Fix remaining arch references found in second pass

- config/docker-compose.dev.yaml: ARCH_CONFIG_FILE → PLANO_CONFIG_FILE,
  arch_config.yaml → plano_config.yaml, archgw_logs → plano_logs
- config/test_passthrough.yaml: container mount path
- tests/e2e/docker-compose.yaml: source file path (was still arch_config.yaml)
- cli/planoai/core.py: comment and log message
- crates/brightstaff/src/tracing/constants.rs: doc comment
- tests/{e2e,archgw}/common.py: get_arch_messages → get_plano_messages,
  arch_state/arch_messages variables renamed
- tests/{e2e,archgw}/test_prompt_gateway.py: updated imports and usages
- demos/shared/test_runner/{common,test_demos}.py: same renames
- tests/e2e/test_model_alias_routing.py: docstring
- .dockerignore: archgw_modelserver → plano_modelserver
- demos/use_cases/claude_code_router/pretty_model_resolution.sh: container name

Note: x-arch-* HTTP header values and Rust constant names intentionally
preserved for backwards compatibility with existing deployments.

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

tests/archgw/common.py

@@ -99,17 +99,17 @@ def get_data_chunks(stream, n=1):
     return chunks
 
 
-def get_arch_messages(response_json):
-    arch_messages = []
+def get_plano_messages(response_json):
+    plano_messages = []
     if response_json and "metadata" in response_json:
-        # load arch_state from metadata
-        arch_state_str = response_json.get("metadata", {}).get(ARCH_STATE_HEADER, "{}")
-        # parse arch_state into json object
-        arch_state = json.loads(arch_state_str)
-        # load messages from arch_state
-        arch_messages_str = arch_state.get("messages", "[]")
+        # load plano_state from metadata
+        plano_state_str = response_json.get("metadata", {}).get(ARCH_STATE_HEADER, "{}")
+        # parse plano_state into json object
+        plano_state = json.loads(plano_state_str)
+        # load messages from plano_state
+        plano_messages_str = plano_state.get("messages", "[]")
         # parse messages into json object
-        arch_messages = json.loads(arch_messages_str)
-        # append messages from arch gateway to history
-        return arch_messages
+        plano_messages = json.loads(plano_messages_str)
+        # append messages from plano gateway to history
+        return plano_messages
     return []

tests/archgw/test_prompt_gateway.py

@@ -18,7 +18,7 @@ def httpserver_listen_address():
 from common import (
     PROMPT_GATEWAY_ENDPOINT,
     TEST_CASE_FIXTURES,
-    get_arch_messages,
+    get_plano_messages,
 )
 
 
@@ -83,10 +83,10 @@ def test_prompt_gateway(httpserver: HTTPServer):
     assert assistant_message["role"] == "assistant"
     assert "content" in assistant_message
     assert "weather" in assistant_message["content"]
-    # now verify arch_messages (tool call and api response) that are sent as response metadata
-    arch_messages = get_arch_messages(response_json)
-    assert len(arch_messages) == 2
-    tool_calls_message = arch_messages[0]
+    # now verify plano_messages (tool call and api response) that are sent as response metadata
+    plano_messages = get_plano_messages(response_json)
+    assert len(plano_messages) == 2
+    tool_calls_message = plano_messages[0]
     tool_calls = tool_calls_message.get("tool_calls", [])
     assert len(tool_calls) > 0
     tool_call = normalize_tool_call_arguments(tool_calls[0]["function"])

tests/e2e/common.py

@@ -98,17 +98,17 @@ def get_data_chunks(stream, n=1):
     return chunks
 
 
-def get_arch_messages(response_json):
-    arch_messages = []
+def get_plano_messages(response_json):
+    plano_messages = []
     if response_json and "metadata" in response_json:
-        # load arch_state from metadata
-        arch_state_str = response_json.get("metadata", {}).get(ARCH_STATE_HEADER, "{}")
-        # parse arch_state into json object
-        arch_state = json.loads(arch_state_str)
-        # load messages from arch_state
-        arch_messages_str = arch_state.get("messages", "[]")
+        # load plano_state from metadata
+        plano_state_str = response_json.get("metadata", {}).get(ARCH_STATE_HEADER, "{}")
+        # parse plano_state into json object
+        plano_state = json.loads(plano_state_str)
+        # load messages from plano_state
+        plano_messages_str = plano_state.get("messages", "[]")
         # parse messages into json object
-        arch_messages = json.loads(arch_messages_str)
-        # append messages from arch gateway to history
-        return arch_messages
+        plano_messages = json.loads(plano_messages_str)
+        # append messages from plano gateway to history
+        return plano_messages
     return []

tests/e2e/docker-compose.yaml

@@ -8,7 +8,7 @@ services:
       - "12000:12000"
       - "19901:9901"
     volumes:
-      - ../../demos/samples_python/weather_forecast/arch_config.yaml:/app/plano_config.yaml
+      - ../../demos/samples_python/weather_forecast/plano_config.yaml:/app/plano_config.yaml
       - /etc/ssl/cert.pem:/etc/ssl/cert.pem
     extra_hosts:
       - "host.docker.internal:host-gateway"

tests/e2e/test_model_alias_routing.py

@@ -260,7 +260,7 @@ def test_anthropic_client_with_alias_streaming():
 
 
 def test_400_error_handling_with_alias():
-    """Test that 400 errors from upstream are properly returned by archgw"""
+    """Test that 400 errors from upstream are properly returned by plano"""
     logger.info(
         "Testing 400 error handling with arch.summarize.v1 and invalid parameter"
     )

tests/e2e/test_prompt_gateway.py

@@ -10,7 +10,7 @@ from common import (
     PROMPT_GATEWAY_ENDPOINT,
     LLM_GATEWAY_ENDPOINT,
     PREFILL_LIST,
-    get_arch_messages,
+    get_plano_messages,
     get_data_chunks,
 )
 
@@ -117,11 +117,11 @@ def test_prompt_gateway(stream):
         assert len(choices) > 0
         assert "role" in choices[0]["message"]
         assert choices[0]["message"]["role"] == "assistant"
-        # now verify arch_messages (tool call and api response) that are sent as response metadata
-        arch_messages = get_arch_messages(response_json)
-        print("arch_messages: ", json.dumps(arch_messages))
-        assert len(arch_messages) == 2
-        tool_calls_message = arch_messages[0]
+        # now verify plano_messages (tool call and api response) that are sent as response metadata
+        plano_messages = get_plano_messages(response_json)
+        print("plano_messages: ", json.dumps(plano_messages))
+        assert len(plano_messages) == 2
+        tool_calls_message = plano_messages[0]
         print("tool_calls_message: ", tool_calls_message)
         tool_calls = tool_calls_message.get("content", [])
         cleaned_tool_call_str = cleanup_tool_call(tool_calls)
@@ -295,10 +295,10 @@ def test_prompt_gateway_param_tool_call(stream):
         assert len(choices) > 0
         assert "role" in choices[0]["message"]
         assert choices[0]["message"]["role"] == "assistant"
-        # now verify arch_messages (tool call and api response) that are sent as response metadata
-        arch_messages = get_arch_messages(response_json)
-        assert len(arch_messages) == 2
-        tool_calls_message = arch_messages[0]
+        # now verify plano_messages (tool call and api response) that are sent as response metadata
+        plano_messages = get_plano_messages(response_json)
+        assert len(plano_messages) == 2
+        tool_calls_message = plano_messages[0]
         tool_calls = tool_calls_message.get("tool_calls", [])
         assert len(tool_calls) > 0
         tool_call = normalize_tool_call_arguments(tool_calls[0]["function"])