Merge remote-tracking branch 'origin/main'

CHANGELOG.md

@@ -132,6 +132,7 @@ Docs: https://docs.openclaw.ai
 - Telegram: scope skill commands to the resolved agent for default accounts so `setMyCommands` no longer triggers `BOT_COMMANDS_TOO_MUCH` when multiple agents are configured. (#15599)
 - Discord: avoid misrouting numeric guild allowlist entries to `/channels/<guildId>` by prefixing guild-only inputs with `guild:` during resolution. (#12326) Thanks @headswim.
 - Memory/QMD: default `memory.qmd.searchMode` to `search` for faster CPU-only recall and always scope `search`/`vsearch` requests to managed collections (auto-falling back to `query` when required). (#16047) Thanks @togotago.
+- Memory/LanceDB: add configurable `captureMaxChars` for auto-capture while keeping the legacy 500-char default. (#16641) Thanks @ciberponk.
 - MS Teams: preserve parsed mention entities/text when appending OneDrive fallback file links, and accept broader real-world Teams mention ID formats (`29:...`, `8:orgid:...`) while still rejecting placeholder patterns. (#15436) Thanks @hyojin.
 - Media: classify `text/*` MIME types as documents in media-kind routing so text attachments are no longer treated as unknown. (#12237) Thanks @arosstale.
 - Inbound/Web UI: preserve literal `\n` sequences when normalizing inbound text so Windows paths like `C:\\Work\\nxxx\\README.md` are not corrupted. (#11547) Thanks @mcaxtr.

extensions/memory-lancedb/config.ts

@@ -11,12 +11,14 @@ export type MemoryConfig = {
   dbPath?: string;
   autoCapture?: boolean;
   autoRecall?: boolean;
+  captureMaxChars?: number;
 };
 
 export const MEMORY_CATEGORIES = ["preference", "fact", "decision", "entity", "other"] as const;
 export type MemoryCategory = (typeof MEMORY_CATEGORIES)[number];
 
 const DEFAULT_MODEL = "text-embedding-3-small";
+export const DEFAULT_CAPTURE_MAX_CHARS = 500;
 const LEGACY_STATE_DIRS: string[] = [];
 
 function resolveDefaultDbPath(): string {
@@ -89,7 +91,11 @@ export const memoryConfigSchema = {
       throw new Error("memory config required");
     }
     const cfg = value as Record<string, unknown>;
-    assertAllowedKeys(cfg, ["embedding", "dbPath", "autoCapture", "autoRecall"], "memory config");
+    assertAllowedKeys(
+      cfg,
+      ["embedding", "dbPath", "autoCapture", "autoRecall", "captureMaxChars"],
+      "memory config",
+    );
 
     const embedding = cfg.embedding as Record<string, unknown> | undefined;
     if (!embedding || typeof embedding.apiKey !== "string") {
@@ -99,6 +105,15 @@ export const memoryConfigSchema = {
 
     const model = resolveEmbeddingModel(embedding);
 
+    const captureMaxChars =
+      typeof cfg.captureMaxChars === "number" ? Math.floor(cfg.captureMaxChars) : undefined;
+    if (
+      typeof captureMaxChars === "number" &&
+      (captureMaxChars < 100 || captureMaxChars > 10_000)
+    ) {
+      throw new Error("captureMaxChars must be between 100 and 10000");
+    }
+
     return {
       embedding: {
         provider: "openai",
@@ -108,6 +123,7 @@ export const memoryConfigSchema = {
       dbPath: typeof cfg.dbPath === "string" ? cfg.dbPath : DEFAULT_DB_PATH,
       autoCapture: cfg.autoCapture !== false,
       autoRecall: cfg.autoRecall !== false,
+      captureMaxChars: captureMaxChars ?? DEFAULT_CAPTURE_MAX_CHARS,
     };
   },
   uiHints: {
@@ -135,5 +151,11 @@ export const memoryConfigSchema = {
       label: "Auto-Recall",
       help: "Automatically inject relevant memories into context",
     },
+    captureMaxChars: {
+      label: "Capture Max Chars",
+      help: "Maximum message length eligible for auto-capture",
+      advanced: true,
+      placeholder: String(DEFAULT_CAPTURE_MAX_CHARS),
+    },
   },
 };

extensions/memory-lancedb/index.test.ts

@@ -61,6 +61,7 @@ describe("memory plugin e2e", () => {
     expect(config).toBeDefined();
     expect(config?.embedding?.apiKey).toBe(OPENAI_API_KEY);
     expect(config?.dbPath).toBe(dbPath);
+    expect(config?.captureMaxChars).toBe(500);
   });
 
   test("config schema resolves env vars", async () => {
@@ -92,6 +93,33 @@ describe("memory plugin e2e", () => {
     }).toThrow("embedding.apiKey is required");
   });
 
+  test("config schema validates captureMaxChars range", async () => {
+    const { default: memoryPlugin } = await import("./index.js");
+
+    expect(() => {
+      memoryPlugin.configSchema?.parse?.({
+        embedding: { apiKey: OPENAI_API_KEY },
+        dbPath,
+        captureMaxChars: 99,
+      });
+    }).toThrow("captureMaxChars must be between 100 and 10000");
+  });
+
+  test("config schema accepts captureMaxChars override", async () => {
+    const { default: memoryPlugin } = await import("./index.js");
+
+    const config = memoryPlugin.configSchema?.parse?.({
+      embedding: {
+        apiKey: OPENAI_API_KEY,
+        model: "text-embedding-3-small",
+      },
+      dbPath,
+      captureMaxChars: 1800,
+    });
+
+    expect(config?.captureMaxChars).toBe(1800);
+  });
+
   test("shouldCapture applies real capture rules", async () => {
     const { shouldCapture } = await import("./index.js");
 
@@ -104,6 +132,14 @@ describe("memory plugin e2e", () => {
     expect(shouldCapture("<relevant-memories>injected</relevant-memories>")).toBe(false);
     expect(shouldCapture("<system>status</system>")).toBe(false);
     expect(shouldCapture("Here is a short **summary**\n- bullet")).toBe(false);
+    const defaultAllowed = `I always prefer this style. ${"x".repeat(400)}`;
+    const defaultTooLong = `I always prefer this style. ${"x".repeat(600)}`;
+    expect(shouldCapture(defaultAllowed)).toBe(true);
+    expect(shouldCapture(defaultTooLong)).toBe(false);
+    const customAllowed = `I always prefer this style. ${"x".repeat(1200)}`;
+    const customTooLong = `I always prefer this style. ${"x".repeat(1600)}`;
+    expect(shouldCapture(customAllowed, { maxChars: 1500 })).toBe(true);
+    expect(shouldCapture(customTooLong, { maxChars: 1500 })).toBe(false);
   });
 
   test("detectCategory classifies using production logic", async () => {

extensions/memory-lancedb/index.ts

@@ -12,6 +12,7 @@ import { Type } from "@sinclair/typebox";
 import { randomUUID } from "node:crypto";
 import OpenAI from "openai";
 import {
+  DEFAULT_CAPTURE_MAX_CHARS,
   MEMORY_CATEGORIES,
   type MemoryCategory,
   memoryConfigSchema,
@@ -194,8 +195,9 @@ const MEMORY_TRIGGERS = [
   /always|never|important/i,
 ];
 
-export function shouldCapture(text: string): boolean {
+export function shouldCapture(text: string, options?: { maxChars?: number }): boolean {
-  if (text.length < 10 || text.length > 500) {
+  const maxChars = options?.maxChars ?? DEFAULT_CAPTURE_MAX_CHARS;
+  if (text.length < 10 || text.length > maxChars) {
     return false;
   }
   // Skip injected context from memory recall
@@ -570,7 +572,9 @@ const memoryPlugin = {
           }
 
           // Filter for capturable content
-          const toCapture = texts.filter((text) => text && shouldCapture(text));
+          const toCapture = texts.filter(
+            (text) => text && shouldCapture(text, { maxChars: cfg.captureMaxChars }),
+          );
           if (toCapture.length === 0) {
             return;
           }

extensions/memory-lancedb/openclaw.plugin.json

@@ -25,6 +25,12 @@
     "autoRecall": {
       "label": "Auto-Recall",
       "help": "Automatically inject relevant memories into context"
+    },
+    "captureMaxChars": {
+      "label": "Capture Max Chars",
+      "help": "Maximum message length eligible for auto-capture",
+      "advanced": true,
+      "placeholder": "500"
     }
   },
   "configSchema": {
@@ -53,6 +59,11 @@
       },
       "autoRecall": {
         "type": "boolean"
+      },
+      "captureMaxChars": {
+        "type": "number",
+        "minimum": 100,
+        "maximum": 10000
       }
     },
     "required": ["embedding"]