mirror of
https://github.com/katanemo/plano.git
synced 2026-06-17 15:25:17 +02:00
Merge remote-tracking branch 'origin/main' into musa/cli
This commit is contained in:
Musa
commit
0416573c82
293 changed files with 8728 additions and 9045 deletions
|
|
@ -1,3 +1,3 @@
|
|||
"""Plano CLI - Intelligent Prompt Gateway."""
|
||||
|
||||
__version__ = "0.4.6"
|
||||
__version__ = "0.4.7"
|
||||
|
|
|
|||
|
|
@ -53,34 +53,34 @@ def validate_and_render_schema():
|
|||
ENVOY_CONFIG_TEMPLATE_FILE = os.getenv(
|
||||
"ENVOY_CONFIG_TEMPLATE_FILE", "envoy.template.yaml"
|
||||
)
|
||||
ARCH_CONFIG_FILE = os.getenv("ARCH_CONFIG_FILE", "/app/arch_config.yaml")
|
||||
ARCH_CONFIG_FILE_RENDERED = os.getenv(
|
||||
"ARCH_CONFIG_FILE_RENDERED", "/app/arch_config_rendered.yaml"
|
||||
PLANO_CONFIG_FILE = os.getenv("PLANO_CONFIG_FILE", "/app/plano_config.yaml")
|
||||
PLANO_CONFIG_FILE_RENDERED = os.getenv(
|
||||
"PLANO_CONFIG_FILE_RENDERED", "/app/plano_config_rendered.yaml"
|
||||
)
|
||||
ENVOY_CONFIG_FILE_RENDERED = os.getenv(
|
||||
"ENVOY_CONFIG_FILE_RENDERED", "/etc/envoy/envoy.yaml"
|
||||
)
|
||||
ARCH_CONFIG_SCHEMA_FILE = os.getenv(
|
||||
"ARCH_CONFIG_SCHEMA_FILE", "arch_config_schema.yaml"
|
||||
PLANO_CONFIG_SCHEMA_FILE = os.getenv(
|
||||
"PLANO_CONFIG_SCHEMA_FILE", "plano_config_schema.yaml"
|
||||
)
|
||||
|
||||
env = Environment(loader=FileSystemLoader(os.getenv("TEMPLATE_ROOT", "./")))
|
||||
template = env.get_template(ENVOY_CONFIG_TEMPLATE_FILE)
|
||||
|
||||
try:
|
||||
validate_prompt_config(ARCH_CONFIG_FILE, ARCH_CONFIG_SCHEMA_FILE)
|
||||
validate_prompt_config(PLANO_CONFIG_FILE, PLANO_CONFIG_SCHEMA_FILE)
|
||||
except Exception as e:
|
||||
print(str(e))
|
||||
exit(1) # validate_prompt_config failed. Exit
|
||||
|
||||
with open(ARCH_CONFIG_FILE, "r") as file:
|
||||
arch_config = file.read()
|
||||
with open(PLANO_CONFIG_FILE, "r") as file:
|
||||
plano_config = file.read()
|
||||
|
||||
with open(ARCH_CONFIG_SCHEMA_FILE, "r") as file:
|
||||
arch_config_schema = file.read()
|
||||
with open(PLANO_CONFIG_SCHEMA_FILE, "r") as file:
|
||||
plano_config_schema = file.read()
|
||||
|
||||
config_yaml = yaml.safe_load(arch_config)
|
||||
_ = yaml.safe_load(arch_config_schema)
|
||||
config_yaml = yaml.safe_load(plano_config)
|
||||
_ = yaml.safe_load(plano_config_schema)
|
||||
inferred_clusters = {}
|
||||
|
||||
# Convert legacy llm_providers to model_providers
|
||||
|
|
@ -145,7 +145,7 @@ def validate_and_render_schema():
|
|||
inferred_clusters[name]["port"],
|
||||
) = get_endpoint_and_port(endpoint, protocol)
|
||||
|
||||
print("defined clusters from arch_config.yaml: ", json.dumps(inferred_clusters))
|
||||
print("defined clusters from plano_config.yaml: ", json.dumps(inferred_clusters))
|
||||
|
||||
if "prompt_targets" in config_yaml:
|
||||
for prompt_target in config_yaml["prompt_targets"]:
|
||||
|
|
@ -154,13 +154,13 @@ def validate_and_render_schema():
|
|||
continue
|
||||
if name not in inferred_clusters:
|
||||
raise Exception(
|
||||
f"Unknown endpoint {name}, please add it in endpoints section in your arch_config.yaml file"
|
||||
f"Unknown endpoint {name}, please add it in endpoints section in your plano_config.yaml file"
|
||||
)
|
||||
|
||||
arch_tracing = config_yaml.get("tracing", {})
|
||||
plano_tracing = config_yaml.get("tracing", {})
|
||||
|
||||
# Resolution order: config yaml > OTEL_TRACING_GRPC_ENDPOINT env var > hardcoded default
|
||||
opentracing_grpc_endpoint = arch_tracing.get(
|
||||
opentracing_grpc_endpoint = plano_tracing.get(
|
||||
"opentracing_grpc_endpoint",
|
||||
os.environ.get(
|
||||
"OTEL_TRACING_GRPC_ENDPOINT", DEFAULT_OTEL_TRACING_GRPC_ENDPOINT
|
||||
|
|
@ -172,7 +172,7 @@ def validate_and_render_schema():
|
|||
print(
|
||||
f"Resolved opentracing_grpc_endpoint to {opentracing_grpc_endpoint} after expanding environment variables"
|
||||
)
|
||||
arch_tracing["opentracing_grpc_endpoint"] = opentracing_grpc_endpoint
|
||||
plano_tracing["opentracing_grpc_endpoint"] = opentracing_grpc_endpoint
|
||||
# ensure that opentracing_grpc_endpoint is a valid URL if present and start with http and must not have any path
|
||||
if opentracing_grpc_endpoint:
|
||||
urlparse_result = urlparse(opentracing_grpc_endpoint)
|
||||
|
|
@ -436,8 +436,8 @@ def validate_and_render_schema():
|
|||
f"Model alias 2 - '{alias_name}' targets '{target}' which is not defined as a model. Available models: {', '.join(sorted(model_name_keys))}"
|
||||
)
|
||||
|
||||
arch_config_string = yaml.dump(config_yaml)
|
||||
arch_llm_config_string = yaml.dump(config_yaml)
|
||||
plano_config_string = yaml.dump(config_yaml)
|
||||
plano_llm_config_string = yaml.dump(config_yaml)
|
||||
|
||||
use_agent_orchestrator = config_yaml.get("overrides", {}).get(
|
||||
"use_agent_orchestrator", False
|
||||
|
|
@ -449,11 +449,11 @@ def validate_and_render_schema():
|
|||
|
||||
if len(endpoints) == 0:
|
||||
raise Exception(
|
||||
"Please provide agent orchestrator in the endpoints section in your arch_config.yaml file"
|
||||
"Please provide agent orchestrator in the endpoints section in your plano_config.yaml file"
|
||||
)
|
||||
elif len(endpoints) > 1:
|
||||
raise Exception(
|
||||
"Please provide single agent orchestrator in the endpoints section in your arch_config.yaml file"
|
||||
"Please provide single agent orchestrator in the endpoints section in your plano_config.yaml file"
|
||||
)
|
||||
else:
|
||||
agent_orchestrator = list(endpoints.keys())[0]
|
||||
|
|
@ -463,11 +463,11 @@ def validate_and_render_schema():
|
|||
data = {
|
||||
"prompt_gateway_listener": prompt_gateway,
|
||||
"llm_gateway_listener": llm_gateway,
|
||||
"arch_config": arch_config_string,
|
||||
"arch_llm_config": arch_llm_config_string,
|
||||
"arch_clusters": inferred_clusters,
|
||||
"arch_model_providers": updated_model_providers,
|
||||
"arch_tracing": arch_tracing,
|
||||
"plano_config": plano_config_string,
|
||||
"plano_llm_config": plano_llm_config_string,
|
||||
"plano_clusters": inferred_clusters,
|
||||
"plano_model_providers": updated_model_providers,
|
||||
"plano_tracing": plano_tracing,
|
||||
"local_llms": llms_with_endpoint,
|
||||
"agent_orchestrator": agent_orchestrator,
|
||||
"listeners": listeners,
|
||||
|
|
@ -479,25 +479,25 @@ def validate_and_render_schema():
|
|||
with open(ENVOY_CONFIG_FILE_RENDERED, "w") as file:
|
||||
file.write(rendered)
|
||||
|
||||
with open(ARCH_CONFIG_FILE_RENDERED, "w") as file:
|
||||
file.write(arch_config_string)
|
||||
with open(PLANO_CONFIG_FILE_RENDERED, "w") as file:
|
||||
file.write(plano_config_string)
|
||||
|
||||
|
||||
def validate_prompt_config(arch_config_file, arch_config_schema_file):
|
||||
with open(arch_config_file, "r") as file:
|
||||
arch_config = file.read()
|
||||
def validate_prompt_config(plano_config_file, plano_config_schema_file):
|
||||
with open(plano_config_file, "r") as file:
|
||||
plano_config = file.read()
|
||||
|
||||
with open(arch_config_schema_file, "r") as file:
|
||||
arch_config_schema = file.read()
|
||||
with open(plano_config_schema_file, "r") as file:
|
||||
plano_config_schema = file.read()
|
||||
|
||||
config_yaml = yaml.safe_load(arch_config)
|
||||
config_schema_yaml = yaml.safe_load(arch_config_schema)
|
||||
config_yaml = yaml.safe_load(plano_config)
|
||||
config_schema_yaml = yaml.safe_load(plano_config_schema)
|
||||
|
||||
try:
|
||||
validate(config_yaml, config_schema_yaml)
|
||||
except Exception as e:
|
||||
print(
|
||||
f"Error validating arch_config file: {arch_config_file}, schema file: {arch_config_schema_file}, error: {e}"
|
||||
f"Error validating plano_config file: {plano_config_file}, schema file: {plano_config_schema_file}, error: {e}"
|
||||
)
|
||||
raise e
|
||||
|
||||
|
|
|
|||
|
|
@ -5,5 +5,5 @@ PLANO_COLOR = "#969FF4"
|
|||
|
||||
SERVICE_NAME_ARCHGW = "plano"
|
||||
PLANO_DOCKER_NAME = "plano"
|
||||
PLANO_DOCKER_IMAGE = os.getenv("PLANO_DOCKER_IMAGE", "katanemo/plano:0.4.6")
|
||||
PLANO_DOCKER_IMAGE = os.getenv("PLANO_DOCKER_IMAGE", "katanemo/plano:0.4.7")
|
||||
DEFAULT_OTEL_TRACING_GRPC_ENDPOINT = "http://host.docker.internal:4317"
|
||||
|
|
|
|||
|
|
@ -24,17 +24,17 @@ from planoai.docker_cli import (
|
|||
log = getLogger(__name__)
|
||||
|
||||
|
||||
def _get_gateway_ports(arch_config_file: str) -> list[int]:
|
||||
def _get_gateway_ports(plano_config_file: str) -> list[int]:
|
||||
PROMPT_GATEWAY_DEFAULT_PORT = 10000
|
||||
LLM_GATEWAY_DEFAULT_PORT = 12000
|
||||
|
||||
# parse arch_config_file yaml file and get prompt_gateway_port
|
||||
arch_config_dict = {}
|
||||
with open(arch_config_file) as f:
|
||||
arch_config_dict = yaml.safe_load(f)
|
||||
# parse plano_config_file yaml file and get prompt_gateway_port
|
||||
plano_config_dict = {}
|
||||
with open(plano_config_file) as f:
|
||||
plano_config_dict = yaml.safe_load(f)
|
||||
|
||||
listeners, _, _ = convert_legacy_listeners(
|
||||
arch_config_dict.get("listeners"), arch_config_dict.get("llm_providers")
|
||||
plano_config_dict.get("listeners"), plano_config_dict.get("llm_providers")
|
||||
)
|
||||
|
||||
all_ports = [listener.get("port") for listener in listeners]
|
||||
|
|
@ -45,7 +45,7 @@ def _get_gateway_ports(arch_config_file: str) -> list[int]:
|
|||
return all_ports
|
||||
|
||||
|
||||
def start_arch(arch_config_file, env, log_timeout=120, foreground=False):
|
||||
def start_plano(plano_config_file, env, log_timeout=120, foreground=False):
|
||||
"""
|
||||
Start Docker Compose in detached mode and stream logs until services are healthy.
|
||||
|
||||
|
|
@ -54,7 +54,7 @@ def start_arch(arch_config_file, env, log_timeout=120, foreground=False):
|
|||
log_timeout (int): Time in seconds to show logs before checking for healthy state.
|
||||
"""
|
||||
log.info(
|
||||
f"Starting arch gateway, image name: {PLANO_DOCKER_NAME}, tag: {PLANO_DOCKER_IMAGE}"
|
||||
f"Starting plano gateway, image name: {PLANO_DOCKER_NAME}, tag: {PLANO_DOCKER_IMAGE}"
|
||||
)
|
||||
|
||||
try:
|
||||
|
|
@ -64,10 +64,10 @@ def start_arch(arch_config_file, env, log_timeout=120, foreground=False):
|
|||
docker_stop_container(PLANO_DOCKER_NAME)
|
||||
docker_remove_container(PLANO_DOCKER_NAME)
|
||||
|
||||
gateway_ports = _get_gateway_ports(arch_config_file)
|
||||
gateway_ports = _get_gateway_ports(plano_config_file)
|
||||
|
||||
return_code, _, plano_stderr = docker_start_plano_detached(
|
||||
arch_config_file,
|
||||
plano_config_file,
|
||||
env,
|
||||
gateway_ports,
|
||||
)
|
||||
|
|
@ -117,7 +117,7 @@ def start_arch(arch_config_file, env, log_timeout=120, foreground=False):
|
|||
stream_gateway_logs(follow=True)
|
||||
|
||||
except KeyboardInterrupt:
|
||||
log.info("Keyboard interrupt received, stopping arch gateway service.")
|
||||
log.info("Keyboard interrupt received, stopping plano gateway service.")
|
||||
stop_docker_container()
|
||||
|
||||
|
||||
|
|
@ -144,15 +144,15 @@ def stop_docker_container(service=PLANO_DOCKER_NAME):
|
|||
log.info(f"Failed to shut down services: {str(e)}")
|
||||
|
||||
|
||||
def start_cli_agent(arch_config_file=None, settings_json="{}"):
|
||||
def start_cli_agent(plano_config_file=None, settings_json="{}"):
|
||||
"""Start a CLI client connected to Plano."""
|
||||
|
||||
with open(arch_config_file, "r") as file:
|
||||
arch_config = file.read()
|
||||
arch_config_yaml = yaml.safe_load(arch_config)
|
||||
with open(plano_config_file, "r") as file:
|
||||
plano_config = file.read()
|
||||
plano_config_yaml = yaml.safe_load(plano_config)
|
||||
|
||||
# Get egress listener configuration
|
||||
egress_config = arch_config_yaml.get("listeners", {}).get("egress_traffic", {})
|
||||
egress_config = plano_config_yaml.get("listeners", {}).get("egress_traffic", {})
|
||||
host = egress_config.get("host", "127.0.0.1")
|
||||
port = egress_config.get("port", 12000)
|
||||
|
||||
|
|
@ -167,7 +167,7 @@ def start_cli_agent(arch_config_file=None, settings_json="{}"):
|
|||
env = os.environ.copy()
|
||||
env.update(
|
||||
{
|
||||
"ANTHROPIC_AUTH_TOKEN": "test", # Use test token for arch
|
||||
"ANTHROPIC_AUTH_TOKEN": "test", # Use test token for plano
|
||||
"ANTHROPIC_API_KEY": "",
|
||||
"ANTHROPIC_BASE_URL": f"http://{host}:{port}",
|
||||
"NO_PROXY": host,
|
||||
|
|
@ -184,7 +184,7 @@ def start_cli_agent(arch_config_file=None, settings_json="{}"):
|
|||
]
|
||||
else:
|
||||
# Check if arch.claude.code.small.fast alias exists in model_aliases
|
||||
model_aliases = arch_config_yaml.get("model_aliases", {})
|
||||
model_aliases = plano_config_yaml.get("model_aliases", {})
|
||||
if "arch.claude.code.small.fast" in model_aliases:
|
||||
env["ANTHROPIC_SMALL_FAST_MODEL"] = "arch.claude.code.small.fast"
|
||||
else:
|
||||
|
|
@ -220,7 +220,7 @@ def start_cli_agent(arch_config_file=None, settings_json="{}"):
|
|||
|
||||
# Use claude from PATH
|
||||
claude_path = "claude"
|
||||
log.info(f"Connecting Claude Code Agent to Arch at {host}:{port}")
|
||||
log.info(f"Connecting Claude Code Agent to Plano at {host}:{port}")
|
||||
|
||||
try:
|
||||
subprocess.run([claude_path] + claude_args, env=env, check=True)
|
||||
|
|
|
|||
|
|
@ -41,7 +41,7 @@ def docker_remove_container(container: str) -> str:
|
|||
|
||||
|
||||
def docker_start_plano_detached(
|
||||
arch_config_file: str,
|
||||
plano_config_file: str,
|
||||
env: dict,
|
||||
gateway_ports: list[int],
|
||||
) -> str:
|
||||
|
|
@ -58,7 +58,7 @@ def docker_start_plano_detached(
|
|||
port_mappings_args = [item for port in port_mappings for item in ("-p", port)]
|
||||
|
||||
volume_mappings = [
|
||||
f"{arch_config_file}:/app/arch_config.yaml:ro",
|
||||
f"{plano_config_file}:/app/plano_config.yaml:ro",
|
||||
]
|
||||
volume_mappings_args = [
|
||||
item for volume in volume_mappings for item in ("-v", volume)
|
||||
|
|
@ -115,7 +115,7 @@ def stream_gateway_logs(follow, service="plano"):
|
|||
log.info(f"Failed to stream logs: {str(e)}")
|
||||
|
||||
|
||||
def docker_validate_plano_schema(arch_config_file):
|
||||
def docker_validate_plano_schema(plano_config_file):
|
||||
import os
|
||||
|
||||
env = os.environ.copy()
|
||||
|
|
@ -129,7 +129,7 @@ def docker_validate_plano_schema(arch_config_file):
|
|||
"--rm",
|
||||
*env_args,
|
||||
"-v",
|
||||
f"{arch_config_file}:/app/arch_config.yaml:ro",
|
||||
f"{plano_config_file}:/app/plano_config.yaml:ro",
|
||||
"--entrypoint",
|
||||
"python",
|
||||
PLANO_DOCKER_IMAGE,
|
||||
|
|
|
|||
|
|
@ -22,7 +22,7 @@ from planoai.utils import (
|
|||
find_repo_root,
|
||||
)
|
||||
from planoai.core import (
|
||||
start_arch,
|
||||
start_plano,
|
||||
stop_docker_container,
|
||||
start_cli_agent,
|
||||
)
|
||||
|
|
@ -45,7 +45,7 @@ def _is_port_in_use(port: int) -> bool:
|
|||
|
||||
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
|
||||
try:
|
||||
s.bind(("0.0.0.0", port))
|
||||
s.bind(("0.0.0.0", port)) # noqa: S104
|
||||
return False
|
||||
except OSError:
|
||||
return True
|
||||
|
|
@ -200,12 +200,12 @@ def up(file, path, foreground, with_tracing, tracing_port):
|
|||
_print_cli_header(console)
|
||||
|
||||
# Use the utility function to find config file
|
||||
arch_config_file = find_config_file(path, file)
|
||||
plano_config_file = find_config_file(path, file)
|
||||
|
||||
# Check if the file exists
|
||||
if not os.path.exists(arch_config_file):
|
||||
if not os.path.exists(plano_config_file):
|
||||
console.print(
|
||||
f"[red]✗[/red] Config file not found: [dim]{arch_config_file}[/dim]"
|
||||
f"[red]✗[/red] Config file not found: [dim]{plano_config_file}[/dim]"
|
||||
)
|
||||
sys.exit(1)
|
||||
|
||||
|
|
@ -216,7 +216,7 @@ def up(file, path, foreground, with_tracing, tracing_port):
|
|||
validation_return_code,
|
||||
_,
|
||||
validation_stderr,
|
||||
) = docker_validate_plano_schema(arch_config_file)
|
||||
) = docker_validate_plano_schema(plano_config_file)
|
||||
|
||||
if validation_return_code != 0:
|
||||
console.print(f"[red]✗[/red] Validation failed")
|
||||
|
|
@ -234,7 +234,7 @@ def up(file, path, foreground, with_tracing, tracing_port):
|
|||
env.pop("PATH", None)
|
||||
|
||||
# Check access keys
|
||||
access_keys = get_llm_provider_access_keys(arch_config_file=arch_config_file)
|
||||
access_keys = get_llm_provider_access_keys(plano_config_file=plano_config_file)
|
||||
access_keys = set(access_keys)
|
||||
access_keys = [item[1:] if item.startswith("$") else item for item in access_keys]
|
||||
|
||||
|
|
@ -302,7 +302,7 @@ def up(file, path, foreground, with_tracing, tracing_port):
|
|||
|
||||
env.update(env_stage)
|
||||
try:
|
||||
start_arch(arch_config_file, env, foreground=foreground)
|
||||
start_plano(plano_config_file, env, foreground=foreground)
|
||||
|
||||
# When tracing is enabled but --foreground is not, keep the process
|
||||
# alive so the OTLP collector continues to receive spans.
|
||||
|
|
@ -363,35 +363,35 @@ def generate_prompt_targets(file):
|
|||
def logs(debug, follow):
|
||||
"""Stream logs from access logs services."""
|
||||
|
||||
archgw_process = None
|
||||
plano_process = None
|
||||
try:
|
||||
if debug:
|
||||
archgw_process = multiprocessing.Process(
|
||||
plano_process = multiprocessing.Process(
|
||||
target=stream_gateway_logs, args=(follow,)
|
||||
)
|
||||
archgw_process.start()
|
||||
plano_process.start()
|
||||
|
||||
archgw_access_logs_process = multiprocessing.Process(
|
||||
plano_access_logs_process = multiprocessing.Process(
|
||||
target=stream_access_logs, args=(follow,)
|
||||
)
|
||||
archgw_access_logs_process.start()
|
||||
archgw_access_logs_process.join()
|
||||
plano_access_logs_process.start()
|
||||
plano_access_logs_process.join()
|
||||
|
||||
if archgw_process:
|
||||
archgw_process.join()
|
||||
if plano_process:
|
||||
plano_process.join()
|
||||
except KeyboardInterrupt:
|
||||
log.info("KeyboardInterrupt detected. Exiting.")
|
||||
if archgw_access_logs_process.is_alive():
|
||||
archgw_access_logs_process.terminate()
|
||||
if archgw_process and archgw_process.is_alive():
|
||||
archgw_process.terminate()
|
||||
if plano_access_logs_process.is_alive():
|
||||
plano_access_logs_process.terminate()
|
||||
if plano_process and plano_process.is_alive():
|
||||
plano_process.terminate()
|
||||
|
||||
|
||||
@click.command()
|
||||
@click.argument("type", type=click.Choice(["claude"]), required=True)
|
||||
@click.argument("file", required=False) # Optional file argument
|
||||
@click.option(
|
||||
"--path", default=".", help="Path to the directory containing arch_config.yaml"
|
||||
"--path", default=".", help="Path to the directory containing plano_config.yaml"
|
||||
)
|
||||
@click.option(
|
||||
"--settings",
|
||||
|
|
@ -405,20 +405,20 @@ def cli_agent(type, file, path, settings):
|
|||
"""
|
||||
|
||||
# Check if plano docker container is running
|
||||
archgw_status = docker_container_status(PLANO_DOCKER_NAME)
|
||||
if archgw_status != "running":
|
||||
log.error(f"plano docker container is not running (status: {archgw_status})")
|
||||
plano_status = docker_container_status(PLANO_DOCKER_NAME)
|
||||
if plano_status != "running":
|
||||
log.error(f"plano docker container is not running (status: {plano_status})")
|
||||
log.error("Please start plano using the 'planoai up' command.")
|
||||
sys.exit(1)
|
||||
|
||||
# Determine arch_config.yaml path
|
||||
arch_config_file = find_config_file(path, file)
|
||||
if not os.path.exists(arch_config_file):
|
||||
log.error(f"Config file not found: {arch_config_file}")
|
||||
# Determine plano_config.yaml path
|
||||
plano_config_file = find_config_file(path, file)
|
||||
if not os.path.exists(plano_config_file):
|
||||
log.error(f"Config file not found: {plano_config_file}")
|
||||
sys.exit(1)
|
||||
|
||||
try:
|
||||
start_cli_agent(arch_config_file, settings)
|
||||
start_cli_agent(plano_config_file, settings)
|
||||
except SystemExit:
|
||||
# Re-raise SystemExit to preserve exit codes
|
||||
raise
|
||||
|
|
|
|||
|
|
@ -1,13 +1,6 @@
|
|||
version: v0.1
|
||||
version: v0.3.0
|
||||
|
||||
listeners:
|
||||
egress_traffic:
|
||||
address: 0.0.0.0
|
||||
port: 12000
|
||||
message_format: openai
|
||||
timeout: 30s
|
||||
|
||||
llm_providers:
|
||||
model_providers:
|
||||
# OpenAI Models
|
||||
- model: openai/gpt-5-2025-08-07
|
||||
access_key: $OPENAI_API_KEY
|
||||
|
|
@ -39,5 +32,10 @@ model_aliases:
|
|||
arch.claude.code.small.fast:
|
||||
target: claude-haiku-4-5
|
||||
|
||||
listeners:
|
||||
- type: model
|
||||
name: model_listener
|
||||
port: 12000
|
||||
|
||||
tracing:
|
||||
random_sampling: 100
|
||||
|
|
|
|||
|
|
@ -1,25 +1,36 @@
|
|||
version: v0.1
|
||||
version: v0.3.0
|
||||
|
||||
listeners:
|
||||
egress_traffic:
|
||||
address: 0.0.0.0
|
||||
port: 12000
|
||||
message_format: openai
|
||||
timeout: 30s
|
||||
|
||||
llm_providers:
|
||||
agents:
|
||||
- id: assistant
|
||||
url: http://localhost:10510
|
||||
|
||||
model_providers:
|
||||
# OpenAI Models
|
||||
- model: openai/gpt-5-mini-2025-08-07
|
||||
access_key: $OPENAI_API_KEY
|
||||
default: true
|
||||
|
||||
# Anthropic Models
|
||||
# Anthropic Models
|
||||
- model: anthropic/claude-sonnet-4-20250514
|
||||
access_key: $ANTHROPIC_API_KEY
|
||||
|
||||
listeners:
|
||||
- type: agent
|
||||
name: conversation_service
|
||||
port: 8001
|
||||
router: plano_orchestrator_v1
|
||||
agents:
|
||||
- id: assistant
|
||||
description: |
|
||||
A conversational assistant that maintains context across multi-turn
|
||||
conversations. It can answer follow-up questions, remember previous
|
||||
context, and provide coherent responses in ongoing dialogues.
|
||||
|
||||
# State storage configuration for v1/responses API
|
||||
# Manages conversation state for multi-turn conversations
|
||||
state_storage:
|
||||
# Type: memory | postgres
|
||||
type: memory
|
||||
|
||||
tracing:
|
||||
random_sampling: 100
|
||||
|
|
|
|||
|
|
@ -1,13 +1,6 @@
|
|||
version: v0.1.0
|
||||
version: v0.3.0
|
||||
|
||||
listeners:
|
||||
egress_traffic:
|
||||
address: 0.0.0.0
|
||||
port: 12000
|
||||
message_format: openai
|
||||
timeout: 30s
|
||||
|
||||
llm_providers:
|
||||
model_providers:
|
||||
|
||||
- model: openai/gpt-4o-mini
|
||||
access_key: $OPENAI_API_KEY
|
||||
|
|
@ -25,5 +18,10 @@ llm_providers:
|
|||
- name: code generation
|
||||
description: generating new code snippets, functions, or boilerplate based on user prompts or requirements
|
||||
|
||||
listeners:
|
||||
- type: model
|
||||
name: model_listener
|
||||
port: 12000
|
||||
|
||||
tracing:
|
||||
random_sampling: 100
|
||||
|
|
|
|||
|
|
@ -31,6 +31,17 @@ MAX_TRACES = 50
|
|||
MAX_SPANS_PER_TRACE = 500
|
||||
|
||||
|
||||
class TraceListenerBindError(RuntimeError):
|
||||
"""Raised when the OTLP/gRPC listener cannot bind to the requested address."""
|
||||
|
||||
|
||||
def _trace_listener_bind_error_message(address: str) -> str:
|
||||
return (
|
||||
f"Failed to start OTLP listener on {address}: address is already in use.\n"
|
||||
"Stop the process using that port or run `planoai trace listen --port <PORT>`."
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class TraceSummary:
|
||||
trace_id: str
|
||||
|
|
@ -496,7 +507,15 @@ def _start_trace_server(host: str, grpc_port: int) -> grpc.Server:
|
|||
trace_service_pb2_grpc.add_TraceServiceServicer_to_server(
|
||||
_OTLPTraceServicer(), grpc_server
|
||||
)
|
||||
grpc_server.add_insecure_port(f"{host}:{grpc_port}")
|
||||
address = f"{host}:{grpc_port}"
|
||||
try:
|
||||
bound_port = grpc_server.add_insecure_port(address)
|
||||
except RuntimeError as exc:
|
||||
raise TraceListenerBindError(
|
||||
_trace_listener_bind_error_message(address)
|
||||
) from exc
|
||||
if bound_port == 0:
|
||||
raise TraceListenerBindError(_trace_listener_bind_error_message(address))
|
||||
grpc_server.start()
|
||||
return grpc_server
|
||||
|
||||
|
|
|
|||
|
|
@ -68,19 +68,19 @@ def find_repo_root(start_path=None):
|
|||
return None
|
||||
|
||||
|
||||
def has_ingress_listener(arch_config_file):
|
||||
"""Check if the arch config file has ingress_traffic listener configured."""
|
||||
def has_ingress_listener(plano_config_file):
|
||||
"""Check if the plano config file has ingress_traffic listener configured."""
|
||||
try:
|
||||
with open(arch_config_file) as f:
|
||||
arch_config_dict = yaml.safe_load(f)
|
||||
with open(plano_config_file) as f:
|
||||
plano_config_dict = yaml.safe_load(f)
|
||||
|
||||
ingress_traffic = arch_config_dict.get("listeners", {}).get(
|
||||
ingress_traffic = plano_config_dict.get("listeners", {}).get(
|
||||
"ingress_traffic", {}
|
||||
)
|
||||
|
||||
return bool(ingress_traffic)
|
||||
except Exception as e:
|
||||
log.error(f"Error reading config file {arch_config_file}: {e}")
|
||||
log.error(f"Error reading config file {plano_config_file}: {e}")
|
||||
return False
|
||||
|
||||
|
||||
|
|
@ -154,34 +154,37 @@ def convert_legacy_listeners(
|
|||
)
|
||||
listener["model_providers"] = model_providers or []
|
||||
model_provider_set = True
|
||||
llm_gateway_listener = listener
|
||||
# Merge user listener values into defaults for the Envoy template
|
||||
llm_gateway_listener = {**llm_gateway_listener, **listener}
|
||||
elif listener.get("type") == "prompt":
|
||||
prompt_gateway_listener = {**prompt_gateway_listener, **listener}
|
||||
if not model_provider_set:
|
||||
listeners.append(llm_gateway_listener)
|
||||
|
||||
return listeners, llm_gateway_listener, prompt_gateway_listener
|
||||
|
||||
|
||||
def get_llm_provider_access_keys(arch_config_file):
|
||||
with open(arch_config_file, "r") as file:
|
||||
arch_config = file.read()
|
||||
arch_config_yaml = yaml.safe_load(arch_config)
|
||||
def get_llm_provider_access_keys(plano_config_file):
|
||||
with open(plano_config_file, "r") as file:
|
||||
plano_config = file.read()
|
||||
plano_config_yaml = yaml.safe_load(plano_config)
|
||||
|
||||
access_key_list = []
|
||||
|
||||
# Convert legacy llm_providers to model_providers
|
||||
if "llm_providers" in arch_config_yaml:
|
||||
if "model_providers" in arch_config_yaml:
|
||||
if "llm_providers" in plano_config_yaml:
|
||||
if "model_providers" in plano_config_yaml:
|
||||
raise Exception(
|
||||
"Please provide either llm_providers or model_providers, not both. llm_providers is deprecated, please use model_providers instead"
|
||||
)
|
||||
arch_config_yaml["model_providers"] = arch_config_yaml["llm_providers"]
|
||||
del arch_config_yaml["llm_providers"]
|
||||
plano_config_yaml["model_providers"] = plano_config_yaml["llm_providers"]
|
||||
del plano_config_yaml["llm_providers"]
|
||||
|
||||
listeners, _, _ = convert_legacy_listeners(
|
||||
arch_config_yaml.get("listeners"), arch_config_yaml.get("model_providers")
|
||||
plano_config_yaml.get("listeners"), plano_config_yaml.get("model_providers")
|
||||
)
|
||||
|
||||
for prompt_target in arch_config_yaml.get("prompt_targets", []):
|
||||
for prompt_target in plano_config_yaml.get("prompt_targets", []):
|
||||
for k, v in prompt_target.get("endpoint", {}).get("http_headers", {}).items():
|
||||
if k.lower() == "authorization":
|
||||
print(
|
||||
|
|
@ -200,7 +203,7 @@ def get_llm_provider_access_keys(arch_config_file):
|
|||
access_key_list.append(access_key)
|
||||
|
||||
# Extract environment variables from state_storage.connection_string
|
||||
state_storage = arch_config_yaml.get("state_storage_v1_responses")
|
||||
state_storage = plano_config_yaml.get("state_storage_v1_responses")
|
||||
if state_storage:
|
||||
connection_string = state_storage.get("connection_string")
|
||||
if connection_string and isinstance(connection_string, str):
|
||||
|
|
@ -251,16 +254,16 @@ def find_config_file(path=".", file=None):
|
|||
# If a file is provided, process that file
|
||||
return os.path.abspath(file)
|
||||
else:
|
||||
# If no file is provided, use the path and look for arch_config.yaml first, then config.yaml for convenience
|
||||
arch_config_file = os.path.abspath(os.path.join(path, "config.yaml"))
|
||||
if not os.path.exists(arch_config_file):
|
||||
arch_config_file = os.path.abspath(os.path.join(path, "arch_config.yaml"))
|
||||
return arch_config_file
|
||||
# If no file is provided, use the path and look for plano_config.yaml first, then config.yaml for convenience
|
||||
plano_config_file = os.path.abspath(os.path.join(path, "config.yaml"))
|
||||
if not os.path.exists(plano_config_file):
|
||||
plano_config_file = os.path.abspath(os.path.join(path, "plano_config.yaml"))
|
||||
return plano_config_file
|
||||
|
||||
|
||||
def stream_access_logs(follow):
|
||||
"""
|
||||
Get the archgw access logs
|
||||
Get the plano access logs
|
||||
"""
|
||||
|
||||
follow_arg = "-f" if follow else ""
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue