Move python implementation under python/ in preparation for the upcoming Go rewrite

2026-05-10 22:37:38 +00:00
parent e797e3d9ff
commit 2e47c8a1b6
47 changed files with 0 additions and 0 deletions
--- a/python/tests/test_new_config.py
+++ b/python/tests/test_new_config.py
@@ -0,0 +1,435 @@
+import pytest
+
+from audita.core.config import (
+    AuditaConfig,
+    ConfigOverrides,
+    DEFAULT_GLOSSARY_CONFIDENCE_THRESHOLD,
+    DEFAULT_GRAMMAR_CONFIDENCE_THRESHOLD,
+    DEFAULT_HOMOPHONES_CONFIDENCE_THRESHOLD,
+    DEFAULT_LLM_CONCURRENCY,
+    DEFAULT_LLM_TIMEOUT_SECONDS,
+    DEFAULT_MAX_SECTION_TOKENS,
+    DEFAULT_MIN_SECTION_TOKENS,
+    DEFAULT_NORMALIZE_MAX_SEGMENT_GAP,
+    DEFAULT_SPOKEN_WORD_CONFIDENCE_THRESHOLD,
+    DEFAULT_VALIDATION_MAX_PROMPT_TOKENS,
+    DEFAULT_WORK_DIR_RETENTION,
+)
+from audita.core.errors import AuditaConfigError
+from audita.modules import DEFAULT_MODULE_KEYS
+
+
+def test_default_config_allows_missing_api_key():
+    config = AuditaConfig.from_sources(env={})
+
+    assert config.api_key is None
+    assert config.llm_concurrency == DEFAULT_LLM_CONCURRENCY
+    assert config.llm_timeout_seconds == DEFAULT_LLM_TIMEOUT_SECONDS
+    assert config.validation_llm_api_key is None
+    assert config.validation_llm_concurrency is None
+    assert config.validation_llm_timeout_seconds is None
+    assert config.validation_model is None
+    assert config.validation_base_url is None
+    assert config.validation_max_retries is None
+    assert config.validation_max_prompt_tokens == DEFAULT_VALIDATION_MAX_PROMPT_TOKENS
+    assert config.target_sections is None
+    assert config.max_section_tokens == DEFAULT_MAX_SECTION_TOKENS
+    assert config.min_section_tokens == DEFAULT_MIN_SECTION_TOKENS
+    assert config.module_keys == DEFAULT_MODULE_KEYS
+    assert config.glossary_confidence_threshold == DEFAULT_GLOSSARY_CONFIDENCE_THRESHOLD
+    assert config.grammar_confidence_threshold == DEFAULT_GRAMMAR_CONFIDENCE_THRESHOLD
+    assert config.homophones_confidence_threshold == DEFAULT_HOMOPHONES_CONFIDENCE_THRESHOLD
+    assert config.spoken_word_confidence_threshold == DEFAULT_SPOKEN_WORD_CONFIDENCE_THRESHOLD
+    assert config.normalize_max_segment_gap == DEFAULT_NORMALIZE_MAX_SEGMENT_GAP
+    assert config.work_dir_retention == DEFAULT_WORK_DIR_RETENTION
+
+
+def test_cli_overrides_take_precedence():
+    config = AuditaConfig.from_sources(
+        env={"AUDITA_MAX_SECTION_TOKENS": "1000"},
+        overrides=ConfigOverrides(max_section_tokens=2000, min_section_tokens=1000),
+    )
+
+    assert config.max_section_tokens == 2000
+
+
+def test_min_section_tokens_cli_override_takes_precedence():
+    config = AuditaConfig.from_sources(
+        env={"AUDITA_MIN_SECTION_TOKENS": "2000"},
+        overrides=ConfigOverrides(min_section_tokens=6000),
+    )
+
+    assert config.min_section_tokens == 6000
+
+
+def test_llm_concurrency_cli_override_takes_precedence():
+    config = AuditaConfig.from_sources(
+        env={"AUDITA_LLM_CONCURRENCY": "2"},
+        overrides=ConfigOverrides(llm_concurrency=4),
+    )
+
+    assert config.llm_concurrency == 4
+
+
+def test_llm_concurrency_env_is_parsed():
+    config = AuditaConfig.from_sources(env={"AUDITA_LLM_CONCURRENCY": "3"})
+
+    assert config.llm_concurrency == 3
+
+
+def test_llm_timeout_seconds_cli_override_takes_precedence():
+    config = AuditaConfig.from_sources(
+        env={"AUDITA_LLM_TIMEOUT_SECONDS": "120"},
+        overrides=ConfigOverrides(llm_timeout_seconds=900.0),
+    )
+
+    assert config.llm_timeout_seconds == 900.0
+
+
+def test_llm_timeout_seconds_env_is_parsed():
+    config = AuditaConfig.from_sources(env={"AUDITA_LLM_TIMEOUT_SECONDS": "120.5"})
+
+    assert config.llm_timeout_seconds == 120.5
+
+
+def test_validation_llm_concurrency_cli_override_takes_precedence():
+    config = AuditaConfig.from_sources(
+        env={"AUDITA_VALIDATION_LLM_CONCURRENCY": "2"},
+        overrides=ConfigOverrides(validation_llm_concurrency=4),
+    )
+
+    assert config.validation_llm_concurrency == 4
+
+
+def test_validation_llm_concurrency_env_is_parsed():
+    config = AuditaConfig.from_sources(env={"AUDITA_VALIDATION_LLM_CONCURRENCY": "3"})
+
+    assert config.validation_llm_concurrency == 3
+
+
+def test_validation_llm_timeout_seconds_cli_override_takes_precedence():
+    config = AuditaConfig.from_sources(
+        env={"AUDITA_VALIDATION_LLM_TIMEOUT_SECONDS": "120"},
+        overrides=ConfigOverrides(validation_llm_timeout_seconds=900.0),
+    )
+
+    assert config.validation_llm_timeout_seconds == 900.0
+
+
+def test_validation_llm_timeout_seconds_env_is_parsed():
+    config = AuditaConfig.from_sources(env={"AUDITA_VALIDATION_LLM_TIMEOUT_SECONDS": "120.5"})
+
+    assert config.validation_llm_timeout_seconds == 120.5
+
+
+def test_validation_model_env_is_parsed():
+    config = AuditaConfig.from_sources(env={"AUDITA_VALIDATION_MODEL": "validator-model"})
+
+    assert config.validation_model == "validator-model"
+
+
+def test_validation_base_url_env_is_parsed():
+    config = AuditaConfig.from_sources(env={"AUDITA_VALIDATION_BASE_URL": "http://localhost:9000/v1"})
+
+    assert config.validation_base_url == "http://localhost:9000/v1"
+
+
+def test_validation_max_retries_env_is_parsed():
+    config = AuditaConfig.from_sources(env={"AUDITA_VALIDATION_MAX_RETRIES": "7"})
+
+    assert config.validation_max_retries == 7
+
+
+def test_validation_max_prompt_tokens_cli_override_takes_precedence():
+    config = AuditaConfig.from_sources(
+        env={"AUDITA_VALIDATION_MAX_PROMPT_TOKENS": "1024"},
+        overrides=ConfigOverrides(validation_max_prompt_tokens=4096),
+    )
+
+    assert config.validation_max_prompt_tokens == 4096
+
+
+def test_validation_max_prompt_tokens_env_is_parsed():
+    config = AuditaConfig.from_sources(env={"AUDITA_VALIDATION_MAX_PROMPT_TOKENS": "1024"})
+
+    assert config.validation_max_prompt_tokens == 1024
+
+
+def test_target_sections_cli_override_takes_precedence():
+    config = AuditaConfig.from_sources(
+        env={"AUDITA_TARGET_SECTIONS": "2"},
+        overrides=ConfigOverrides(target_sections=5),
+    )
+
+    assert config.target_sections == 5
+
+
+def test_target_sections_env_is_parsed():
+    config = AuditaConfig.from_sources(env={"AUDITA_TARGET_SECTIONS": "3"})
+
+    assert config.target_sections == 3
+
+
+def test_min_section_tokens_env_is_parsed():
+    config = AuditaConfig.from_sources(env={"AUDITA_MIN_SECTION_TOKENS": "3000"})
+
+    assert config.min_section_tokens == 3000
+
+
+def test_generic_llm_api_key_env_is_read():
+    config = AuditaConfig.from_sources(env={"AUDITA_LLM_API_KEY": "generic-key"})
+
+    assert config.api_key == "generic-key"
+
+
+def test_generic_llm_api_key_takes_precedence_over_openrouter_env():
+    config = AuditaConfig.from_sources(
+        env={
+            "AUDITA_LLM_API_KEY": "generic-key",
+            "OPENROUTER_API_KEY": "legacy-key",
+        }
+    )
+
+    assert config.api_key == "generic-key"
+
+
+def test_llm_api_key_cli_override_takes_precedence_over_env():
+    config = AuditaConfig.from_sources(
+        env={
+            "AUDITA_LLM_API_KEY": "generic-key",
+            "OPENROUTER_API_KEY": "legacy-key",
+        },
+        overrides=ConfigOverrides(llm_api_key="cli-key"),
+    )
+
+    assert config.api_key == "cli-key"
+
+
+def test_blank_llm_api_key_override_resolves_to_none():
+    config = AuditaConfig.from_sources(
+        env={"OPENROUTER_API_KEY": "legacy-key"},
+        overrides=ConfigOverrides(llm_api_key="   "),
+    )
+
+    assert config.api_key is None
+
+
+def test_validation_llm_api_key_env_is_read():
+    config = AuditaConfig.from_sources(env={"AUDITA_VALIDATION_LLM_API_KEY": "validation-key"})
+
+    assert config.validation_llm_api_key == "validation-key"
+
+
+def test_blank_validation_llm_api_key_override_disables_primary_fallback():
+    config = AuditaConfig.from_sources(
+        env={"AUDITA_LLM_API_KEY": "primary-key"},
+        overrides=ConfigOverrides(validation_llm_api_key="   "),
+    )
+
+    assert config.validation_llm_api_key == ""
+    assert config.validation_llm_config().api_key == ""
+
+
+def test_effective_validation_fields_fall_back_to_primary_settings():
+    config = AuditaConfig.from_sources(
+        env={
+            "AUDITA_LLM_API_KEY": "primary-key",
+            "AUDITA_MODEL": "primary-model",
+            "AUDITA_BASE_URL": "http://localhost:8000/v1",
+            "AUDITA_LLM_TIMEOUT_SECONDS": "120",
+            "AUDITA_LLM_CONCURRENCY": "5",
+            "AUDITA_MAX_RETRIES": "9",
+        }
+    )
+
+    validation = config.validation_llm_config()
+
+    assert validation.api_key == "primary-key"
+    assert validation.model == "primary-model"
+    assert validation.base_url == "http://localhost:8000/v1"
+    assert validation.llm_timeout_seconds == 120.0
+    assert validation.llm_concurrency == 5
+    assert validation.max_retries == 9
+
+
+def test_effective_validation_fields_use_overrides_when_set():
+    config = AuditaConfig.from_sources(
+        env={
+            "AUDITA_LLM_API_KEY": "primary-key",
+            "AUDITA_MODEL": "primary-model",
+            "AUDITA_BASE_URL": "http://localhost:8000/v1",
+            "AUDITA_LLM_TIMEOUT_SECONDS": "120",
+            "AUDITA_LLM_CONCURRENCY": "5",
+            "AUDITA_MAX_RETRIES": "9",
+            "AUDITA_VALIDATION_LLM_API_KEY": "validation-key",
+            "AUDITA_VALIDATION_MODEL": "validation-model",
+            "AUDITA_VALIDATION_BASE_URL": "http://localhost:9000/v1",
+            "AUDITA_VALIDATION_LLM_TIMEOUT_SECONDS": "240",
+            "AUDITA_VALIDATION_LLM_CONCURRENCY": "3",
+            "AUDITA_VALIDATION_MAX_RETRIES": "2",
+        }
+    )
+
+    validation = config.validation_llm_config()
+
+    assert validation.api_key == "validation-key"
+    assert validation.model == "validation-model"
+    assert validation.base_url == "http://localhost:9000/v1"
+    assert validation.llm_timeout_seconds == 240.0
+    assert validation.llm_concurrency == 3
+    assert validation.max_retries == 2
+
+
+def test_module_key_overrides_take_precedence():
+    config = AuditaConfig.from_sources(
+        env={"AUDITA_MODULES": "grammar"},
+        overrides=ConfigOverrides(module_keys="homophones,grammar"),
+    )
+
+    assert config.module_keys == ("homophones", "grammar")
+
+
+def test_module_key_env_is_parsed_and_trimmed():
+    config = AuditaConfig.from_sources(env={"AUDITA_MODULES": " glossary , grammar "})
+
+    assert config.module_keys == ("glossary", "grammar")
+
+
+def test_invalid_work_dir_retention_is_rejected():
+    with pytest.raises(AuditaConfigError):
+        AuditaConfig.from_sources(env={"AUDITA_WORK_DIR_RETENTION": "sometimes"})
+
+
+def test_report_dict_includes_llm_timeout_seconds():
+    config = AuditaConfig.from_sources(env={"AUDITA_LLM_TIMEOUT_SECONDS": "321"})
+
+    assert config.to_report_dict()["llm_timeout_seconds"] == 321.0
+
+
+def test_report_dict_includes_target_sections():
+    config = AuditaConfig.from_sources(env={"AUDITA_TARGET_SECTIONS": "7"})
+
+    assert config.to_report_dict()["target_sections"] == 7
+
+
+def test_report_dict_includes_effective_validation_llm_config():
+    config = AuditaConfig.from_sources(
+        env={
+            "AUDITA_LLM_API_KEY": "primary-key",
+            "AUDITA_VALIDATION_MODEL": "validation-model",
+        }
+    )
+
+    report = config.to_report_dict()
+
+    assert report["validation_model"] == "validation-model"
+    assert report["validation_max_prompt_tokens"] == DEFAULT_VALIDATION_MAX_PROMPT_TOKENS
+    assert report["effective_validation_llm"]["api_key_configured"] is True
+    assert report["effective_validation_llm"]["model"] == "validation-model"
+
+
+def test_threshold_overrides_take_precedence():
+    config = AuditaConfig.from_sources(
+        env={
+            "AUDITA_GLOSSARY_CONFIDENCE_THRESHOLD": "0.6",
+            "AUDITA_GRAMMAR_CONFIDENCE_THRESHOLD": "0.65",
+            "AUDITA_HOMOPHONES_CONFIDENCE_THRESHOLD": "0.7",
+            "AUDITA_SPOKEN_WORD_CONFIDENCE_THRESHOLD": "0.75",
+        },
+        overrides=ConfigOverrides(
+            glossary_confidence_threshold=0.85,
+            grammar_confidence_threshold=0.88,
+            homophones_confidence_threshold=0.9,
+            spoken_word_confidence_threshold=0.95,
+        ),
+    )
+
+    assert config.glossary_confidence_threshold == 0.85
+    assert config.grammar_confidence_threshold == 0.88
+    assert config.homophones_confidence_threshold == 0.9
+    assert config.spoken_word_confidence_threshold == 0.95
+
+
+@pytest.mark.parametrize(
+    "value",
+    [
+        "",
+        "grammar,,homophones",
+        "bogus",
+    ],
+)
+def test_invalid_module_sequences_are_rejected(value):
+    with pytest.raises(AuditaConfigError, match="AUDITA_MODULES"):
+        AuditaConfig.from_sources(env={"AUDITA_MODULES": value})
+
+
+@pytest.mark.parametrize(
+    "env_name",
+    [
+        "AUDITA_GLOSSARY_CONFIDENCE_THRESHOLD",
+        "AUDITA_GRAMMAR_CONFIDENCE_THRESHOLD",
+        "AUDITA_HOMOPHONES_CONFIDENCE_THRESHOLD",
+        "AUDITA_SPOKEN_WORD_CONFIDENCE_THRESHOLD",
+    ],
+)
+def test_invalid_thresholds_are_rejected(env_name):
+    with pytest.raises(AuditaConfigError):
+        AuditaConfig.from_sources(env={env_name: "1.5"})
+
+
+@pytest.mark.parametrize("value", ["0", "-1", "many"])
+def test_invalid_llm_concurrency_is_rejected(value):
+    with pytest.raises(AuditaConfigError, match="AUDITA_LLM_CONCURRENCY"):
+        AuditaConfig.from_sources(env={"AUDITA_LLM_CONCURRENCY": value})
+
+
+@pytest.mark.parametrize("value", ["0", "-1", "many"])
+def test_invalid_llm_timeout_seconds_is_rejected(value):
+    with pytest.raises(AuditaConfigError, match="AUDITA_LLM_TIMEOUT_SECONDS"):
+        AuditaConfig.from_sources(env={"AUDITA_LLM_TIMEOUT_SECONDS": value})
+
+
+@pytest.mark.parametrize("value", ["0", "-1", "many"])
+def test_invalid_validation_llm_concurrency_is_rejected(value):
+    with pytest.raises(AuditaConfigError, match="AUDITA_VALIDATION_LLM_CONCURRENCY"):
+        AuditaConfig.from_sources(env={"AUDITA_VALIDATION_LLM_CONCURRENCY": value})
+
+
+@pytest.mark.parametrize("value", ["0", "-1", "many"])
+def test_invalid_validation_llm_timeout_seconds_is_rejected(value):
+    with pytest.raises(AuditaConfigError, match="AUDITA_VALIDATION_LLM_TIMEOUT_SECONDS"):
+        AuditaConfig.from_sources(env={"AUDITA_VALIDATION_LLM_TIMEOUT_SECONDS": value})
+
+
+@pytest.mark.parametrize("value", ["-1", "many"])
+def test_invalid_validation_max_retries_is_rejected(value):
+    with pytest.raises(AuditaConfigError, match="AUDITA_VALIDATION_MAX_RETRIES"):
+        AuditaConfig.from_sources(env={"AUDITA_VALIDATION_MAX_RETRIES": value})
+
+
+@pytest.mark.parametrize("value", ["0", "-1", "many"])
+def test_invalid_validation_max_prompt_tokens_is_rejected(value):
+    with pytest.raises(AuditaConfigError, match="AUDITA_VALIDATION_MAX_PROMPT_TOKENS"):
+        AuditaConfig.from_sources(env={"AUDITA_VALIDATION_MAX_PROMPT_TOKENS": value})
+
+
+@pytest.mark.parametrize("value", ["0", "-1", "many"])
+def test_invalid_target_sections_is_rejected(value):
+    with pytest.raises(AuditaConfigError, match="AUDITA_TARGET_SECTIONS"):
+        AuditaConfig.from_sources(env={"AUDITA_TARGET_SECTIONS": value})
+
+
+@pytest.mark.parametrize("value", ["0", "-1", "many"])
+def test_invalid_min_section_tokens_is_rejected(value):
+    with pytest.raises(AuditaConfigError, match="AUDITA_MIN_SECTION_TOKENS"):
+        AuditaConfig.from_sources(env={"AUDITA_MIN_SECTION_TOKENS": value})
+
+
+def test_min_section_tokens_must_not_exceed_max_section_tokens():
+    with pytest.raises(AuditaConfigError, match="AUDITA_MIN_SECTION_TOKENS"):
+        AuditaConfig.from_sources(
+            env={
+                "AUDITA_MIN_SECTION_TOKENS": "9000",
+                "AUDITA_MAX_SECTION_TOKENS": "8000",
+            }
+        )