feat: allow compaction model override via config (#38753)

Merged via squash.

Prepared head SHA: a3d6d6c845
Co-authored-by: starbuck100 <25417736+starbuck100@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman

docs/concepts/compaction.md

@@ -24,6 +24,36 @@ Compaction **persists** in the session’s JSONL history.
 Use the `agents.defaults.compaction` setting in your `openclaw.json` to configure compaction behavior (mode, target tokens, etc.).
 Compaction summarization preserves opaque identifiers by default (`identifierPolicy: "strict"`). You can override this with `identifierPolicy: "off"` or provide custom text with `identifierPolicy: "custom"` and `identifierInstructions`.
 
+You can optionally specify a different model for compaction summarization via `agents.defaults.compaction.model`. This is useful when your primary model is a local or small model and you want compaction summaries produced by a more capable model. The override accepts any `provider/model-id` string:
+
+```json
+{
+  "agents": {
+    "defaults": {
+      "compaction": {
+        "model": "openrouter/anthropic/claude-sonnet-4-5"
+      }
+    }
+  }
+}
+```
+
+This also works with local models, for example a second Ollama model dedicated to summarization or a fine-tuned compaction specialist:
+
+```json
+{
+  "agents": {
+    "defaults": {
+      "compaction": {
+        "model": "ollama/llama3.1:8b"
+      }
+    }
+  }
+}
+```
+
+When unset, compaction uses the agent's primary model.
+
 ## Auto-compaction (default on)
 
 When a session nears or exceeds the model’s context window, OpenClaw triggers auto-compaction and may retry the original request using the compacted context.