chore: apply formatter

docs/concepts/memory.md

@@ -4,6 +4,7 @@ read_when:
   - You want the memory file layout and workflow
   - You want to tune the automatic pre-compaction memory flush
 ---
+
 # Memory
 
 Moltbot memory is **plain Markdown in the agent workspace**. The files are the
@@ -38,7 +39,7 @@ These files live under the workspace (`agents.defaults.workspace`, default
 
 When a session is **close to auto-compaction**, Moltbot triggers a **silent,
 agentic turn** that reminds the model to write durable memory **before** the
-context is compacted. The default prompts explicitly say the model *may reply*,
+context is compacted. The default prompts explicitly say the model _may reply_,
 but usually `NO_REPLY` is the correct response so the user never sees this turn.
 
 This is controlled by `agents.defaults.compaction.memoryFlush`:
@@ -53,15 +54,16 @@ This is controlled by `agents.defaults.compaction.memoryFlush`:
           enabled: true,
           softThresholdTokens: 4000,
           systemPrompt: "Session nearing compaction. Store durable memories now.",
-          prompt: "Write any lasting notes to memory/YYYY-MM-DD.md; reply with NO_REPLY if nothing to store."
-        }
-      }
-    }
-  }
+          prompt: "Write any lasting notes to memory/YYYY-MM-DD.md; reply with NO_REPLY if nothing to store.",
+        },
+      },
+    },
+  },
 }
 ```
 
 Details:
+
 - **Soft threshold**: flush triggers when the session token estimate crosses
   `contextWindow - reserveTokensFloor - softThresholdTokens`.
 - **Silent** by default: prompts include `NO_REPLY` so nothing is delivered.
@@ -79,6 +81,7 @@ Moltbot can build a small vector index over `MEMORY.md` and `memory/*.md` so
 semantic queries can find related notes even when wording differs.
 
 Defaults:
+
 - Enabled by default.
 - Watches memory files for changes (debounced).
 - Uses remote embeddings by default. If `memorySearch.provider` is not set, Moltbot auto-selects:
@@ -258,6 +261,7 @@ agents: {
 ```
 
 Notes:
+
 - `remote.baseUrl` is optional (defaults to the Gemini API base URL).
 - `remote.headers` lets you add extra headers if needed.
 - Default model: `gemini-embedding-001`.
@@ -285,10 +289,12 @@ If you don't want to set an API key, use `memorySearch.provider = "local"` or se
 `memorySearch.fallback = "none"`.
 
 Fallbacks:
+
 - `memorySearch.fallback` can be `openai`, `gemini`, `local`, or `none`.
 - The fallback provider is only used when the primary embedding provider fails.
 
 Batch indexing (OpenAI + Gemini):
+
 - Enabled by default for OpenAI and Gemini embeddings. Set `agents.defaults.memorySearch.remote.batch.enabled = false` to disable.
 - Default behavior waits for batch completion; tune `remote.batch.wait`, `remote.batch.pollIntervalMs`, and `remote.batch.timeoutMinutes` if needed.
 - Set `remote.batch.concurrency` to control how many batch jobs we submit in parallel (default: 2).
@@ -296,6 +302,7 @@ Batch indexing (OpenAI + Gemini):
 - Gemini batch jobs use the async embeddings batch endpoint and require Gemini Batch API availability.
 
 Why OpenAI batch is fast + cheap:
+
 - For large backfills, OpenAI is typically the fastest option we support because we can submit many embedding requests in a single batch job and let OpenAI process them asynchronously.
 - OpenAI offers discounted pricing for Batch API workloads, so large indexing runs are usually cheaper than sending the same requests synchronously.
 - See the OpenAI Batch API docs and pricing for details:
@@ -321,10 +328,12 @@ agents: {
 ```
 
 Tools:
+
 - `memory_search` — returns snippets with file + line ranges.
 - `memory_get` — read memory file content by path.
 
 Local mode:
+
 - Set `agents.defaults.memorySearch.provider = "local"`.
 - Provide `agents.defaults.memorySearch.local.modelPath` (GGUF or `hf:` URI).
 - Optional: set `agents.defaults.memorySearch.fallback = "none"` to avoid remote fallback.
@@ -345,6 +354,7 @@ Local mode:
 ### Hybrid search (BM25 + vector)
 
 When enabled, Moltbot combines:
+
 - **Vector similarity** (semantic match, wording can differ)
 - **BM25 keyword relevance** (exact tokens like IDs, env vars, code symbols)
 
@@ -353,10 +363,12 @@ If full-text search is unavailable on your platform, Moltbot falls back to vecto
 #### Why hybrid?
 
 Vector search is great at “this means the same thing”:
+
 - “Mac Studio gateway host” vs “the machine running the gateway”
 - “debounce file updates” vs “avoid indexing on every write”
 
 But it can be weak at exact, high-signal tokens:
+
 - IDs (`a828e60`, `b3b9895a…`)
 - code symbols (`memorySearch.query.hybrid`)
 - error strings (“sqlite-vec unavailable”)
@@ -369,17 +381,21 @@ good results for both “natural language” queries and “needle in a haystack
 
 Implementation sketch:
 
-1) Retrieve a candidate pool from both sides:
+1. Retrieve a candidate pool from both sides:
+
 - **Vector**: top `maxResults * candidateMultiplier` by cosine similarity.
 - **BM25**: top `maxResults * candidateMultiplier` by FTS5 BM25 rank (lower is better).
 
-2) Convert BM25 rank into a 0..1-ish score:
+2. Convert BM25 rank into a 0..1-ish score:
+
 - `textScore = 1 / (1 + max(0, bm25Rank))`
 
-3) Union candidates by chunk id and compute a weighted score:
+3. Union candidates by chunk id and compute a weighted score:
+
 - `finalScore = vectorWeight * vectorScore + textWeight * textScore`
 
 Notes:
+
 - `vectorWeight` + `textWeight` is normalized to 1.0 in config resolution, so weights behave as percentages.
 - If embeddings are unavailable (or the provider returns a zero-vector), we still run BM25 and return keyword matches.
 - If FTS5 can’t be created, we keep vector-only search (no hard failure).
@@ -443,6 +459,7 @@ agents: {
 ```
 
 Notes:
+
 - Session indexing is **opt-in** (off by default).
 - Session updates are debounced and **indexed asynchronously** once they cross delta thresholds (best-effort).
 - `memory_search` never blocks on indexing; results can be slightly stale until background sync finishes.
@@ -491,6 +508,7 @@ agents: {
 ```
 
 Notes:
+
 - `enabled` defaults to true; when disabled, search falls back to in-process
   cosine similarity over stored embeddings.
 - If the sqlite-vec extension is missing or fails to load, Moltbot logs the
@@ -527,5 +545,6 @@ agents: {
 ```
 
 Notes:
+
 - `remote.*` takes precedence over `models.providers.openai.*`.
 - `remote.headers` merge with OpenAI headers; remote wins on key conflicts. Omit `remote.headers` to use the OpenAI defaults.

src/agents/pi-embedded-runner/system-prompt.ts

@@ -3,10 +3,10 @@ import type { AgentSession } from "@mariozechner/pi-coding-agent";
 import type { MemoryCitationsMode } from "../../config/types.memory.js";
 import type { ResolvedTimeFormat } from "../date-time.js";
 import type { EmbeddedContextFile } from "../pi-embedded-helpers.js";
-import { buildAgentSystemPrompt, type PromptMode } from "../system-prompt.js";
-import { buildToolSummaryMap } from "../tool-summaries.js";
 import type { EmbeddedSandboxInfo } from "./types.js";
 import type { ReasoningLevel, ThinkLevel } from "./utils.js";
+import { buildAgentSystemPrompt, type PromptMode } from "../system-prompt.js";
+import { buildToolSummaryMap } from "../tool-summaries.js";
 
 export function buildEmbeddedSystemPrompt(params: {
   workspaceDir: string;

src/agents/system-prompt.ts

@@ -1,9 +1,9 @@
 import type { ReasoningLevel, ThinkLevel } from "../auto-reply/thinking.js";
-import { SILENT_REPLY_TOKEN } from "../auto-reply/tokens.js";
-import { listDeliverableMessageChannels } from "../utils/message-channel.js";
 import type { MemoryCitationsMode } from "../config/types.memory.js";
 import type { ResolvedTimeFormat } from "./date-time.js";
 import type { EmbeddedContextFile } from "./pi-embedded-helpers.js";
+import { SILENT_REPLY_TOKEN } from "../auto-reply/tokens.js";
+import { listDeliverableMessageChannels } from "../utils/message-channel.js";
 
 /**
  * Controls which hardcoded sections are included in the system prompt.

src/agents/tools/memory-tool.ts

@@ -1,14 +1,13 @@
 import { Type } from "@sinclair/typebox";
-
 import type { MoltbotConfig } from "../../config/config.js";
 import type { MemoryCitationsMode } from "../../config/types.memory.js";
+import type { MemorySearchResult } from "../../memory/types.js";
+import type { AnyAgentTool } from "./common.js";
 import { resolveMemoryBackendConfig } from "../../memory/backend-config.js";
 import { getMemorySearchManager } from "../../memory/index.js";
-import type { MemorySearchResult } from "../../memory/types.js";
 import { parseAgentSessionKey } from "../../routing/session-key.js";
 import { resolveSessionAgentId } from "../agent-scope.js";
 import { resolveMemorySearchConfig } from "../memory-search.js";
-import type { AnyAgentTool } from "./common.js";
 import { jsonResult, readNumberParam, readStringParam } from "./common.js";
 
 const MemorySearchSchema = Type.Object({
@@ -200,10 +199,7 @@ function deriveChatTypeFromSessionKey(sessionKey?: string): "direct" | "group" |
   if (!parsed?.rest) {
     return "direct";
   }
-  const tokens = parsed.rest
-    .toLowerCase()
-    .split(":")
-    .filter(Boolean);
+  const tokens = parsed.rest.toLowerCase().split(":").filter(Boolean);
   if (tokens.includes("channel")) {
     return "channel";
   }

src/cli/memory-cli.ts

@@ -319,7 +319,12 @@ export async function runMemoryStatus(opts: MemoryCommandOptions) {
         ) as MemorySourceName[];
         const workspaceDir = status.workspaceDir;
         const scan = workspaceDir
-          ? await scanMemorySources({ workspaceDir, agentId, sources, extraPaths: status.extraPaths })
+          ? await scanMemorySources({
+              workspaceDir,
+              agentId,
+              sources,
+              extraPaths: status.extraPaths,
+            })
           : undefined;
         allResults.push({ agentId, status, embeddingProbe, indexError, scan });
       },

src/commands/status.scan.ts

@@ -1,3 +1,5 @@
+import type { MemoryProviderStatus } from "../memory/types.js";
+import type { RuntimeEnv } from "../runtime.js";
 import { withProgress } from "../cli/progress.js";
 import { loadConfig } from "../config/config.js";
 import { buildGatewayConnectionDetails, callGateway } from "../gateway/call.js";
@@ -7,14 +9,12 @@ import { collectChannelStatusIssues } from "../infra/channels-status-issues.js";
 import { resolveOsSummary } from "../infra/os-summary.js";
 import { getTailnetHostname } from "../infra/tailscale.js";
 import { getMemorySearchManager } from "../memory/index.js";
-import type { MemoryProviderStatus } from "../memory/types.js";
 import { runExec } from "../process/exec.js";
-import type { RuntimeEnv } from "../runtime.js";
+import { buildChannelsTable } from "./status-all/channels.js";
 import { getAgentLocalStatuses } from "./status.agent-local.js";
 import { pickGatewaySelfPresence, resolveGatewayProbeAuth } from "./status.gateway-probe.js";
 import { getStatusSummary } from "./status.summary.js";
 import { getUpdateCheckResult } from "./status.update.js";
-import { buildChannelsTable } from "./status-all/channels.js";
 
 type MemoryStatusSnapshot = MemoryProviderStatus & {
   agentId: string;

src/config/types.openclaw.ts

@@ -12,6 +12,7 @@ import type {
   TalkConfig,
 } from "./types.gateway.js";
 import type { HooksConfig } from "./types.hooks.js";
+import type { MemoryConfig } from "./types.memory.js";
 import type {
   AudioConfig,
   BroadcastConfig,
@@ -23,7 +24,6 @@ import type { NodeHostConfig } from "./types.node-host.js";
 import type { PluginsConfig } from "./types.plugins.js";
 import type { SkillsConfig } from "./types.skills.js";
 import type { ToolsConfig } from "./types.tools.js";
-import type { MemoryConfig } from "./types.memory.js";
 
 export type OpenClawConfig = {
   meta?: {

src/config/zod-schema.ts

@@ -1,7 +1,7 @@
 import { z } from "zod";
 import { ToolsSchema } from "./zod-schema.agent-runtime.js";
-import { ApprovalsSchema } from "./zod-schema.approvals.js";
 import { AgentsSchema, AudioSchema, BindingsSchema, BroadcastSchema } from "./zod-schema.agents.js";
+import { ApprovalsSchema } from "./zod-schema.approvals.js";
 import { HexColorSchema, ModelsConfigSchema } from "./zod-schema.core.js";
 import { HookMappingSchema, HooksGmailSchema, InternalHooksSchema } from "./zod-schema.hooks.js";
 import { ChannelsSchema } from "./zod-schema.providers.js";

src/memory/search-manager.ts

@@ -1,12 +1,12 @@
-import { createSubsystemLogger } from "../logging/subsystem.js";
 import type { MoltbotConfig } from "../config/config.js";
-import { resolveMemoryBackendConfig } from "./backend-config.js";
 import type { ResolvedQmdConfig } from "./backend-config.js";
 import type {
   MemoryEmbeddingProbeResult,
   MemorySearchManager,
   MemorySyncProgressUpdate,
 } from "./types.js";
+import { createSubsystemLogger } from "../logging/subsystem.js";
+import { resolveMemoryBackendConfig } from "./backend-config.js";
 
 const log = createSubsystemLogger("memory");
 const QMD_MANAGER_CACHE = new Map<string, MemorySearchManager>();

src/memory/session-files.ts

@@ -1,8 +1,8 @@
 import fs from "node:fs/promises";
 import path from "node:path";
 import { resolveSessionTranscriptsDirForAgent } from "../config/sessions/paths.js";
-import { createSubsystemLogger } from "../logging/subsystem.js";
 import { redactSensitiveText } from "../logging/redact.js";
+import { createSubsystemLogger } from "../logging/subsystem.js";
 import { hashText } from "./internal.js";
 
 const log = createSubsystemLogger("memory");