q792602257
a5aeb8889c
Tests / Test failed: 2, passed: 849
- ToolCallDecision captures thinking blocks and pre-tool text output
- AnthropicToolCallingClient supports optional extended thinking (budget_tokens + beta header)
- PlannedStep carries rationale and thinking from each LLM decision
- WorldEvent replaces scene_summary with rationale/thinking/page fields (backward-compatible)
- AI planner system prompt instructs reflection before each tool call
- _history_summary() emits compact {page, rationale, action, success} dicts
- Cloud DB migration 0011 adds nullable rationale/thinking columns to planner_decision_log
- OpenAI client extracts reasoning_content into thinking field
91 lines
2.8 KiB
Python
91 lines
2.8 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
|
|
|
|
|
|
def test_load_config_parses_thinking_budget_tokens() -> None:
|
|
config = load_config({"AI_PLANNER_THINKING_BUDGET_TOKENS": "4096"})
|
|
|
|
assert config.thinking_budget_tokens == 4096
|
|
|
|
|
|
def test_load_config_thinking_budget_tokens_unset_defaults_to_none() -> None:
|
|
config = load_config(_NO_RELEVANT_VARS)
|
|
|
|
assert config.thinking_budget_tokens is None
|
|
|
|
|
|
def test_load_config_thinking_budget_tokens_invalid_or_non_positive_gives_none() -> None:
|
|
for value in ["not-a-number", "0", "-1"]:
|
|
config = load_config({"AI_PLANNER_THINKING_BUDGET_TOKENS": value, **_NO_RELEVANT_VARS})
|
|
assert config.thinking_budget_tokens is None
|