feat: enable adaptive context pruning by default

docs/concepts/session-pruning.md

@@ -1,12 +1,12 @@
 ---
-summary: "Session pruning: opt-in tool-result trimming to reduce context bloat"
+summary: "Session pruning: tool-result trimming to reduce context bloat"
 read_when:
   - You want to reduce LLM context growth from tool outputs
   - You are tuning agent.contextPruning
 ---
 # Session Pruning
 
-Session pruning trims **old tool results** from the in-memory context right before each LLM call. It is **opt-in** and does **not** rewrite the on-disk session history (`*.jsonl`).
+Session pruning trims **old tool results** from the in-memory context right before each LLM call. It does **not** rewrite the on-disk session history (`*.jsonl`).
 
 ## When it runs
 - Before each LLM request (context hook).
@@ -59,7 +59,7 @@ Pruning uses an estimated context window (chars ≈ tokens × 4). The window siz
 - `hardClear`: `{ enabled: true, placeholder: "[Old tool result content cleared]" }`
 
 ## Examples
-Minimal (adaptive):
+Default (adaptive):
 ```json5
 {
   agent: {
@@ -68,6 +68,15 @@ Minimal (adaptive):
 }
 ```
 
+To disable:
+```json5
+{
+  agent: {
+    contextPruning: { mode: "off" }
+  }
+}
+```
+
 Aggressive:
 ```json5
 {

docs/concepts/session.md

@@ -21,8 +21,8 @@ All session state is **owned by the gateway** (the “master” Clawdbot). UI cl
 - Group entries may include `displayName`, `provider`, `subject`, `room`, and `space` to label sessions in UIs.
 - Clawdbot does **not** read legacy Pi/Tau session folders.
 
-## Session pruning (optional)
-Clawdbot can trim **old tool results** from the in-memory context right before LLM calls (opt-in).
+## Session pruning
+Clawdbot trims **old tool results** from the in-memory context right before LLM calls by default.
 This does **not** rewrite JSONL history. See [/concepts/session-pruning](/concepts/session-pruning).
 
 ## Mapping transports → session keys

docs/gateway/configuration.md

@@ -994,7 +994,7 @@ If you configure the same alias name (case-insensitive) yourself, your value win
 }
 ```
 
-#### `agent.contextPruning` (opt-in tool-result pruning)
+#### `agent.contextPruning` (tool-result pruning)
 
 `agent.contextPruning` prunes **old tool results** from the in-memory context right before a request is sent to the LLM.
 It does **not** modify the session history on disk (`*.jsonl` remains complete).
@@ -1025,7 +1025,7 @@ Notes / current limitations:
 - If the session doesn’t contain at least `keepLastAssistants` assistant messages yet, pruning is skipped.
 - In `aggressive` mode, `hardClear.enabled` is ignored (eligible tool results are always replaced with `hardClear.placeholder`).
 
-Example (minimal):
+Default (adaptive):
 ```json5
 {
   agent: {
@@ -1036,6 +1036,17 @@ Example (minimal):
 }
 ```
 
+To disable:
+```json5
+{
+  agent: {
+    contextPruning: {
+      mode: "off"
+    }
+  }
+}
+```
+
 Defaults (when `mode` is `"adaptive"` or `"aggressive"`):
 - `keepLastAssistants`: `3`
 - `softTrimRatio`: `0.3` (adaptive only)