@soat/cli 0.47.0 → 0.49.0

package/dist/index.mjs

@@ -13,7 +13,7 @@ import * as os from "node:os";
 import { createHmac, timingSafeEqual } from "node:crypto";
 
 //#region package.json
-var version = "0.47.0";
+var version = "0.49.0";
 
 //#endregion
 //#region src/cli-wrappers/wrappers/formations.ts
@@ -703,7 +703,7 @@ var routes = {
   "merge-actor-tags": {
     serviceClass: "Actors",
     operationId: "mergeActorTags",
-    description: "Merges provided tags with existing tags (existing tags are preserved unless overridden)",
+    description: "Merges provided tags into the actor's existing tags (existing tags are preserved unless overridden)",
     moduleDocsUrl: "https://soat.ttoss.dev/docs/modules/actors",
     httpMethod: "patch",
     pathParams: ["actor_id"],
@@ -854,6 +854,12 @@ var routes = {
       "required": false,
       "type": "object",
       "in": "body"
+    }, {
+      "name": "prompt_caching",
+      "description": "Prompt caching for this agent's turns. `{\"enabled\": true}` marks a cache breakpoint at the end of the turn's static prefix — the tool definitions and the instructions together — so a provider that caches by explicit breakpoint reads that prefix back on every later step of the turn and every later turn of the session instead of being charged for it again. Null or omitted is off: a cache write costs more than an uncached token, so an agent whose prefix is never re-read would pay for the privilege. An agent with no `instructions` has no block to mark and caches nothing. Cache reads are reported as `cached_tokens` and cache writes as `cache_write_tokens` on usage.",
+      "required": false,
+      "type": "object",
+      "in": "body"
     }, {
       "name": "max_context_messages",
       "description": "Maximum number of recent messages included in the context window. Null means no limit.",
@@ -1012,6 +1018,12 @@ var routes = {
       "required": false,
       "type": "object",
       "in": "body"
+    }, {
+      "name": "prompt_caching",
+      "description": "Prompt caching for this agent's turns. `{\"enabled\": true}` marks a cache breakpoint at the end of the turn's static prefix — the tool definitions and the instructions together — so a provider that caches by explicit breakpoint reads that prefix back on every later step of the turn and every later turn of the session instead of being charged for it again. Null or omitted is off: a cache write costs more than an uncached token, so an agent whose prefix is never re-read would pay for the privilege. An agent with no `instructions` has no block to mark and caches nothing. Cache reads are reported as `cached_tokens` and cache writes as `cache_write_tokens` on usage.",
+      "required": false,
+      "type": "object",
+      "in": "body"
     }, {
       "name": "max_context_messages",
       "description": "Maximum number of recent messages included in the context window. Null means no limit.",
@@ -1154,6 +1166,12 @@ var routes = {
       "required": false,
       "type": "object",
       "in": "body"
+    }, {
+      "name": "prompt_caching",
+      "description": "Prompt caching for this agent's turns. `{\"enabled\": true}` marks a cache breakpoint at the end of the turn's static prefix — the tool definitions and the instructions together — so a provider that caches by explicit breakpoint reads that prefix back on every later step of the turn and every later turn of the session instead of being charged for it again. Null or omitted is off: a cache write costs more than an uncached token, so an agent whose prefix is never re-read would pay for the privilege. An agent with no `instructions` has no block to mark and caches nothing. Cache reads are reported as `cached_tokens` and cache writes as `cache_write_tokens` on usage.",
+      "required": false,
+      "type": "object",
+      "in": "body"
     }, {
       "name": "max_context_messages",
       "description": "Maximum number of recent messages included in the context window. Null means no limit.",
@@ -2611,7 +2629,7 @@ var routes = {
   "merge-conversation-tags": {
     serviceClass: "Conversations",
     operationId: "mergeConversationTags",
-    description: "Merges provided tags with existing tags",
+    description: "Merges provided tags into the conversation's existing tags (existing tags are preserved unless overridden)",
     moduleDocsUrl: "https://soat.ttoss.dev/docs/modules/conversations",
     httpMethod: "patch",
     pathParams: ["conversation_id"],
@@ -2995,7 +3013,7 @@ var routes = {
   "merge-document-tags": {
     serviceClass: "Documents",
     operationId: "mergeDocumentTags",
-    description: "Merges provided tags with existing tags (existing tags are preserved unless overridden)",
+    description: "Merges provided tags into the document's existing tags (existing tags are preserved unless overridden)",
     moduleDocsUrl: "https://soat.ttoss.dev/docs/modules/documents",
     httpMethod: "patch",
     pathParams: ["document_id"],
@@ -4069,7 +4087,7 @@ var routes = {
   "merge-file-tags": {
     serviceClass: "Files",
     operationId: "mergeFileTags",
-    description: "Merges provided tags with existing tags",
+    description: "Merges provided tags into the file's existing tags (existing tags are preserved unless overridden)",
     moduleDocsUrl: "https://soat.ttoss.dev/docs/modules/files",
     httpMethod: "patch",
     pathParams: ["file_id"],
@@ -4949,7 +4967,7 @@ var routes = {
   "search-knowledge": {
     serviceClass: "Knowledge",
     operationId: "searchKnowledge",
-    description: "Searches across documents and memory entries using semantic search, file paths, document IDs, memory IDs, or tags. At least one of `query`, `tags`, `document_paths`, `document_ids`, or `memory_ids` must be provided.",
+    description: "Searches across documents and memory entries using hybrid retrieval — a vector query and a full-text query per source, fused by reciprocal rank — or by file paths, document IDs, memory IDs, or tags. At least one of `query`, `tags`, `document_paths`, `document_ids`, or `memory_ids` must be provided.",
     moduleDocsUrl: "https://soat.ttoss.dev/docs/modules/knowledge",
     httpMethod: "post",
     pathParams: [],
@@ -4962,13 +4980,31 @@ var routes = {
       "in": "body"
     }, {
       "name": "query",
-      "description": "Semantic search query text",
+      "description": "Search query text. Runs a vector query and a full-text query over each store and fuses the rankings; the full-text channel matches exact tokens and phrases, the vector channel everything else.",
       "required": false,
       "type": "string",
       "in": "body"
+    }, {
+      "name": "min_similarity",
+      "description": "Minimum raw cosine `similarity_score` a **vector** candidate must reach to take part in ranking, applied before fusion. Only applies when `query` is provided. Lexical candidates are deliberately exempt: a result that literally contains the searched token is the evidence, and dropping it for a low cosine is the failure hybrid search exists to prevent. Not a floor on `score`, whose fused value encodes rank position rather than similarity.",
+      "required": false,
+      "type": "number",
+      "in": "body"
     }, {
       "name": "min_score",
-      "description": "Minimum `score` a result must reach to be returned. Filters on the implementation-defined `score`, not on `similarity_score`, so the cutoff follows the ranking. Only applies when `query` is provided. Because the scale behind `score` is not part of the contract, treat a tuned value as tied to the deployment rather than portable.",
+      "description": "Deprecated alias for `min_similarity`, with identical behavior. While ranking was single-signal `score` equaled `similarity_score`, so this has only ever filtered cosine and an existing value keeps returning the same results. `min_similarity` wins when both are sent. Removed in v2.",
+      "required": false,
+      "type": "number",
+      "in": "body"
+    }, {
+      "name": "rrf_k",
+      "description": "The `k` in the reciprocal rank fusion term `1 / (k + rank)`, which sets how steeply a result's contribution decays with its position in each ranked list. A smaller value weights the very top of each list more heavily. Defaults to the deployment's `KNOWLEDGE_RRF_K`, itself 60 by default. Only applies when `query` is provided.",
+      "required": false,
+      "type": "integer",
+      "in": "body"
+    }, {
+      "name": "recency_half_life_days",
+      "description": "Half-life, in days, of a recency decay applied to **memory** results after fusion: a result's `score` is multiplied by `2 ^ (-age_in_days / recency_half_life_days)`, where age is measured from its `updated_at`. Document results are never decayed. `0` — the default, and the default of the deployment's `KNOWLEDGE_RECENCY_HALF_LIFE_DAYS` — disables the blend entirely; it is a switch, not a lower bound, and sending `0` turns off a deployment-wide decay for this one request. Accepts fractions (`0.5` is twelve hours). How many ranks a given half-life costs depends on `rrf_k`. Only applies when `query` is provided.",
       "required": false,
       "type": "number",
       "in": "body"
@@ -5173,7 +5209,7 @@ var routes = {
   "merge-memory-tags": {
     serviceClass: "Memories",
     operationId: "mergeMemoryTags",
-    description: "Merges provided tags with existing tags (existing tags are preserved unless overridden)",
+    description: "Merges provided tags into the memory's existing tags (existing tags are preserved unless overridden)",
     moduleDocsUrl: "https://soat.ttoss.dev/docs/modules/memories",
     httpMethod: "patch",
     pathParams: ["memory_id"],
@@ -5373,7 +5409,7 @@ var routes = {
   "merge-memory-entry-tags": {
     serviceClass: "MemoryEntries",
     operationId: "mergeMemoryEntryTags",
-    description: "Merges provided tags with existing tags (existing tags are preserved unless overridden)",
+    description: "Merges provided tags into the memory entry's existing tags (existing tags are preserved unless overridden)",
     moduleDocsUrl: "https://soat.ttoss.dev/docs/modules/memory-entries",
     httpMethod: "patch",
     pathParams: ["entry_id"],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@soat/cli",
-  "version": "0.47.0",
+  "version": "0.49.0",
   "description": "CLI for SOAT — open-source infrastructure for production-ready AI agents.",
   "keywords": [
     "ai-agents",
@@ -22,7 +22,7 @@
   "dependencies": {
     "@inquirer/input": "^5.1.2",
     "@inquirer/password": "^5.1.1",
-    "@soat/sdk": "0.47.0",
+    "@soat/sdk": "0.49.0",
     "@ttoss/logger": "^0.8.19",
     "commander": "^15.0.0",
     "js-yaml": "^5.2.1"