feat: upgrade default workspace model to claude-opus-4-7 (#727)

Replace the anthropic:claude-sonnet-4-6 default across config, handlers,
env example, and litellm proxy config. All tests updated to match the new
default; sonnet-4-6 alias kept in litellm_config.yml for pinned workspaces.

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

.env.example

@@ -71,7 +71,7 @@ CEREBRAS_API_KEY=              # Cerebras API key (cloud.cerebras.ai). Use with
 GOOGLE_API_KEY=                # Google AI API key (aistudio.google.com). Use with model: google_genai:gemini-2.5-flash
 MAX_TOKENS=2048                # Max output tokens for OpenRouter requests (default: 2048)
 LANGGRAPH_RECURSION_LIMIT=500  # LangGraph/DeepAgents max ReAct steps per turn (lib default: 25; raised to 500 — PM fan-out to 6+ reports + synthesis routinely exceeds 100)
-MODEL_PROVIDER=anthropic:claude-sonnet-4-6   # Format: provider:model. Providers: anthropic, openai, openrouter, groq, cerebras, google_genai, ollama
+MODEL_PROVIDER=anthropic:claude-opus-4-7    # Format: provider:model. Providers: anthropic, openai, openrouter, groq, cerebras, google_genai, ollama
 
 # ---- Workspace tier resource limits (issue #14) ----
 # Per-tier memory/CPU caps applied to each workspace Docker container.

infra/litellm_config.yml

@@ -30,6 +30,11 @@ model_list:
       model: anthropic/claude-sonnet-4-6
       api_key: ${ANTHROPIC_API_KEY}
 
+  - model_name: claude-opus-4-7
+    litellm_params:
+      model: anthropic/claude-opus-4-7
+      api_key: ${ANTHROPIC_API_KEY}
+
   # ── OpenAI ─────────────────────────────────────────────────────────────────
   - model_name: gpt-4o
     litellm_params:

platform/internal/handlers/org.go

@@ -338,7 +338,7 @@ func (h *OrgHandler) createWorkspaceTree(ws OrgWorkspace, parentID *string, defa
 		if runtime == "claude-code" {
 			model = "sonnet"
 		} else {
-			model = "anthropic:claude-sonnet-4-6"
+			model = "anthropic:claude-opus-4-7"
 		}
 	}
 	tier := ws.Tier

platform/internal/handlers/org_test.go

@@ -189,7 +189,7 @@ func TestOrgDefaults_Model_FallbackClaudeCode(t *testing.T) {
 		if runtime == "claude-code" {
 			model = "sonnet"
 		} else {
-			model = "anthropic:claude-sonnet-4-6"
+			model = "anthropic:claude-opus-4-7"
 		}
 	}
 	if model != "sonnet" {
@@ -211,11 +211,11 @@ func TestOrgDefaults_Model_FallbackDeepAgents(t *testing.T) {
 		if runtime == "claude-code" {
 			model = "sonnet"
 		} else {
-			model = "anthropic:claude-sonnet-4-6"
+			model = "anthropic:claude-opus-4-7"
 		}
 	}
-	if model != "anthropic:claude-sonnet-4-6" {
+	if model != "anthropic:claude-opus-4-7" {
-		t.Errorf("deepagents with empty model should get 'anthropic:claude-sonnet-4-6', got %q", model)
+		t.Errorf("deepagents with empty model should get 'anthropic:claude-opus-4-7', got %q", model)
 	}
 }
 
@@ -227,11 +227,11 @@ func TestOrgDefaults_Model_FallbackLangGraph(t *testing.T) {
 		if runtime == "claude-code" {
 			model = "sonnet"
 		} else {
-			model = "anthropic:claude-sonnet-4-6"
+			model = "anthropic:claude-opus-4-7"
 		}
 	}
-	if model != "anthropic:claude-sonnet-4-6" {
+	if model != "anthropic:claude-opus-4-7" {
-		t.Errorf("langgraph with empty model should get 'anthropic:claude-sonnet-4-6', got %q", model)
+		t.Errorf("langgraph with empty model should get 'anthropic:claude-opus-4-7', got %q", model)
 	}
 }
 

platform/internal/handlers/workspace_provision.go

@@ -417,7 +417,7 @@ func (h *WorkspaceHandler) ensureDefaultConfig(workspaceID string, payload model
 		if runtime == "claude-code" {
 			model = "sonnet"
 		} else {
-			model = "anthropic:claude-sonnet-4-6"
+			model = "anthropic:claude-opus-4-7"
 		}
 	}
 

platform/internal/handlers/workspace_provision_test.go

@@ -215,7 +215,7 @@ func TestEnsureDefaultConfig_LangGraph(t *testing.T) {
 	if !contains(content, "tier: 1") {
 		t.Errorf("config.yaml missing tier, got:\n%s", content)
 	}
-	if !contains(content, `model: "anthropic:claude-sonnet-4-6"`) {
+	if !contains(content, `model: "anthropic:claude-opus-4-7"`) {
 		t.Errorf("config.yaml should use default langgraph model, got:\n%s", content)
 	}
 }
@@ -354,7 +354,7 @@ func TestEnsureDefaultConfig_EmptyRuntimeDefaultsToLangGraph(t *testing.T) {
 	if !contains(configYAML, "runtime: langgraph") {
 		t.Errorf("empty runtime should default to langgraph, got:\n%s", configYAML)
 	}
-	if !contains(configYAML, `model: "anthropic:claude-sonnet-4-6"`) {
+	if !contains(configYAML, `model: "anthropic:claude-opus-4-7"`) {
 		t.Errorf("langgraph default model should be anthropic (quoted), got:\n%s", configYAML)
 	}
 }

workspace-template/config.py

@@ -197,7 +197,7 @@ class WorkspaceConfig:
     description: str = ""
     version: str = "1.0.0"
     tier: int = 1
-    model: str = "anthropic:claude-sonnet-4-6"
+    model: str = "anthropic:claude-opus-4-7"
     runtime: str = "langgraph"  # langgraph | claude-code | codex | ollama | custom
     runtime_config: RuntimeConfig = field(default_factory=RuntimeConfig)
     initial_prompt: str = ""
@@ -251,7 +251,7 @@ def load_config(config_path: Optional[str] = None) -> WorkspaceConfig:
         raw = yaml.safe_load(f) or {}
 
     # Override model from env if provided
-    model = os.environ.get("MODEL_PROVIDER", raw.get("model", "anthropic:claude-sonnet-4-6"))
+    model = os.environ.get("MODEL_PROVIDER", raw.get("model", "anthropic:claude-opus-4-7"))
 
     runtime = raw.get("runtime", "langgraph")
     runtime_raw = raw.get("runtime_config", {})

workspace-template/tests/test_config.py

@@ -52,7 +52,7 @@ def test_load_config_defaults(tmp_path):
     assert cfg.description == ""
     assert cfg.version == "1.0.0"
     assert cfg.tier == 1
-    assert cfg.model == "anthropic:claude-sonnet-4-6"
+    assert cfg.model == "anthropic:claude-opus-4-7"
     assert cfg.skills == []
     assert cfg.tools == []
     assert cfg.prompt_files == []