@agentmemory/agentmemory 0.9.16 → 0.9.18

package/.env.example

@@ -45,6 +45,12 @@
 
 # MAX_TOKENS=4096                                # Cap LLM completion tokens for compression / summarise calls
 
+# Outbound LLM / embedding timeout — shared across every raw-fetch provider
+# (Gemini, OpenRouter, MiniMax, OpenAI LLM, and OpenAI/Cohere/Voyage/OpenRouter
+# embedding). The OpenAI LLM path also honours the OpenAI-scoped
+# OPENAI_TIMEOUT_MS alias for back-compat with v0.9.17 (precedence).
+# AGENTMEMORY_LLM_TIMEOUT_MS=60000                # Default: 60 000 ms (60 s)
+
 # Opt-in Claude-subscription fallback (spawns @anthropic-ai/claude-agent-sdk
 # child sessions). Off by default — the agent-sdk fallback can trigger
 # Stop-hook recursion (#149 follow-up) when invoked from inside Claude Code.

package/AGENTS.md

@@ -104,16 +104,16 @@ Hook scripts in `src/hooks/` are standalone Node.js scripts (no iii-sdk import).
 
 ## Testing
 
-- All tests must pass before PR: `npm test` (699+ tests)
+- All tests must pass before PR: `npm test` (950+ tests)
 - Mock pattern: `vi.mock("iii-sdk")` with mock `sdk.trigger`, `kv.get/set/list`
 - Test files go in `test/` with `.test.ts` extension
 - Follow existing patterns in `test/crystallize.test.ts` for function tests
 
-## Current Stats (v0.8.9)
+## Current Stats (v0.9.16)
 
-- 44 MCP tools (8 visible by default, `AGENTMEMORY_TOOLS=all` for all)
-- 104 REST endpoints
+- 51 MCP tools (8 visible by default, `AGENTMEMORY_TOOLS=all` for all)
+- 121 REST endpoints
 - 6 MCP resources, 3 MCP prompts
 - 12 hooks, 4 skills
 - 50+ iii functions
-- 699 tests
+- 950+ tests

package/README.md

@@ -45,7 +45,7 @@
   <picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/stat-tools.svg"><img src="assets/tags/stat-tools.svg" alt="51 MCP tools" height="38" /></picture>
   <picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/stat-hooks.svg"><img src="assets/tags/stat-hooks.svg" alt="12 auto hooks" height="38" /></picture>
   <picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/stat-deps.svg"><img src="assets/tags/stat-deps.svg" alt="0 external DBs" height="38" /></picture>
-  <picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/stat-tests.svg"><img src="assets/tags/stat-tests.svg" alt="827 tests passing" height="38" /></picture>
+  <picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/stat-tests.svg"><img src="assets/tags/stat-tests.svg" alt="950+ tests passing" height="38" /></picture>
 </p>
 
 <p align="center">
@@ -777,7 +777,7 @@ npm install @xenova/transformers
 
 > **MCP shim vs full server:** the published `@agentmemory/mcp` package is a thin shim. It exposes the full 51-tool surface **only when it can reach a running agentmemory server** via `AGENTMEMORY_URL` (proxy mode). With no server reachable, the shim falls back to a 7-tool local set (`memory_save`, `memory_recall`, `memory_smart_search`, `memory_sessions`, `memory_export`, `memory_audit`, `memory_governance_delete`). The `AGENTMEMORY_TOOLS=core|all` env var is a *server-side* flag — setting it in the shim's `env` block has no effect. If you see only 7 tools in Cursor / OpenCode / Gemini CLI, start `npx @agentmemory/agentmemory` (or the Docker stack) and set `AGENTMEMORY_URL=http://localhost:3111`.
 
-### 50 Tools
+### 51 Tools
 
 <details>
 <summary>Core tools (always available)</summary>
@@ -799,7 +799,7 @@ npm install @xenova/transformers
 </details>
 
 <details>
-<summary>Extended tools (50 total — set AGENTMEMORY_TOOLS=all)</summary>
+<summary>Extended tools (51 total — set AGENTMEMORY_TOOLS=all)</summary>
 
 | Tool | Description |
 |------|-------------|
@@ -1017,7 +1017,7 @@ Full registry: [workers.iii.dev](https://workers.iii.dev). Every worker there co
 | Prometheus / Grafana | iii OTEL + health monitor |
 | Custom plugin systems | `iii worker add <name>` |
 
-**118 source files · ~21,800 LOC · 800 tests · 123 functions · 34 KV scopes** — all on three primitives. No `agentmemory plugin install`. The plugin system is iii itself.
+**118 source files · ~21,800 LOC · 950+ tests · 123 functions · 34 KV scopes** — all on three primitives. No `agentmemory plugin install`. The plugin system is iii itself.
 
 ---
 
@@ -1047,6 +1047,30 @@ Create `~/.agentmemory/.env`:
 # GEMINI_API_KEY=...
 # OPENROUTER_API_KEY=...
 # MINIMAX_API_KEY=...
+# OPENAI_API_KEY=***                       # NOTE: this same key auto-activates BOTH the
+#                                          # OpenAI LLM provider (here) AND the OpenAI
+#                                          # embedding provider (further below). Set
+#                                          # OPENAI_API_KEY_FOR_LLM=false to scope it
+#                                          # to embeddings only.
+# OPENAI_BASE_URL=https://api.openai.com   # Optional: override for Azure / vLLM / LM Studio / proxies
+#                                          # Azure: https://<resource>.openai.azure.com/openai/deployments/<deployment>
+#                                          # Auto-detected from `.openai.azure.com` hostname; uses
+#                                          # api-key header + api-version query param.
+# OPENAI_API_VERSION=2024-08-01-preview    # Optional: Azure api-version query param
+# OPENAI_MODEL=gpt-4o-mini                 # Optional: default model
+# OPENAI_TIMEOUT_MS=60000                  # Optional: OpenAI-scoped alias for the outbound fetch
+#                                          # timeout. Takes precedence over AGENTMEMORY_LLM_TIMEOUT_MS
+#                                          # for back-compat with v0.9.17. New configs should
+#                                          # prefer the global AGENTMEMORY_LLM_TIMEOUT_MS below.
+# OPENAI_REASONING_EFFORT=none             # Optional: "low" | "medium" | "high" | "none"
+#                                          # Honored only by OpenAI's reasoning models (o1, o3,
+#                                          # gpt-*-reasoning) and providers that mirror that
+#                                          # schema (Ollama Cloud thinking models). Standard
+#                                          # chat models reject this field with 400. Set to
+#                                          # "none" for thinking models that return reasoning
+#                                          # but no content.
+# OPENAI_API_KEY_FOR_LLM=false             # Optional: set to false to skip OpenAI auto-detection
+#                                          # for LLM (useful if you only want OpenAI for embeddings)
 # Opt-in Claude-subscription fallback (spawns @anthropic-ai/claude-agent-sdk);
 # leave OFF unless you understand the Stop-hook recursion risk (#149 follow-up):
 # AGENTMEMORY_ALLOW_AGENT_SDK=true
@@ -1059,6 +1083,17 @@ Create `~/.agentmemory/.env`:
 # OPENAI_EMBEDDING_MODEL=text-embedding-3-small
 # OPENAI_EMBEDDING_DIMENSIONS=1536        # Required when the model is not in the known-models table
 
+# Outbound LLM / embedding timeout
+# AGENTMEMORY_LLM_TIMEOUT_MS=60000       # Default: 60 000 ms (60 s). Applies to every
+                                          # raw-fetch provider (Gemini, OpenRouter, MiniMax,
+                                          # OpenAI LLM, OpenAI/Cohere/Voyage/OpenRouter
+                                          # embedding). For the OpenAI LLM path, the
+                                          # OpenAI-scoped OPENAI_TIMEOUT_MS alias (above)
+                                          # takes precedence when set, for back-compat
+                                          # with v0.9.17.
+                                          # Increase for slow networks or large batch calls;
+                                          # decrease to fail-fast on rate-limit holds.
+
 # Search tuning
 # BM25_WEIGHT=0.4
 # VECTOR_WEIGHT=0.6
@@ -1128,7 +1163,7 @@ Create `~/.agentmemory/.env`:
 
 <h2 id="api"><picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/section-api.svg"><img src="assets/tags/section-api.svg" alt="API" height="32" /></picture></h2>
 
-107 endpoints on port `3111`. The REST API binds to `127.0.0.1` by default. Protected endpoints require `Authorization: Bearer <secret>` when `AGENTMEMORY_SECRET` is set, and mesh sync endpoints require `AGENTMEMORY_SECRET` on both peers.
+121 endpoints on port `3111`. The REST API binds to `127.0.0.1` by default. Protected endpoints require `Authorization: Bearer <secret>` when `AGENTMEMORY_SECRET` is set, and mesh sync endpoints require `AGENTMEMORY_SECRET` on both peers.
 
 <details>
 <summary>Key endpoints</summary>
@@ -1162,7 +1197,7 @@ Full endpoint list: [`src/triggers/api.ts`](src/triggers/api.ts)
 ```bash
 npm run dev               # Hot reload
 npm run build             # Production build
-npm test                  # 800 tests (~1.7s)
+npm test                  # 950+ tests
 npm run test:integration  # API tests (requires running services)
 ```
 

package/dist/.env.example

@@ -45,6 +45,12 @@
 
 # MAX_TOKENS=4096                                # Cap LLM completion tokens for compression / summarise calls
 
+# Outbound LLM / embedding timeout — shared across every raw-fetch provider
+# (Gemini, OpenRouter, MiniMax, OpenAI LLM, and OpenAI/Cohere/Voyage/OpenRouter
+# embedding). The OpenAI LLM path also honours the OpenAI-scoped
+# OPENAI_TIMEOUT_MS alias for back-compat with v0.9.17 (precedence).
+# AGENTMEMORY_LLM_TIMEOUT_MS=60000                # Default: 60 000 ms (60 s)
+
 # Opt-in Claude-subscription fallback (spawns @anthropic-ai/claude-agent-sdk
 # child sessions). Off by default — the agent-sdk fallback can trigger
 # Stop-hook recursion (#149 follow-up) when invoked from inside Claude Code.

package/dist/cli.mjs

@@ -1433,7 +1433,7 @@ function bootLog(msg) {
 
 //#endregion
 //#region src/version.ts
-const VERSION = "0.9.16";
+const VERSION = "0.9.18";
 
 //#endregion
 //#region src/cli.ts
@@ -2088,7 +2088,7 @@ async function main() {
 	if (firstRun || IS_RESET) await runOnboarding();
 	if (skipEngine) {
 		if (IS_VERBOSE) p.log.info("Skipping engine check (--no-engine)");
-		await import("./src-3Oy_OOlF.mjs");
+		await import("./src-C7vygXCj.mjs");
 		if (await waitForAgentmemoryReady(15e3)) {
 			const consoleState = await ensureIiiConsole();
 			await maybeOfferGlobalInstall();
@@ -2100,7 +2100,7 @@ async function main() {
 		if (IS_VERBOSE) p.log.success("iii-engine is running");
 		warnIfEngineVersionMismatch(whichBinary("iii") ?? fallbackIiiPaths().find((p) => existsSync(p)) ?? null);
 		adoptRunningEngine();
-		await import("./src-3Oy_OOlF.mjs");
+		await import("./src-C7vygXCj.mjs");
 		if (await waitForAgentmemoryReady(15e3)) {
 			const consoleState = await ensureIiiConsole();
 			await maybeOfferGlobalInstall();
@@ -2149,7 +2149,7 @@ async function main() {
 		process.exit(1);
 	}
 	s.stop("iii-engine is ready");
-	await import("./src-3Oy_OOlF.mjs");
+	await import("./src-C7vygXCj.mjs");
 	if (await waitForAgentmemoryReady(15e3)) {
 		const consoleState = await ensureIiiConsole();
 		await maybeOfferGlobalInstall();
@@ -2159,7 +2159,13 @@ async function main() {
 }
 async function apiFetch(base, path, timeoutMs = 5e3) {
 	try {
-		return await (await fetch(`${base}/agentmemory/${path}`, { signal: AbortSignal.timeout(timeoutMs) })).json();
+		const headers = {};
+		const secret = process.env["AGENTMEMORY_SECRET"];
+		if (secret) headers["Authorization"] = `Bearer ${secret}`;
+		return await (await fetch(`${base}/agentmemory/${path}`, {
+			signal: AbortSignal.timeout(timeoutMs),
+			headers
+		})).json();
 	} catch {
 		return null;
 	}
@@ -3034,7 +3040,7 @@ async function runStop() {
 	p.outro("Stopped. Memories persisted to disk; restart anytime with: npx @agentmemory/agentmemory");
 }
 async function runMcp() {
-	await import("./standalone-BQOaGF4z.mjs");
+	await import("./standalone-kg2TedgD.mjs");
 }
 async function runConnectCmd() {
 	const { runConnect } = await Promise.resolve().then(() => connect_exports);