标准参数用（thinking / reasoning_effort 之类库不认识也不该认识的字段）。
+ * 先展开它、再写核心字段——model / messages / temperature / max_tokens /
+ * tools 永远以库的口径为准，extra body 撞了这些键也盖不掉。
+ *
  * @param {Object} payload
  * @param {{ stream?: boolean, forwardTools?: boolean }} [options]
  *   stream — set to include an explicit `stream` field in the body

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@rei-standard/amsg-shared",
-  "version": "0.4.0-next.3",
+  "version": "0.4.0-next.5",
   "description": "ReiStandard Active Messaging shared types and push builders — the lowest layer (no deps on other amsg packages)",
   "repository": {
     "type": "git",