chore(models): upgrade the opus alias to claude-opus-4-8

MODEL_MAP["opus"] moves off claude-opus-4-6 to the newest Opus tier at the
same price; pricing already matched via the claude-opus-4 fragment, and a
new test_opus_is_priced guard keeps the alias priced. Fixtures, panel
mocks, and docs follow.

tests/unit/billing/test_pricing.py

@@ -562,7 +562,14 @@ class TestProviderAwareness:
         assert cost == _ZERO_COST
 
     def test_is_anthropic_model_true_for_claude_names(self) -> None:
-        for name in ("claude-opus-4-6", "claude-fable-5", "opus", "sonnet", "haiku"):
+        for name in (
+            "claude-opus-4-6",
+            "claude-opus-4-8",
+            "claude-fable-5",
+            "opus",
+            "sonnet",
+            "haiku",
+        ):
             assert _is_anthropic_model(name) is True, name
 
     def test_is_anthropic_model_false_for_non_claude_names(self) -> None:

tests/unit/models/test_misc_models.py

@@ -106,7 +106,7 @@ def test_build_anthropic_entries_skips_missing_models() -> None:
     # Patch MODEL_MAP to be missing one entry → loop hits the `continue` branch.
     with patch(
         "roboco.models.llm_catalog.MODEL_MAP",
-        {"opus": "claude-opus-4-6"},  # sonnet+haiku missing
+        {"opus": "claude-opus-4-8"},  # sonnet+haiku missing
     ):
         entries = _build_anthropic_entries()
     # Only one entry survives — opus.

tests/unit/models/test_model_map.py

@@ -12,9 +12,10 @@ def test_sonnet_alias_resolves_to_sonnet_5() -> None:
     assert MODEL_MAP["sonnet"] == "claude-sonnet-5"
 
 
-def test_opus_alias_unchanged() -> None:
-    # CEO preference: stay on Opus 4.6 (4.7/4.8 not preferred).
-    assert MODEL_MAP["opus"] == "claude-opus-4-6"
+def test_opus_alias_resolves_to_opus_4_8() -> None:
+    # CEO upgrade to the newest Opus tier ("Opus 5" does not exist — the
+    # Claude 5 family is Fable/Mythos/Sonnet; Opus tops out at 4.8).
+    assert MODEL_MAP["opus"] == "claude-opus-4-8"
 
 
 def test_sonnet_5_is_priced() -> None:
@@ -23,6 +24,12 @@ def test_sonnet_5_is_priced() -> None:
     assert cost > 0.0
 
 
+def test_opus_is_priced() -> None:
+    # Same silent-$0 guard for the opus alias.
+    cost = calculate_cost(MODEL_MAP["opus"], tokens_input=_M, tokens_output=0)
+    assert cost > 0.0
+
+
 def test_no_lifecycle_role_routes_below_the_structured_verb_floor() -> None:
     # Retired haiku from lifecycle roles (2026-07-24): a haiku QA/documenter
     # can't emit the structured review envelopes (criteria_verified, findings)

tests/unit/runtime/test_intake_spawn.py

@@ -56,7 +56,7 @@ def _spec(**overrides: Any) -> _IntakeRunSpec:
         },
         "session_id": "sess-abc",
         "cwd": "/data/workspaces/roboco/board/intake-1",
-        "cli_model": "claude-opus-4-6",
+        "cli_model": "claude-opus-4-8",
         "api_url": "http://roboco-orchestrator:8000",
         "provider_base_url": None,
         "provider_auth_token": None,
@@ -108,7 +108,7 @@ class TestBuildIntakeRunCmd:
         assert "ROBOCO_WORKSPACE=/data/workspaces/roboco/board/intake-1" in cmd
         assert "ROBOCO_API_URL=http://roboco-orchestrator:8000" in cmd
         assert "ROBOCO_AGENT_ID=intake-1" in cmd
-        assert "CLAUDE_CODE_SUBAGENT_MODEL=claude-opus-4-6" in cmd
+        assert "CLAUDE_CODE_SUBAGENT_MODEL=claude-opus-4-8" in cmd
 
     def test_mounts_prompt_and_workspaces(self) -> None:
         cmd = AgentOrchestrator._build_intake_run_cmd(_spec())

tests/unit/runtime/test_orchestrator_manifest.py

@@ -99,7 +99,7 @@ class TestBuildManifestForAgent:
             mock_settings.manifest_host_dir = str(tmp_path)
             mock_settings.workspaces_root = str(tmp_path / "workspaces")
 
-            result = _build_manifest_for_agent("be-dev-1", "claude-opus-4-6")
+            result = _build_manifest_for_agent("be-dev-1", "claude-opus-4-8")
 
         assert result is not None
         data = json.loads(result.read_text())

tests/unit/runtime/test_spawn_manifest.py

@@ -87,7 +87,7 @@ class TestBuildForRole:
                 role=role,
                 team="board",
                 workspace_path=Path("/tmp/x"),
-                agent_model="claude-opus-4-6",
+                agent_model="claude-opus-4-8",
             )
         )
         assert "read_messages" in m.do_tools

tests/unit/services/test_audit_agent_id.py

@@ -182,7 +182,7 @@ async def test_log_agent_event_resolves_slug_to_uuid(
         event_type="agent.spawned",
         agent_slug=slug,
         task_id=task_id,
-        details={"container_id": "abc123def456", "model": "claude-opus-4-6"},
+        details={"container_id": "abc123def456", "model": "claude-opus-4-8"},
     )
 
     # Read back the row.

tests/unit/services/test_usage.py

@@ -945,7 +945,7 @@ class TestGetRecentSessions:
         row = MagicMock()
         row.id = sid
         row.agent_slug = "product-owner"
-        row.model = "claude-opus-4-6"
+        row.model = "claude-opus-4-8"
         row.started_at = datetime.datetime(2026, 6, 11, 20, 41, tzinfo=datetime.UTC)
         row.ended_at = datetime.datetime(2026, 6, 11, 20, 42, tzinfo=datetime.UTC)
         row.tokens_input = exp_in
@@ -966,7 +966,7 @@ class TestGetRecentSessions:
         s = out[0]
         assert s["id"] == str(sid)
         assert s["agent_slug"] == "product-owner"
-        assert s["model"] == "claude-opus-4-6"
+        assert s["model"] == "claude-opus-4-8"
         assert s["tokens_input"] == exp_in
         assert s["tokens_output"] == exp_out
         assert s["tokens_cache"] == exp_cr + exp_cw