q792602257andClaude Sonnet 5
61ff3b425d
Replaces the stub Planner's fixed describe_screen/[] behavior with a real decision-maker: AIPlanner uses native tool/function calling (Anthropic or OpenAI, pluggable via AI_PLANNER_PROVIDER) to select exactly one grounded action per turn, with an explicit finish_task(success, reason) tool for completion/failure instead of an ambiguous "no tool call" signal. Default disabled (AI_PLANNER_ENABLED=false) and additive; TaskRunner falls back to the existing stub Planner unchanged when disabled. Amends CONSTITUTION.md's Perception Boundary with one narrow exception: only the AI Planner may receive the current step's raw screenshot bytes alongside Scene, for vision-grounded coordinate grounding. Also fixes a latent gap in TaskRunner.run(): observe/plan exceptions are now caught per iteration and turned into a failed task with a failure_reason, instead of propagating uncaught. openspec change: ai-planner-runtime. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
73 lines
2.2 KiB
Python
73 lines
2.2 KiB
Python
from __future__ import annotations
|
|
|
|
from runtime.planner_config import (
|
|
DEFAULT_MODEL_BY_PROVIDER,
|
|
DEFAULT_PROVIDER,
|
|
DEFAULT_TIMEOUT_SECONDS,
|
|
PlannerConfig,
|
|
load_config,
|
|
)
|
|
|
|
_NO_RELEVANT_VARS = {"UNRELATED": "1"}
|
|
|
|
|
|
def test_load_config_defaults_when_unset() -> None:
|
|
config = load_config(_NO_RELEVANT_VARS)
|
|
|
|
assert config == PlannerConfig(
|
|
enabled=False,
|
|
provider=DEFAULT_PROVIDER,
|
|
model="",
|
|
timeout=DEFAULT_TIMEOUT_SECONDS,
|
|
)
|
|
assert config.resolved_model() == DEFAULT_MODEL_BY_PROVIDER[DEFAULT_PROVIDER]
|
|
|
|
|
|
def test_load_config_parses_enabled_truthy_values() -> None:
|
|
for value in ["1", "true", "True", "yes", "on", "enabled"]:
|
|
assert load_config({"AI_PLANNER_ENABLED": value}).enabled is True
|
|
|
|
|
|
def test_load_config_parses_enabled_falsy_values() -> None:
|
|
for value in ["0", "false", "no", "off", ""]:
|
|
assert load_config({"AI_PLANNER_ENABLED": value}).enabled is False
|
|
|
|
|
|
def test_load_config_selects_provider_and_resolves_default_model() -> None:
|
|
config = load_config({"AI_PLANNER_PROVIDER": "openai"})
|
|
|
|
assert config.provider == "openai"
|
|
assert config.resolved_model() == "gpt-5.6"
|
|
|
|
|
|
def test_load_config_anthropic_default_model() -> None:
|
|
config = load_config({"AI_PLANNER_PROVIDER": "anthropic"})
|
|
|
|
assert config.resolved_model() == "claude-sonnet-5"
|
|
|
|
|
|
def test_load_config_falls_back_to_default_provider_when_unsupported() -> None:
|
|
config = load_config({"AI_PLANNER_PROVIDER": "not-a-real-provider"})
|
|
|
|
assert config.provider == DEFAULT_PROVIDER
|
|
|
|
|
|
def test_load_config_model_override_wins_regardless_of_provider() -> None:
|
|
config = load_config(
|
|
{"AI_PLANNER_PROVIDER": "openai", "AI_PLANNER_MODEL": "custom-model"}
|
|
)
|
|
|
|
assert config.resolved_model() == "custom-model"
|
|
|
|
|
|
def test_load_config_parses_valid_timeout() -> None:
|
|
config = load_config({"AI_PLANNER_TIMEOUT_SECONDS": "12.5"})
|
|
|
|
assert config.timeout == 12.5
|
|
|
|
|
|
def test_load_config_falls_back_to_default_timeout_when_invalid_or_non_positive() -> None:
|
|
for value in ["not-a-number", "0", "-5"]:
|
|
config = load_config({"AI_PLANNER_TIMEOUT_SECONDS": value, **_NO_RELEVANT_VARS})
|
|
assert config.timeout == DEFAULT_TIMEOUT_SECONDS
|