chore(ollama): update suggested onboarding models (#62626)

Merged via squash.

Prepared head SHA: 48c083b88a
Co-authored-by: BruceMacD <5853428+BruceMacD@users.noreply.github.com>
Co-authored-by: BruceMacD <5853428+BruceMacD@users.noreply.github.com>
Reviewed-by: @BruceMacD

CHANGELOG.md

@@ -31,6 +31,7 @@ Docs: https://docs.openclaw.ai
 - Tools/media: document per-provider music and video generation capabilities, and add shared live video-to-video sweep coverage for providers that support local reference clips.
 - Compaction: add pluggable compaction provider registry so plugins can replace the built-in summarization pipeline. Configure via `agents.defaults.compaction.provider`; falls back to LLM summarization on provider failure. (#56224) Thanks @DhruvBhatia0.
 - Discord/events: allow `event-create` to accept a cover image URL or local file path, load and validate PNG/JPG/GIF event cover media, and pass the encoded image payload through Discord admin action/runtime paths. (#60883) Thanks @bittoby.
+- Providers/Ollama: update suggested onboarding models to gemma4 (local), glm-5.1 and minimax-m2.7 (cloud). (#62626) Thanks @BruceMacD.
 
 ### Fixes
 
@@ -89,12 +90,8 @@ Docs: https://docs.openclaw.ai
 - Providers/Mistral: send `reasoning_effort` for `mistral/mistral-small-latest` (Mistral Small 4) with thinking-level mapping, and mark the catalog entry as reasoning-capable so adjustable reasoning matches Mistral’s Chat Completions API. (#62162) Thanks @neeravmakwana.
 - OpenAI TTS/Groq: send `wav` to Groq-compatible speech endpoints, honor explicit `responseFormat` overrides on OpenAI-compatible paths, and only mark voice-note output as voice-compatible when the actual format is `opus`. (#62233) Thanks @neeravmakwana.
 - BlueBubbles/network: respect explicit private-network opt-out for loopback and private `serverUrl` values across account resolution, status probes, monitor startup, and attachment downloads, while keeping public-host attachment hostname pinning intact. (#59373) Thanks @jpreagan.
-<<<<<<< HEAD
 - Agents/heartbeat: keep heartbeat runs pinned to the main session so active subagent transcripts are not overwritten by heartbeat status messages. (#61803) thanks @100yenadmin.
 - Agents/compaction: stop compaction-wait aborts from re-entering prompt failover and replaying completed tool turns. (#62600) Thanks @i-dentifier.
-=======
-- Approvals/runtime: move native approval lifecycle assembly into shared core bootstrap/runtime seams driven by channel capabilities and runtime contexts, and remove the legacy bundled approval fallback wiring. (#62135) Thanks @gumadeiras.
->>>>>>> 367f6afaf1 (Approvals: finish capability cutover and Matrix parity)
 
 ## 2026.4.5
 

docs/help/faq.md

@@ -2254,7 +2254,7 @@ for usage/billing and raise limits as needed.
     Quickest setup:
 
     1. Install Ollama from `https://ollama.com/download`
-    2. Pull a local model such as `ollama pull glm-4.7-flash`
+    2. Pull a local model such as `ollama pull gemma4`
     3. If you want cloud models too, run `ollama signin`
     4. Run `openclaw onboard` and choose `Ollama`
     5. Pick `Local` or `Cloud + Local`

docs/providers/ollama.md

@@ -57,7 +57,7 @@ openclaw onboard --non-interactive \
 2. Pull a local model if you want local inference:
 
 ```bash
-ollama pull glm-4.7-flash
+ollama pull gemma4
 # or
 ollama pull gpt-oss:20b
 # or
@@ -78,12 +78,12 @@ openclaw onboard
 
 - `Local`: local models only
 - `Cloud + Local`: local models plus cloud models
-- Cloud models such as `kimi-k2.5:cloud`, `minimax-m2.5:cloud`, and `glm-5:cloud` do **not** require a local `ollama pull`
+- Cloud models such as `kimi-k2.5:cloud`, `minimax-m2.7:cloud`, and `glm-5.1:cloud` do **not** require a local `ollama pull`
 
 OpenClaw currently suggests:
 
-- local default: `glm-4.7-flash`
-- cloud defaults: `kimi-k2.5:cloud`, `minimax-m2.5:cloud`, `glm-5:cloud`
+- local default: `gemma4`
+- cloud defaults: `kimi-k2.5:cloud`, `minimax-m2.7:cloud`, `glm-5.1:cloud`
 
 5. If you prefer manual setup, enable Ollama for OpenClaw directly (any value works; Ollama doesn't require a real key):
 
@@ -99,7 +99,7 @@ openclaw config set models.providers.ollama.apiKey "ollama-local"
 
 ```bash
 openclaw models list
-openclaw models set ollama/glm-4.7-flash
+openclaw models set ollama/gemma4
 ```
 
 7. Or set the default in config:
@@ -108,7 +108,7 @@ openclaw models set ollama/glm-4.7-flash
 {
   agents: {
     defaults: {
-      model: { primary: "ollama/glm-4.7-flash" },
+      model: { primary: "ollama/gemma4" },
     },
   },
 }
@@ -229,7 +229,7 @@ Once configured, all your Ollama models are available:
 
 ## Cloud models
 
-Cloud models let you run cloud-hosted models (for example `kimi-k2.5:cloud`, `minimax-m2.5:cloud`, `glm-5:cloud`) alongside your local models.
+Cloud models let you run cloud-hosted models (for example `kimi-k2.5:cloud`, `minimax-m2.7:cloud`, `glm-5.1:cloud`) alongside your local models.
 
 To use cloud models, select **Cloud + Local** mode during setup. The wizard checks whether you are signed in and opens a browser sign-in flow when needed. If authentication cannot be verified, the wizard falls back to local model defaults.
 
@@ -355,7 +355,7 @@ To add models:
 
 ```bash
 ollama list  # See what's installed
-ollama pull glm-4.7-flash
+ollama pull gemma4
 ollama pull gpt-oss:20b
 ollama pull llama3.3     # Or another model
 ```

extensions/ollama/index.test.ts

@@ -115,13 +115,13 @@ describe("ollama plugin", () => {
 
     await provider.onModelSelected?.({
       config,
-      model: "ollama/glm-4.7-flash",
+      model: "ollama/gemma4",
       prompter,
     });
 
     expect(ensureOllamaModelPulledMock).toHaveBeenCalledWith({
       config,
-      model: "ollama/glm-4.7-flash",
+      model: "ollama/gemma4",
       prompter,
     });
   });

extensions/ollama/src/defaults.ts

@@ -9,5 +9,5 @@ export const OLLAMA_DEFAULT_COST = {
   cacheWrite: 0,
 };
 
-export const OLLAMA_DEFAULT_MODEL = "glm-4.7-flash";
+export const OLLAMA_DEFAULT_MODEL = "gemma4";
 export const DEFAULT_OLLAMA_EMBEDDING_MODEL = "nomic-embed-text";

extensions/ollama/src/provider-models.test.ts

@@ -41,7 +41,7 @@ describe("ollama provider models", () => {
   });
 
   it("sets models with vision capability from /api/show capabilities", async () => {
-    const models: OllamaTagModel[] = [{ name: "kimi-k2.5:cloud" }, { name: "glm-5:cloud" }];
+    const models: OllamaTagModel[] = [{ name: "kimi-k2.5:cloud" }, { name: "glm-5.1:cloud" }];
     const fetchMock = vi.fn(async (input: string | URL | Request, init?: RequestInit) => {
       const url = requestUrl(input);
       if (!url.endsWith("/api/show")) {
@@ -54,7 +54,7 @@ describe("ollama provider models", () => {
           capabilities: ["vision", "thinking", "completion", "tools"],
         });
       }
-      if (body.name === "glm-5:cloud") {
+      if (body.name === "glm-5.1:cloud") {
         return jsonResponse({
           model_info: { "glm5.context_length": 202752 },
           capabilities: ["thinking", "completion", "tools"],
@@ -73,7 +73,7 @@ describe("ollama provider models", () => {
         capabilities: ["vision", "thinking", "completion", "tools"],
       },
       {
-        name: "glm-5:cloud",
+        name: "glm-5.1:cloud",
         contextWindow: 202752,
         capabilities: ["thinking", "completion", "tools"],
       },
@@ -88,7 +88,7 @@ describe("ollama provider models", () => {
     ]);
     expect(visionModel.input).toEqual(["text", "image"]);
 
-    const textModel = buildOllamaModelDefinition("glm-5:cloud", 202752, ["completion", "tools"]);
+    const textModel = buildOllamaModelDefinition("glm-5.1:cloud", 202752, ["completion", "tools"]);
     expect(textModel.input).toEqual(["text"]);
 
     const noCapabilities = buildOllamaModelDefinition("unknown-model", 65536);

extensions/ollama/src/setup.test.ts

@@ -105,7 +105,7 @@ describe("ollama setup", () => {
     });
     const modelIds = result.config.models?.providers?.ollama?.models?.map((m) => m.id);
 
-    expect(modelIds?.[0]).toBe("glm-4.7-flash");
+    expect(modelIds?.[0]).toBe("gemma4");
   });
 
   it("puts suggested cloud model first in remote mode", async () => {
@@ -128,7 +128,7 @@ describe("ollama setup", () => {
   it("mode selection affects model ordering (local)", async () => {
     const prompter = createModePrompter("local");
 
-    const fetchMock = createOllamaFetchMock({ tags: ["llama3:8b", "glm-4.7-flash"] });
+    const fetchMock = createOllamaFetchMock({ tags: ["llama3:8b", "gemma4"] });
     vi.stubGlobal("fetch", fetchMock);
 
     const result = await promptAndConfigureOllama({
@@ -139,7 +139,7 @@ describe("ollama setup", () => {
     });
 
     const modelIds = result.config.models?.providers?.ollama?.models?.map((m) => m.id);
-    expect(modelIds?.[0]).toBe("glm-4.7-flash");
+    expect(modelIds?.[0]).toBe("gemma4");
     expect(modelIds).toContain("llama3:8b");
   });
 
@@ -194,7 +194,7 @@ describe("ollama setup", () => {
     } as unknown as WizardPrompter;
 
     const fetchMock = createOllamaFetchMock({
-      tags: ["llama3:8b", "glm-4.7-flash", "deepseek-r1:14b"],
+      tags: ["llama3:8b", "gemma4", "deepseek-r1:14b"],
     });
     vi.stubGlobal("fetch", fetchMock);
 
@@ -209,10 +209,10 @@ describe("ollama setup", () => {
 
     expect(modelIds).toEqual([
       "kimi-k2.5:cloud",
-      "minimax-m2.5:cloud",
-      "glm-5:cloud",
+      "minimax-m2.7:cloud",
+      "glm-5.1:cloud",
       "llama3:8b",
-      "glm-4.7-flash",
+      "gemma4",
       "deepseek-r1:14b",
     ]);
     expect(models?.find((model) => model.id === "kimi-k2.5:cloud")?.input).toEqual([
@@ -261,8 +261,8 @@ describe("ollama setup", () => {
       vi.stubGlobal("fetch", fetchMock);
 
       await ensureOllamaModelPulled({
-        config: createDefaultOllamaConfig("ollama/glm-4.7-flash"),
-        model: "ollama/glm-4.7-flash",
+        config: createDefaultOllamaConfig("ollama/gemma4"),
+        model: "ollama/gemma4",
         prompter,
       });
 
@@ -273,12 +273,12 @@ describe("ollama setup", () => {
     it("skips pull when model is already available", async () => {
       const prompter = {} as unknown as WizardPrompter;
 
-      const fetchMock = createOllamaFetchMock({ tags: ["glm-4.7-flash"] });
+      const fetchMock = createOllamaFetchMock({ tags: ["gemma4"] });
       vi.stubGlobal("fetch", fetchMock);
 
       await ensureOllamaModelPulled({
-        config: createDefaultOllamaConfig("ollama/glm-4.7-flash"),
-        model: "ollama/glm-4.7-flash",
+        config: createDefaultOllamaConfig("ollama/gemma4"),
+        model: "ollama/gemma4",
         prompter,
       });
 

extensions/ollama/src/setup.ts

@@ -20,7 +20,7 @@ import {
 } from "./provider-models.js";
 
 const OLLAMA_SUGGESTED_MODELS_LOCAL = [OLLAMA_DEFAULT_MODEL];
-const OLLAMA_SUGGESTED_MODELS_CLOUD = ["kimi-k2.5:cloud", "minimax-m2.5:cloud", "glm-5:cloud"];
+const OLLAMA_SUGGESTED_MODELS_CLOUD = ["kimi-k2.5:cloud", "minimax-m2.7:cloud", "glm-5.1:cloud"];
 const OLLAMA_CONTEXT_ENRICH_LIMIT = 200;
 
 type OllamaMode = "remote" | "local";