feat: inject SOUL.md/IDENTITY.md persona and detect workspace context files

- input-filter: scan workspace for SOUL.md, IDENTITY.md, MEMORY.md etc. on each turn
- bootstrap: when these files exist, instruct Claude to Read them at session start
- This gives the contractor agent its OpenClaw persona (SOUL.md embody, IDENTITY.md fill)
- Memory note added to bootstrap when workspace has memory files

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/bridge/bootstrap.ts

@@ -4,6 +4,8 @@ export type BootstrapInput = {
   workspace: string;
   /** Skills XML block extracted from the OpenClaw system prompt, if any */
   skillsBlock?: string;
+  /** Subset of OpenClaw context files present in the workspace (for persona/identity) */
+  workspaceContextFiles?: string[];
 };
 
 /**
@@ -12,6 +14,10 @@ export type BootstrapInput = {
  * Must NOT be re-injected on every turn.
  */
 export function buildBootstrap(input: BootstrapInput): string {
+  const contextFiles = input.workspaceContextFiles ?? [];
+  const hasSoul = contextFiles.includes("SOUL.md");
+  const hasIdentity = contextFiles.includes("IDENTITY.md");
+
   const lines = [
     `You are operating as a contractor agent inside OpenClaw.`,
     ``,
@@ -32,6 +38,38 @@ export function buildBootstrap(input: BootstrapInput): string {
     `- If a task is unclear, ask one focused clarifying question.`,
   ];
 
+  // Inject persona/identity context from OpenClaw workspace files.
+  // These files define who this agent is and how it should behave.
+  if (hasSoul || hasIdentity) {
+    lines.push(``, `## Persona & Identity`);
+    if (hasSoul) {
+      lines.push(
+        `Read ${input.workspace}/SOUL.md now (using the Read tool) and embody the persona and tone it describes.`,
+        `SOUL.md defines your values, communication style, and boundaries — treat it as authoritative.`,
+      );
+    }
+    if (hasIdentity) {
+      lines.push(
+        `Read ${input.workspace}/IDENTITY.md now (using the Read tool) to understand your name, creature type, and personal vibe.`,
+        `If IDENTITY.md is empty/template-only, you may fill it in as you develop your identity.`,
+      );
+    }
+  }
+
+  // Memory system note: OpenClaw uses workspace/memory/*.md + MEMORY.md.
+  // Claude Code also maintains per-project auto-memory at ~/.claude/projects/<path>/memory/.
+  // Both are active; Claude Code's auto-memory is loaded automatically each session.
+  // OpenClaw memory tools (memory_search, memory_get) are available as MCP tools
+  // but require bridge-side implementations to execute (not yet wired).
+  if (contextFiles.includes("MEMORY.md") || contextFiles.some(f => f.startsWith("memory/"))) {
+    lines.push(
+      ``,
+      `## Memory`,
+      `OpenClaw memory files exist in ${input.workspace}/memory/ and ${input.workspace}/MEMORY.md.`,
+      `Use the Read tool to access these directly. For writing new memories, write to ${input.workspace}/memory/<topic>.md.`,
+    );
+  }
+
   if (input.skillsBlock) {
     lines.push(
       ``,

src/bridge/input-filter.ts

@@ -1,3 +1,5 @@
+import fs from "node:fs";
+import path from "node:path";
 import type { BridgeInboundRequest, OpenAIMessage } from "../types/model.js";
 
 function messageText(m: OpenAIMessage): string {
@@ -33,6 +35,8 @@ export type RequestContext = {
   workspace: string;
   /** Raw <available_skills>...</available_skills> XML block from the system prompt */
   skillsBlock: string;
+  /** OpenClaw context files present in the workspace (SOUL.md, IDENTITY.md, etc.) */
+  workspaceContextFiles: string[];
 };
 
 /**
@@ -67,9 +71,25 @@ export function extractRequestContext(req: BridgeInboundRequest): RequestContext
     ? skillsMatch[0].replace(/~\//g, `${home}/`)
     : "";
 
+  // Detect which OpenClaw context files are present in the workspace.
+  // These tell us what persona/memory files to surface to Claude.
+  const workspace = repoMatch?.[1] ?? "";
+  const CONTEXT_FILES = ["SOUL.md", "IDENTITY.md", "MEMORY.md", "AGENTS.md", "USER.md"];
+  const workspaceContextFiles: string[] = [];
+  if (workspace) {
+    for (const f of CONTEXT_FILES) {
+      if (fs.existsSync(path.join(workspace, f))) workspaceContextFiles.push(f);
+    }
+    // Also check for memory/ directory
+    if (fs.existsSync(path.join(workspace, "memory"))) {
+      workspaceContextFiles.push("memory/");
+    }
+  }
+
   return {
     agentId: agentMatch?.[1] ?? "",
-    workspace: repoMatch?.[1] ?? "",
+    workspace,
     skillsBlock,
+    workspaceContextFiles,
   };
 }

src/bridge/server.ts

@@ -104,7 +104,7 @@ export function createBridgeServer(config: BridgeServerConfig): http.Server {
 
     // Extract agent ID and workspace from the system prompt's Runtime line.
     // OpenClaw does NOT send agent/session info as HTTP headers — it's in the system prompt.
-    const { agentId: parsedAgentId, workspace: parsedWorkspace, skillsBlock } = extractRequestContext(body);
+    const { agentId: parsedAgentId, workspace: parsedWorkspace, skillsBlock, workspaceContextFiles } = extractRequestContext(body);
     const latestMessage = extractLatestUserMessage(body);
 
     if (!latestMessage) {
@@ -139,7 +139,7 @@ export function createBridgeServer(config: BridgeServerConfig): http.Server {
     // Build prompt: bootstrap on first turn, bare message on subsequent turns
     const isFirstTurn = !claudeSessionId;
     const prompt = isFirstTurn
-      ? `${buildBootstrap({ agentId, openclawSessionKey: sessionKey, workspace, skillsBlock: skillsBlock || undefined })}\n\n---\n\n${latestMessage}`
+      ? `${buildBootstrap({ agentId, openclawSessionKey: sessionKey, workspace, skillsBlock: skillsBlock || undefined, workspaceContextFiles })}\n\n---\n\n${latestMessage}`
       : latestMessage;
 
     // Start SSE response