clawmem 0.10.1 → 0.10.2

package/README.md

@@ -332,6 +332,7 @@ If your GPU lives on a separate machine, point the env vars at it:
 ```bash
 export CLAWMEM_EMBED_URL=http://gpu-host:8088
 export CLAWMEM_LLM_URL=http://gpu-host:8089
+export CLAWMEM_LLM_MODEL=qwen3
 export CLAWMEM_RERANK_URL=http://gpu-host:8090
 ```
 
@@ -944,6 +945,9 @@ Notes referenced by the agent during a session get boosted (`access_count++`). U
 | `CLAWMEM_EMBED_TPM_LIMIT` | `100000` | Tokens-per-minute limit for cloud embedding pacing. Match to your provider tier. |
 | `CLAWMEM_EMBED_DIMENSIONS` | (none) | Output dimensions for OpenAI `text-embedding-3-*` Matryoshka models (e.g. `512`, `1024`). |
 | `CLAWMEM_LLM_URL` | `http://localhost:8089` | LLM server URL for intent/query/A-MEM. Without it, falls to `node-llama-cpp` (if allowed). |
+| `CLAWMEM_LLM_MODEL` | `qwen3` | Model name sent to the configured LLM endpoint. Override this for OpenAI-compatible proxies such as `gpt-5.4-mini`. |
+| `CLAWMEM_LLM_REASONING_EFFORT` | (none) | Optional top-level `reasoning_effort` field for Chat Completions endpoints that support it (for example OpenAI reasoning models). Leave unset for llama-server/vLLM unless your serving stack explicitly accepts that field. |
+| `CLAWMEM_LLM_NO_THINK` | `true` | Append `/no_think` to remote LLM prompts. Set to `false` for standard OpenAI models and other endpoints that reject or treat the Qwen-style suffix as literal prompt text. |
 | `CLAWMEM_RERANK_URL` | `http://localhost:8090` | Reranker server URL. Without it, falls to `node-llama-cpp` (if allowed). |
 | `CLAWMEM_NO_LOCAL_MODELS` | `false` | Block `node-llama-cpp` from auto-downloading GGUF models. Set `true` for remote-only setups where you want fail-fast on unreachable endpoints. |
 | `CLAWMEM_MERGE_SCORE_NORMAL` | `0.93` | **v0.7.1.** Phase 2 consolidation merge-safety threshold when candidate and existing anchors align. Merges above this normalized 3-gram cosine score are allowed. |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "clawmem",
-  "version": "0.10.1",
+  "version": "0.10.2",
   "description": "On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.",
   "type": "module",
   "bin": {

package/src/clawmem.ts

@@ -1491,6 +1491,7 @@ async function cmdSetupOpenClaw(args: string[]) {
   console.log(`  3. Configure GPU endpoints (if not using defaults):`);
   console.log(`     ${c.cyan}openclaw config set plugins.entries.clawmem.config.gpuEmbed http://YOUR_GPU:8088${c.reset}`);
   console.log(`     ${c.cyan}openclaw config set plugins.entries.clawmem.config.gpuLlm http://YOUR_GPU:8089${c.reset}`);
+  console.log(`     ${c.cyan}openclaw config set plugins.entries.clawmem.config.gpuLlmModel qwen3${c.reset}`);
   console.log(`     ${c.cyan}openclaw config set plugins.entries.clawmem.config.gpuRerank http://YOUR_GPU:8090${c.reset}`);
   console.log();
   console.log(`  4. Start the REST API (for agent tools):`);

package/src/hermes/__init__.py

@@ -15,6 +15,9 @@ Config via environment variables:
   CLAWMEM_PROFILE       — Retrieval profile: speed, balanced, deep (default: balanced)
   CLAWMEM_EMBED_URL     — GPU embedding server URL (optional)
   CLAWMEM_LLM_URL       — GPU LLM server URL (optional)
+  CLAWMEM_LLM_MODEL     — Model name sent to the GPU/cloud LLM endpoint (optional)
+  CLAWMEM_LLM_REASONING_EFFORT — Top-level reasoning_effort for supporting Chat Completions endpoints (optional)
+  CLAWMEM_LLM_NO_THINK  — Append /no_think to remote prompts; false disables it for standard OpenAI models (optional)
   CLAWMEM_RERANK_URL    — GPU reranker server URL (optional)
 
 Agent-context isolation:
@@ -295,6 +298,24 @@ class ClawMemProvider(MemoryProvider):
                 "secret": False,
                 "env_var": "CLAWMEM_LLM_URL",
             },
+            {
+                "key": "llm_model",
+                "description": "Model name sent to the GPU LLM server (e.g., qwen3, gpt-5.4-mini)",
+                "secret": False,
+                "env_var": "CLAWMEM_LLM_MODEL",
+            },
+            {
+                "key": "llm_reasoning_effort",
+                "description": "Optional top-level reasoning_effort for Chat Completions endpoints that support it",
+                "secret": False,
+                "env_var": "CLAWMEM_LLM_REASONING_EFFORT",
+            },
+            {
+                "key": "llm_no_think",
+                "description": "Append /no_think to remote LLM prompts; disable for standard OpenAI models",
+                "secret": False,
+                "env_var": "CLAWMEM_LLM_NO_THINK",
+            },
         ]
 
     # -- Core lifecycle --------------------------------------------------------
@@ -324,7 +345,15 @@ class ClawMemProvider(MemoryProvider):
             )
 
         # Build env for hook shell-outs (GPU endpoints, profile)
-        for var in ("CLAWMEM_EMBED_URL", "CLAWMEM_LLM_URL", "CLAWMEM_RERANK_URL", "CLAWMEM_PROFILE"):
+        for var in (
+            "CLAWMEM_EMBED_URL",
+            "CLAWMEM_LLM_URL",
+            "CLAWMEM_LLM_MODEL",
+            "CLAWMEM_LLM_REASONING_EFFORT",
+            "CLAWMEM_LLM_NO_THINK",
+            "CLAWMEM_RERANK_URL",
+            "CLAWMEM_PROFILE",
+        ):
             val = os.environ.get(var)
             if val:
                 self._env_extra[var] = val

package/src/llm.ts

@@ -237,6 +237,23 @@ export type LlamaCppConfig = {
    * When set, generate() calls /v1/chat/completions instead of local node-llama-cpp.
    */
   remoteLlmUrl?: string;
+  /**
+   * Remote LLM model name to send with chat completion requests.
+   * Env: CLAWMEM_LLM_MODEL
+   */
+  remoteLlmModel?: string;
+  /**
+   * Optional top-level reasoning_effort field for Chat Completions endpoints that support it.
+   * Example values: none, minimal, low, medium, high, xhigh.
+   * Env: CLAWMEM_LLM_REASONING_EFFORT
+   */
+  remoteLlmReasoningEffort?: string;
+  /**
+   * Whether to append /no_think to remote LLM prompts.
+   * Defaults to true to preserve current behavior with Qwen3-compatible endpoints.
+   * Env: CLAWMEM_LLM_NO_THINK
+   */
+  remoteLlmNoThink?: boolean;
   /**
    * Inactivity timeout in ms before unloading contexts (default: 2 minutes, 0 to disable).
    *
@@ -259,6 +276,23 @@ export type LlamaCppConfig = {
  */
 // Default inactivity timeout: 2 minutes
 const DEFAULT_INACTIVITY_TIMEOUT_MS = 2 * 60 * 1000;
+const ALLOWED_REMOTE_LLM_REASONING_EFFORTS = new Set(["none", "minimal", "low", "medium", "high", "xhigh"]);
+
+function normalizeRemoteLlmReasoningEffort(value?: string): string | null {
+  const raw = (value || "").trim().toLowerCase();
+  if (!raw) return null;
+  if (!ALLOWED_REMOTE_LLM_REASONING_EFFORTS.has(raw)) {
+    console.warn(`[clawmem] Ignoring unsupported remoteLlmReasoningEffort=${raw}`);
+    return null;
+  }
+  return raw;
+}
+
+function buildRemoteChatCompletionsUrl(remoteLlmUrl: string): string {
+  const baseUrl = remoteLlmUrl.replace(/\/+$/, "");
+  const endpoint = baseUrl.endsWith("/v1") ? "/chat/completions" : "/v1/chat/completions";
+  return `${baseUrl}${endpoint}`;
+}
 
 export class LlamaCpp implements LLM {
   private llama: Llama | null = null;
@@ -276,6 +310,9 @@ export class LlamaCpp implements LLM {
   private remoteEmbedApiKey: string | null;
   private remoteEmbedModel: string;
   private remoteLlmUrl: string | null;
+  private remoteLlmModel: string;
+  private remoteLlmReasoningEffort: string | null;
+  private remoteLlmNoThink: boolean;
 
   // Ensure we don't load the same model concurrently (which can allocate duplicate VRAM).
   private embedModelLoadPromise: Promise<LlamaModel> | null = null;
@@ -306,6 +343,10 @@ export class LlamaCpp implements LLM {
     this.remoteEmbedApiKey = config.remoteEmbedApiKey || null;
     this.remoteEmbedModel = config.remoteEmbedModel || "embedding";
     this.remoteLlmUrl = config.remoteLlmUrl || null;
+    const normalizedRemoteLlmModel = config.remoteLlmModel?.trim();
+    this.remoteLlmModel = normalizedRemoteLlmModel || "qwen3";
+    this.remoteLlmReasoningEffort = normalizeRemoteLlmReasoningEffort(config.remoteLlmReasoningEffort);
+    this.remoteLlmNoThink = config.remoteLlmNoThink ?? true;
     this.inactivityTimeoutMs = config.inactivityTimeoutMs ?? DEFAULT_INACTIVITY_TIMEOUT_MS;
     this.disposeModelsOnInactivity = config.disposeModelsOnInactivity ?? false;
   }
@@ -921,15 +962,19 @@ export class LlamaCpp implements LLM {
     // Re-check: concurrent call may have set cooldown while we were awaited
     if (this.isRemoteLlmDown()) return null;
     try {
-      const resp = await fetch(`${this.remoteLlmUrl}/v1/chat/completions`, {
+      const body: Record<string, unknown> = {
+        model: this.remoteLlmModel,
+        messages: [{ role: "user", content: this.remoteLlmNoThink ? `${prompt} /no_think` : prompt }],
+        max_tokens: maxTokens,
+        temperature,
+      };
+      if (this.remoteLlmReasoningEffort) {
+        body.reasoning_effort = this.remoteLlmReasoningEffort;
+      }
+      const resp = await fetch(buildRemoteChatCompletionsUrl(this.remoteLlmUrl!), {
         method: "POST",
         headers: { "Content-Type": "application/json" },
-        body: JSON.stringify({
-          model: "qwen3",
-          messages: [{ role: "user", content: `${prompt} /no_think` }],
-          max_tokens: maxTokens,
-          temperature,
-        }),
+        body: JSON.stringify(body),
         signal,
       });
 
@@ -1254,6 +1299,13 @@ export function getDefaultLlamaCpp(): LlamaCpp {
       remoteEmbedApiKey: embedApiKey,
       remoteEmbedModel: process.env.CLAWMEM_EMBED_MODEL || undefined,
       remoteLlmUrl: process.env.CLAWMEM_LLM_URL || undefined,
+      remoteLlmModel: process.env.CLAWMEM_LLM_MODEL?.trim() || undefined,
+      remoteLlmReasoningEffort: process.env.CLAWMEM_LLM_REASONING_EFFORT || undefined,
+      remoteLlmNoThink: (() => {
+        const raw = (process.env.CLAWMEM_LLM_NO_THINK || "").trim().toLowerCase();
+        if (!raw) return undefined;
+        return !["0", "false", "no", "off"].includes(raw);
+      })(),
     });
   }
   return defaultLlamaCpp;
@@ -1276,4 +1328,3 @@ export async function disposeDefaultLlamaCpp(): Promise<void> {
     defaultLlamaCpp = null;
   }
 }
-

package/src/openclaw/index.ts

@@ -37,8 +37,8 @@
  *   4. REST API service (`clawmem serve`) lifecycle — unchanged.
  *
  * §14.3 critical correctness contract: `agent_end` is fire-and-forget at
- * `attempt.ts:2198-2224`. Precompact-extract MUST run inside
- * `handleBeforePromptBuild` (which IS awaited at `attempt.ts:1642`), gated
+ * `attempt.ts:2470-2496`. Precompact-extract MUST run inside
+ * `handleBeforePromptBuild` (which IS awaited at `attempt.ts:1873`), gated
  * by the proximity heuristic in `compaction-threshold.ts`. See `engine.ts`
  * top-of-file comment for the full rationale.
  */
@@ -107,6 +107,13 @@ const clawmemPlugin = {
       env: {
         ...(pluginCfg.gpuEmbed ? { CLAWMEM_EMBED_URL: pluginCfg.gpuEmbed as string } : {}),
         ...(pluginCfg.gpuLlm ? { CLAWMEM_LLM_URL: pluginCfg.gpuLlm as string } : {}),
+        ...(pluginCfg.gpuLlmModel ? { CLAWMEM_LLM_MODEL: pluginCfg.gpuLlmModel as string } : {}),
+        ...(pluginCfg.gpuLlmReasoningEffort
+          ? { CLAWMEM_LLM_REASONING_EFFORT: pluginCfg.gpuLlmReasoningEffort as string }
+          : {}),
+        ...(pluginCfg.gpuLlmNoThink !== undefined
+          ? { CLAWMEM_LLM_NO_THINK: String(pluginCfg.gpuLlmNoThink) }
+          : {}),
         ...(pluginCfg.gpuRerank ? { CLAWMEM_RERANK_URL: pluginCfg.gpuRerank as string } : {}),
         CLAWMEM_PROFILE: profile,
       },
@@ -154,7 +161,7 @@ const clawmemPlugin = {
     // ----- Plugin Hook: before_prompt_build (AWAITED — load-bearing path) -----
     // Both context-surfacing retrieval injection and pre-emptive precompact
     // extraction live here. handleBeforePromptBuild is async and the OpenClaw
-    // attempt path awaits the result at attempt.ts:1642 before building the
+    // attempt path awaits the result at attempt.ts:1873 before building the
     // effective prompt. precompact-extract therefore runs strictly before
     // the LLM call that could trigger compaction on this turn.
     api.on(
@@ -168,7 +175,7 @@ const clawmemPlugin = {
     // ----- Plugin Hook: agent_end (FIRE-AND-FORGET in core) -----
     // Decision-extractor, handoff-generator, and feedback-loop run here.
     // These writes are eventually-consistent (saveMemory dedupes), so the
-    // fire-and-forget context at attempt.ts:2198-2224 is acceptable.
+    // fire-and-forget context at attempt.ts:2470-2496 is acceptable.
     // precompact-extract is intentionally NOT in this handler — it lives
     // in handleBeforePromptBuild for correctness reasons.
     api.on("agent_end", async (event: AgentEndEvent, ctx: AgentEndContext) => {

package/src/openclaw/openclaw.plugin.json

@@ -41,6 +41,23 @@
       "help": "URL for ClawMem LLM (query expansion, extraction)",
       "advanced": true
     },
+    "gpuLlmModel": {
+      "label": "LLM Model",
+      "placeholder": "qwen3",
+      "help": "Model name sent to the configured LLM endpoint",
+      "advanced": true
+    },
+    "gpuLlmReasoningEffort": {
+      "label": "Reasoning Effort",
+      "placeholder": "(unset)",
+      "help": "Optional top-level reasoning_effort for Chat Completions endpoints that support it. Unset omits the field.",
+      "advanced": true
+    },
+    "gpuLlmNoThink": {
+      "label": "Append /no_think",
+      "help": "Append /no_think to remote LLM prompts (default: true). Disable for standard OpenAI models.",
+      "advanced": true
+    },
     "gpuRerank": {
       "label": "Reranker Endpoint",
       "placeholder": "http://localhost:8090",
@@ -78,6 +95,16 @@
       "gpuLlm": {
         "type": "string"
       },
+      "gpuLlmModel": {
+        "type": "string"
+      },
+      "gpuLlmReasoningEffort": {
+        "type": "string",
+        "enum": ["none", "minimal", "low", "medium", "high", "xhigh"]
+      },
+      "gpuLlmNoThink": {
+        "type": "boolean"
+      },
       "gpuRerank": {
         "type": "string"
       }

package/src/openclaw/package.json

@@ -1,6 +1,6 @@
 {
   "name": "clawmem-openclaw-plugin",
-  "version": "0.10.1",
+  "version": "0.10.2",
   "description": "OpenClaw plugin adapter for ClawMem — on-device hybrid memory layer",
   "type": "module",
   "openclaw": {