Rename all arch references to plano (#745)

* Rename all arch references to plano across the codebase

Complete rebrand from "Arch"/"archgw" to "Plano" including:
- Config files: arch_config_schema.yaml, workflow, demo configs
- Environment variables: ARCH_CONFIG_* → PLANO_CONFIG_*
- Python CLI: variables, functions, file paths, docker mounts
- Rust crates: config paths, log messages, metadata keys
- Docker/build: Dockerfile, supervisord, .dockerignore, .gitignore
- Docker Compose: volume mounts and env vars across all demos/tests
- GitHub workflows: job/step names
- Shell scripts: log messages
- Demos: Python code, READMEs, VS Code configs, Grafana dashboard
- Docs: RST includes, code comments, config references
- Package metadata: package.json, pyproject.toml, uv.lock

External URLs (docs.archgw.com, github.com/katanemo/archgw) left as-is.

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

* Update remaining arch references in docs

- Rename RST cross-reference labels: arch_access_logging, arch_overview_tracing, arch_overview_threading → plano_*
- Update label references in request_lifecycle.rst
- Rename arch_config_state_storage_example.yaml → plano_config_state_storage_example.yaml
- Update config YAML comments: "Arch creates/uses" → "Plano creates/uses"
- Update "the Arch gateway" → "the Plano gateway" in configuration_reference.rst
- Update arch_config_schema.yaml reference in provider_models.py
- Rename arch_agent_router → plano_agent_router in config example

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

* 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>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

demos/shared/chatbot_ui/.vscode/launch.json

@@ -15,7 +15,7 @@
         "LLM": "1",
         "CHAT_COMPLETION_ENDPOINT": "http://localhost:10000/v1",
         "STREAMING": "True",
-        "ARCH_CONFIG": "../../samples_python/weather_forecast/arch_config.yaml"
+        "PLANO_CONFIG": "../../samples_python/weather_forecast/plano_config.yaml"
       }
     },
     {
@@ -29,7 +29,7 @@
         "LLM": "1",
         "CHAT_COMPLETION_ENDPOINT": "http://localhost:12000/v1",
         "STREAMING": "True",
-        "ARCH_CONFIG": "../../samples_python/weather_forecast/arch_config.yaml"
+        "PLANO_CONFIG": "../../samples_python/weather_forecast/plano_config.yaml"
       }
     },
   ]

demos/shared/chatbot_ui/common.py

@@ -37,7 +37,7 @@ def chat(
 
     try:
         response = client.chat.completions.create(
-            # we select model from arch_config file
+            # we select model from plano_config file
             model="None",
             messages=history,
             temperature=1.0,
@@ -86,7 +86,7 @@ def create_gradio_app(demo_description, client):
 
             with gr.Column(scale=2):
                 chatbot = gr.Chatbot(
-                    label="Arch Chatbot",
+                    label="Plano Chatbot",
                     elem_classes="chatbot",
                 )
                 textbox = gr.Textbox(
@@ -110,7 +110,7 @@ def process_stream_chunk(chunk, history):
     delta = chunk.choices[0].delta
     if delta.role and delta.role != history[-1]["role"]:
         # create new history item if role changes
-        # this is likely due to arch tool call and api response
+        # this is likely due to Plano tool call and api response
         history.append({"role": delta.role})
 
     history[-1]["model"] = chunk.model
@@ -159,7 +159,7 @@ def convert_prompt_target_to_openai_format(target):
 
 def get_prompt_targets():
     try:
-        with open(os.getenv("ARCH_CONFIG", "config.yaml"), "r") as file:
+        with open(os.getenv("PLANO_CONFIG", "config.yaml"), "r") as file:
             config = yaml.safe_load(file)
 
             available_tools = []
@@ -181,7 +181,7 @@ def get_prompt_targets():
 
 def get_llm_models():
     try:
-        with open(os.getenv("ARCH_CONFIG", "config.yaml"), "r") as file:
+        with open(os.getenv("PLANO_CONFIG", "config.yaml"), "r") as file:
             config = yaml.safe_load(file)
 
             available_models = [""]

demos/shared/grafana/dashboards/envoy_overview.json

@@ -787,7 +787,7 @@
   },
   "timepicker": {},
   "timezone": "browser",
-  "title": "Arch Gateway Dashboard",
+  "title": "Plano Gateway Dashboard",
   "uid": "adt6uhx5lk8aob",
   "version": 1,
   "weekStart": ""

demos/shared/test_runner/common.py

@@ -19,17 +19,17 @@ 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 []

demos/shared/test_runner/test_demos.py

@@ -1,6 +1,6 @@
 import json
 import os
-from common import get_arch_messages
+from common import get_plano_messages
 import pytest
 import requests
 from deepdiff import DeepDiff
@@ -46,10 +46,10 @@ def test_demos(test_data):
     assert choices[0]["message"]["role"] == "assistant"
     assert expected_output_contains.lower() in choices[0]["message"]["content"].lower()
 
-    # 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