fix: raise bootstrap file default limit

docs/concepts/agent-workspace.md

@@ -99,7 +99,7 @@ These are the standard files OpenClaw expects inside the workspace:
 </AccordionGroup>
 
 <Note>
-If any bootstrap file is missing, OpenClaw injects a "missing file" marker into the session and continues. Large bootstrap files are truncated when injected; adjust limits with `agents.defaults.bootstrapMaxChars` (default: 12000) and `agents.defaults.bootstrapTotalMaxChars` (default: 60000). `openclaw setup` can recreate missing defaults without overwriting existing files.
+If any bootstrap file is missing, OpenClaw injects a "missing file" marker into the session and continues. Large bootstrap files are truncated when injected; adjust limits with `agents.defaults.bootstrapMaxChars` (default: 20000) and `agents.defaults.bootstrapTotalMaxChars` (default: 60000). `openclaw setup` can recreate missing defaults without overwriting existing files.
 </Note>
 
 ## What is NOT in the workspace

docs/concepts/context.md

@@ -122,7 +122,7 @@ By default, OpenClaw injects a fixed set of workspace files (if present):
 - `HEARTBEAT.md`
 - `BOOTSTRAP.md` (first-run only)
 
-Large files are truncated per-file using `agents.defaults.bootstrapMaxChars` (default `12000` chars). OpenClaw also enforces a total bootstrap injection cap across files with `agents.defaults.bootstrapTotalMaxChars` (default `60000` chars). `/context` shows **raw vs injected** sizes and whether truncation happened.
+Large files are truncated per-file using `agents.defaults.bootstrapMaxChars` (default `20000` chars). OpenClaw also enforces a total bootstrap injection cap across files with `agents.defaults.bootstrapTotalMaxChars` (default `60000` chars). `/context` shows **raw vs injected** sizes and whether truncation happened.
 
 When truncation occurs, the runtime can inject an in-prompt warning block under Project Context. Configure this with `agents.defaults.bootstrapPromptTruncationWarning` (`off`, `once`, `always`; default `always`).
 

docs/concepts/system-prompt.md

@@ -208,7 +208,7 @@ because of the bootstrap file limits below.
 </Note>
 
 Large files are truncated with a marker. The max per-file size is controlled by
-`agents.defaults.bootstrapMaxChars` (default: 12000). Total injected bootstrap
+`agents.defaults.bootstrapMaxChars` (default: 20000). Total injected bootstrap
 content across files is capped by `agents.defaults.bootstrapTotalMaxChars`
 (default: 60000). Missing files inject a short missing-file marker. When truncation
 occurs, OpenClaw can inject a concise system-prompt warning notice; control this with

docs/gateway/config-agents.md

@@ -103,11 +103,11 @@ Per-agent override: `agents.list[].contextInjection`. Omitted values inherit
 
 ### `agents.defaults.bootstrapMaxChars`
 
-Max characters per workspace bootstrap file before truncation. Default: `12000`.
+Max characters per workspace bootstrap file before truncation. Default: `20000`.
 
 ```json5
 {
-  agents: { defaults: { bootstrapMaxChars: 12000 } },
+  agents: { defaults: { bootstrapMaxChars: 20000 } },
 }
 ```
 
@@ -138,7 +138,7 @@ injection behavior from the shared defaults. Omitted fields inherit from
   agents: {
     defaults: {
       contextInjection: "continuation-skip",
-      bootstrapMaxChars: 12000,
+      bootstrapMaxChars: 20000,
       bootstrapTotalMaxChars: 60000,
     },
     list: [

docs/help/faq.md

@@ -631,6 +631,48 @@ lives on the [First-run FAQ](/help/faq-first-run).
 
   </Accordion>
 
+  <Accordion title="Can I make SOUL.md bigger?">
+    Yes. `SOUL.md` is one of the workspace bootstrap files injected into the
+    agent context. The default per-file injection limit is `20000` characters,
+    and the total bootstrap budget across files is `60000` characters.
+
+    Change the shared defaults in your OpenClaw config:
+
+    ```json5
+    {
+      agents: {
+        defaults: {
+          bootstrapMaxChars: 50000,
+          bootstrapTotalMaxChars: 300000,
+        },
+      },
+    }
+    ```
+
+    Or override one agent:
+
+    ```json5
+    {
+      agents: {
+        list: [
+          {
+            id: "main",
+            bootstrapMaxChars: 50000,
+            bootstrapTotalMaxChars: 300000,
+          },
+        ],
+      },
+    }
+    ```
+
+    Use `/context` to check raw vs injected sizes and whether truncation happened.
+    Keep `SOUL.md` focused on voice, stance, and personality; put operating rules
+    in `AGENTS.md` and durable facts in memory.
+
+    See [Context](/concepts/context) and [Agent config](/gateway/config-agents).
+
+  </Accordion>
+
   <Accordion title="Recommended backup strategy">
     Put your **agent workspace** in a **private** git repo and back it up somewhere
     private (for example GitHub private). This captures memory + AGENTS/SOUL/USER

docs/reference/token-use.md

@@ -20,7 +20,7 @@ OpenClaw assembles its own system prompt on every run. It includes:
   prompt surface. It is bounded by `skills.limits.maxSkillsPromptChars`, with
   optional per-agent override at `agents.list[].skillsLimits.maxSkillsPromptChars`.
 - Self-update instructions
-- Workspace + bootstrap files (`AGENTS.md`, `SOUL.md`, `TOOLS.md`, `IDENTITY.md`, `USER.md`, `HEARTBEAT.md`, `BOOTSTRAP.md` when new, plus `MEMORY.md` when present). Native Codex turns do not paste raw `MEMORY.md` from the configured agent workspace when memory tools are available for that workspace; they include a small memory pointer in turn-scoped collaboration developer instructions and use memory tools on demand. If tools are disabled, memory search is unavailable, or the active workspace differs from the agent memory workspace, `MEMORY.md` uses the normal bounded turn-context path. Lowercase root `memory.md` is not injected; it is legacy repair input for `openclaw doctor --fix` when paired with `MEMORY.md`. Large injected files are truncated by `agents.defaults.bootstrapMaxChars` (default: 12000), and total bootstrap injection is capped by `agents.defaults.bootstrapTotalMaxChars` (default: 60000). `memory/*.md` daily files are not part of the normal bootstrap prompt; they remain on-demand via memory tools on ordinary turns, but reset/startup model runs can prepend a one-shot startup-context block with recent daily memory for that first turn. Bare chat `/new` and `/reset` commands are acknowledged without invoking the model. The startup prelude is controlled by `agents.defaults.startupContext`. Post-compaction AGENTS.md excerpts are separate and require explicit `agents.defaults.compaction.postCompactionSections` opt-in.
+- Workspace + bootstrap files (`AGENTS.md`, `SOUL.md`, `TOOLS.md`, `IDENTITY.md`, `USER.md`, `HEARTBEAT.md`, `BOOTSTRAP.md` when new, plus `MEMORY.md` when present). Native Codex turns do not paste raw `MEMORY.md` from the configured agent workspace when memory tools are available for that workspace; they include a small memory pointer in turn-scoped collaboration developer instructions and use memory tools on demand. If tools are disabled, memory search is unavailable, or the active workspace differs from the agent memory workspace, `MEMORY.md` uses the normal bounded turn-context path. Lowercase root `memory.md` is not injected; it is legacy repair input for `openclaw doctor --fix` when paired with `MEMORY.md`. Large injected files are truncated by `agents.defaults.bootstrapMaxChars` (default: 20000), and total bootstrap injection is capped by `agents.defaults.bootstrapTotalMaxChars` (default: 60000). `memory/*.md` daily files are not part of the normal bootstrap prompt; they remain on-demand via memory tools on ordinary turns, but reset/startup model runs can prepend a one-shot startup-context block with recent daily memory for that first turn. Bare chat `/new` and `/reset` commands are acknowledged without invoking the model. The startup prelude is controlled by `agents.defaults.startupContext`. Post-compaction AGENTS.md excerpts are separate and require explicit `agents.defaults.compaction.postCompactionSections` opt-in.
 - Time (UTC + user timezone)
 - Reply tags + heartbeat behavior
 - Runtime metadata (host/OS/model/thinking)

src/agents/bootstrap-files.test.ts

@@ -634,11 +634,11 @@ describe("makeBootstrapWarn", () => {
       warn: (message) => warnings.push(message),
     });
 
-    warn?.("workspace bootstrap file MEMORY.md is 36697 chars (limit 12000); truncating");
-    warn?.("workspace bootstrap file MEMORY.md is 36697 chars (limit 12000); truncating");
+    warn?.("workspace bootstrap file MEMORY.md is 36697 chars (limit 20000); truncating");
+    warn?.("workspace bootstrap file MEMORY.md is 36697 chars (limit 20000); truncating");
 
     expect(warnings).toEqual([
-      "workspace bootstrap file MEMORY.md is 36697 chars (limit 12000); truncating (sessionKey=agent:main:test-session)",
+      "workspace bootstrap file MEMORY.md is 36697 chars (limit 20000); truncating (sessionKey=agent:main:test-session)",
     ]);
   });
 
@@ -653,12 +653,12 @@ describe("makeBootstrapWarn", () => {
       warn: (message) => warnings.push(message),
     });
 
-    first?.("workspace bootstrap file MEMORY.md is 36697 chars (limit 12000); truncating");
-    second?.("workspace bootstrap file MEMORY.md is 36697 chars (limit 12000); truncating");
+    first?.("workspace bootstrap file MEMORY.md is 36697 chars (limit 20000); truncating");
+    second?.("workspace bootstrap file MEMORY.md is 36697 chars (limit 20000); truncating");
 
     expect(warnings).toEqual([
-      "workspace bootstrap file MEMORY.md is 36697 chars (limit 12000); truncating (sessionKey=agent:main:first-session)",
-      "workspace bootstrap file MEMORY.md is 36697 chars (limit 12000); truncating (sessionKey=agent:main:second-session)",
+      "workspace bootstrap file MEMORY.md is 36697 chars (limit 20000); truncating (sessionKey=agent:main:first-session)",
+      "workspace bootstrap file MEMORY.md is 36697 chars (limit 20000); truncating (sessionKey=agent:main:second-session)",
     ]);
   });
 
@@ -675,12 +675,12 @@ describe("makeBootstrapWarn", () => {
       warn: (message) => warnings.push(message),
     });
 
-    first?.("workspace bootstrap file MEMORY.md is 36697 chars (limit 12000); truncating");
-    second?.("workspace bootstrap file MEMORY.md is 36697 chars (limit 12000); truncating");
+    first?.("workspace bootstrap file MEMORY.md is 36697 chars (limit 20000); truncating");
+    second?.("workspace bootstrap file MEMORY.md is 36697 chars (limit 20000); truncating");
 
     expect(warnings).toEqual([
-      "workspace bootstrap file MEMORY.md is 36697 chars (limit 12000); truncating (sessionKey=agent:main:shared-session)",
-      "workspace bootstrap file MEMORY.md is 36697 chars (limit 12000); truncating (sessionKey=agent:main:shared-session)",
+      "workspace bootstrap file MEMORY.md is 36697 chars (limit 20000); truncating (sessionKey=agent:main:shared-session)",
+      "workspace bootstrap file MEMORY.md is 36697 chars (limit 20000); truncating (sessionKey=agent:main:shared-session)",
     ]);
   });
 });

src/agents/embedded-agent-helpers/bootstrap.ts

@@ -85,7 +85,7 @@ export function stripThoughtSignatures<T>(
   }) as T;
 }
 
-export const DEFAULT_BOOTSTRAP_MAX_CHARS = 12_000;
+export const DEFAULT_BOOTSTRAP_MAX_CHARS = 20_000;
 export const DEFAULT_BOOTSTRAP_TOTAL_MAX_CHARS = 60_000;
 export const DEFAULT_BOOTSTRAP_PROMPT_TRUNCATION_WARNING_MODE = "always";
 const MIN_BOOTSTRAP_FILE_BUDGET_CHARS = 64;

src/auto-reply/reply/commands-context-report.test.ts

@@ -101,7 +101,7 @@ describe("buildContextReply", () => {
         omitBootstrapLimits: true,
       }),
     );
-    expect(result.text).toContain("Bootstrap max/file: 12,000 chars");
+    expect(result.text).toContain("Bootstrap max/file: 20,000 chars");
     expect(result.text).toContain("Bootstrap max/total: 60,000 chars");
     expect(result.text).not.toContain("Bootstrap max/file: ? chars");
   });

src/config/schema.help.ts

@@ -1121,7 +1121,7 @@ export const FIELD_HELP: Record<string, string> = {
   "agents.defaults.contextInjection":
     'Controls when workspace bootstrap files are injected into the system prompt: "always" (default) or "continuation-skip" for safe continuation turns after a completed assistant response.',
   "agents.defaults.bootstrapMaxChars":
-    "Max characters of each workspace bootstrap file injected into the system prompt before truncation (default: 12000).",
+    "Max characters of each workspace bootstrap file injected into the system prompt before truncation (default: 20000).",
   "agents.defaults.bootstrapTotalMaxChars":
     "Max total characters across all injected workspace bootstrap files (default: 60000).",
   "agents.defaults.experimental":

ui/src/ui/views/config-quick.test.ts

@@ -133,6 +133,21 @@ describe("renderQuickSettings", () => {
     expect(container.querySelectorAll(".qs-card--span-all")).toHaveLength(1);
   });
 
+  it("shows the current bootstrap default when config omits the explicit limit", () => {
+    const container = document.createElement("div");
+
+    render(renderQuickSettings(createProps({ configObject: {} })), container);
+
+    const stat = Array.from(container.querySelectorAll<HTMLElement>(".qs-profile-stat")).find(
+      (candidate) =>
+        candidate.querySelector(".qs-profile-stat__label")?.textContent?.trim() ===
+        "Bootstrap Per File",
+    );
+    expect(stat?.querySelector(".qs-profile-stat__value")?.textContent?.trim()).toBe(
+      "20,000 chars",
+    );
+  });
+
   it("lets operators change browser and tool profile from Security quick settings", () => {
     const onBrowserEnabledToggle = vi.fn();
     const onToolProfileChange = vi.fn();

ui/src/ui/views/config-quick.ts

@@ -327,7 +327,7 @@ type ProfileSettings = {
 };
 
 const DEFAULT_PROFILE_SETTINGS: ProfileSettings = {
-  bootstrapMaxChars: 12_000,
+  bootstrapMaxChars: 20_000,
   bootstrapTotalMaxChars: 60_000,
   contextInjection: "always",
 };