logdetective 2.0.0__tar.gz → 2.0.2__tar.gz

{logdetective-2.0.0 → logdetective-2.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: logdetective
-Version: 2.0.0
+Version: 2.0.2
 Summary: Log using LLM AI to search for build/test failures and provide ideas for fixing these.
 License: Apache-2.0
 Author: Jiri Podivin
@@ -20,23 +20,30 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Software Development :: Debuggers
 Provides-Extra: server
 Provides-Extra: server-testing
-Requires-Dist: aiohttp (>=3.7.4)
+Provides-Extra: testing
+Requires-Dist: aiohttp (>=3.7.4,<4.0.0)
 Requires-Dist: aiolimiter (>=1.0.0,<2.0.0) ; extra == "server"
+Requires-Dist: aioresponses (>=0.7.8,<0.8.0) ; extra == "testing"
 Requires-Dist: alembic (>=1.13.3,<2.0.0) ; extra == "server" or extra == "server-testing"
 Requires-Dist: backoff (==2.2.1) ; extra == "server" or extra == "server-testing"
 Requires-Dist: drain3 (>=0.9.11,<0.10.0)
-Requires-Dist: fastapi (>=0.111.1) ; extra == "server" or extra == "server-testing"
-Requires-Dist: huggingface-hub (>0.23.2)
+Requires-Dist: fastapi (>=0.111.1,<1.0.0) ; extra == "server" or extra == "server-testing"
+Requires-Dist: flexmock (>=0.12.2,<0.13.0) ; extra == "testing"
+Requires-Dist: huggingface-hub (>0.23.2,<0.35.0)
 Requires-Dist: koji (>=1.35.0,<2.0.0) ; extra == "server" or extra == "server-testing"
-Requires-Dist: llama-cpp-python (>0.2.56,!=0.2.86)
+Requires-Dist: llama-cpp-python (>0.2.56,!=0.2.86,<1.0.0)
 Requires-Dist: matplotlib (>=3.8.4,<4.0.0) ; extra == "server" or extra == "server-testing"
 Requires-Dist: numpy (>=1.26.0)
 Requires-Dist: openai (>=1.82.1,<2.0.0) ; extra == "server" or extra == "server-testing"
 Requires-Dist: psycopg2 (>=2.9.9,<3.0.0) ; extra == "server"
 Requires-Dist: psycopg2-binary (>=2.9.9,<3.0.0) ; extra == "server-testing"
 Requires-Dist: pydantic (>=2.8.2,<3.0.0)
+Requires-Dist: pytest (>=8.4.1,<9.0.0) ; extra == "testing"
+Requires-Dist: pytest-asyncio (>=1.1.0,<2.0.0) ; extra == "testing"
+Requires-Dist: pytest-mock (>=3.14.1,<4.0.0) ; extra == "server-testing"
 Requires-Dist: python-gitlab (>=4.4.0)
 Requires-Dist: pyyaml (>=6.0.1,<7.0.0)
+Requires-Dist: responses (>=0.25.7,<0.26.0) ; extra == "server-testing"
 Requires-Dist: sentry-sdk[fastapi] (>=2.17.0,<3.0.0) ; extra == "server" or extra == "server-testing"
 Requires-Dist: sqlalchemy (>=2.0.36,<3.0.0) ; extra == "server" or extra == "server-testing"
 Project-URL: homepage, https://github.com/fedora-copr/logdetective

{logdetective-2.0.0 → logdetective-2.0.2}/logdetective/extractors.py

@@ -20,7 +20,8 @@ class DrainExtractor:
         context: bool = False,
         max_clusters=8,
         skip_snippets: SkipSnippets = SkipSnippets({}),
-    ):
+        max_snippet_len: int = 2000
+    ):  # pylint: disable=R0913,R0917
         config = TemplateMinerConfig()
         config.load(f"{os.path.dirname(__file__)}/drain3.ini")
         config.profiling_enabled = verbose
@@ -29,11 +30,12 @@ class DrainExtractor:
         self.verbose = verbose
         self.context = context
         self.skip_snippets = skip_snippets
+        self.max_snippet_len = max_snippet_len
 
     def __call__(self, log: str) -> list[Tuple[int, str]]:
         out = []
         # Create chunks
-        chunks = list(get_chunks(log))
+        chunks = list(get_chunks(log, self.max_snippet_len))
         # Keep only chunks that don't match any of the excluded patterns
         chunks = [
             (_, chunk)

{logdetective-2.0.0 → logdetective-2.0.2}/logdetective/server/models.py

@@ -244,18 +244,18 @@ class InferenceConfig(BaseModel):  # pylint: disable=too-many-instance-attribute
 class ExtractorConfig(BaseModel):
     """Model for extractor configuration of logdetective server."""
 
-    context: bool = True
     max_clusters: int = 8
     verbose: bool = False
+    max_snippet_len: int = 2000
 
     def __init__(self, data: Optional[dict] = None):
         super().__init__()
         if data is None:
             return
 
-        self.context = data.get("context", True)
         self.max_clusters = data.get("max_clusters", 8)
         self.verbose = data.get("verbose", False)
+        self.max_snippet_len = data.get("max_snippet_len", 2000)
 
 
 class GitLabInstanceConfig(BaseModel):  # pylint: disable=too-many-instance-attributes

{logdetective-2.0.0 → logdetective-2.0.2}/logdetective/server/server.py

@@ -117,23 +117,25 @@ def requires_token_when_set(authentication: Annotated[str | None, Header()] = No
         LOG.info("LOGDETECTIVE_TOKEN env var not set, authentication disabled")
         # no token required, means local dev environment
         return
-    token = None
     if authentication:
         try:
             token = authentication.split(" ", 1)[1]
-        except (ValueError, IndexError):
+        except (ValueError, IndexError) as ex:
             LOG.warning(
-                "Authentication header has invalid structure (%s), it should be 'Bearer TOKEN'",
+                "Authentication header has invalid structure '%s', it should be 'Bearer TOKEN'",
                 authentication,
             )
             # eat the exception and raise 401 below
-            token = None
+            raise HTTPException(
+                status_code=401,
+                detail=f"Invalid authentication, HEADER '{authentication}' not valid.",
+            ) from ex
         if token == API_TOKEN:
             return
-    LOG.info(
-        "LOGDETECTIVE_TOKEN env var is set (%s), clien token = %s", API_TOKEN, token
-    )
-    raise HTTPException(status_code=401, detail=f"Token {token} not valid.")
+        LOG.info("Provided token '%s' does not match expected value.", token)
+        raise HTTPException(status_code=401, detail=f"Token '{token}' not valid.")
+    LOG.error("No authentication header provided but LOGDETECTIVE_TOKEN env var is set")
+    raise HTTPException(status_code=401, detail="No token provided.")
 
 
 app = FastAPI(dependencies=[Depends(requires_token_when_set)], lifespan=lifespan)

{logdetective-2.0.0 → logdetective-2.0.2}/logdetective/server/templates/gitlab_full_comment.md.j2

@@ -12,7 +12,7 @@ In this case, we are {{ "%.2f" | format(certainty) }}% certain of the response {
 {% for snippet in snippets %}
 <li>
 <b>Line {{ snippet.line_number }}:</b> <code>{{ snippet.text }}</code>
-{{ snippet.explanation }}
+{{ snippet.explanation.text }}
 </li>
 {% endfor %}
 </ul>

{logdetective-2.0.0 → logdetective-2.0.2}/logdetective/server/utils.py

@@ -29,6 +29,7 @@ def mine_logs(log: str) -> List[Tuple[int, str]]:
         context=True,
         max_clusters=SERVER_CONFIG.extractor.max_clusters,
         skip_snippets=SKIP_SNIPPETS_CONFIG,
+        max_snippet_len=SERVER_CONFIG.extractor.max_snippet_len
     )
 
     LOG.info("Getting summary")

{logdetective-2.0.0 → logdetective-2.0.2}/logdetective/utils.py

@@ -39,7 +39,7 @@ def chunk_continues(text: str, index: int) -> bool:
     return False
 
 
-def get_chunks(text: str) -> Generator[Tuple[int, str], None, None]:
+def get_chunks(text: str, max_len: int = 2000) -> Generator[Tuple[int, str], None, None]:
     """Split log into chunks according to heuristic
     based on whitespace and backslash presence.
     """
@@ -54,7 +54,7 @@ def get_chunks(text: str) -> Generator[Tuple[int, str], None, None]:
         chunk += text[i]
         if text[i] == "\n":
             next_line_number += 1
-            if i + 1 < text_len and chunk_continues(text, i):
+            if i + 1 < text_len and chunk_continues(text, i) and i + 1 < max_len:
                 i += 1
                 continue
             yield (original_line_number, chunk)

{logdetective-2.0.0 → logdetective-2.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "logdetective"
-version = "2.0.0"
+version = "2.0.2"
 description = "Log using LLM AI to search for build/test failures and provide ideas for fixing these."
 authors = ["Jiri Podivin <jpodivin@gmail.com>"]
 license = "Apache-2.0"
@@ -32,32 +32,51 @@ issues = "https://github.com/fedora-copr/logdetective/issues"
 
 [tool.poetry.dependencies]
 python = "^3.11"
-llama-cpp-python = ">0.2.56,!=0.2.86"
-drain3 = "^0.9.11"
-huggingface-hub = ">0.23.2"
+llama-cpp-python = ">0.2.56,!=0.2.86,<1.0.0"
+drain3 = ">=0.9.11,<0.10.0"
+huggingface-hub = ">0.23.2,<0.35.0"
 # rawhide has numpy 2, F40 and F41 are still on 1.26
 # we need to support both versions
 numpy = ">=1.26.0"
 python-gitlab = ">=4.4.0"
-pydantic = "^2.8.2"
-pyyaml = "^6.0.1"
-aiohttp = ">=3.7.4"  # latest version in el8
-aiolimiter = "^1.0.0"
+pydantic = ">=2.8.2,<3.0.0"
+pyyaml = ">=6.0.1,<7.0.0"
+aiohttp = ">=3.7.4,<4.0.0"  # latest version in el8
+aiolimiter = ">=1.0.0,<2.0.0"
 
-fastapi = {version = ">=0.111.1", optional = true }
-sqlalchemy = {version = "^2.0.36", optional = true }
-psycopg2-binary = {version = "^2.9.9", optional = true }
-psycopg2 = {version = "^2.9.9", optional = true }
-alembic = {version = "^1.13.3", optional = true }
-matplotlib = {version = "^3.8.4", optional = true }
+fastapi = {version = ">=0.111.1,<1.0.0", optional = true }
+sqlalchemy = {version = ">=2.0.36,<3.0.0", optional = true }
+psycopg2-binary = {version = ">=2.9.9,<3.0.0", optional = true }
+psycopg2 = {version = ">=2.9.9,<3.0.0", optional = true }
+alembic = {version = ">=1.13.3,<2.0.0", optional = true }
+matplotlib = {version = ">=3.8.4,<4.0.0", optional = true }
 backoff = {version = "2.2.1", optional = true }
-sentry-sdk = {version = "^2.17.0", optional = true, extras = ["fastapi"]}
-openai = {version = "^1.82.1", optional = true}
-koji = {version = "^1.35.0", optional = true}
+sentry-sdk = {version = ">=2.17.0,<3.0.0", optional = true, extras = ["fastapi"]}
+openai = {version = ">=1.82.1,<2.0.0", optional = true}
+koji = {version = ">=1.35.0,<2.0.0", optional = true}
+responses = {version = ">=0.25.7,<0.26.0", optional = true}
+aioresponses = {version = ">=0.7.8,<0.8.0", optional = true}
+pytest-asyncio = {version = ">=1.1.0,<2.0.0", optional = true}
+pytest-mock = {version = ">=3.14.1,<4.0.0", optional = true}
+flexmock = {version = ">=0.12.2,<0.13.0", optional = true}
+pytest = {version = ">=8.4.1,<9.0.0", optional = true}
 
 [tool.poetry.extras]
 server = ["fastapi", "sqlalchemy", "psycopg2", "alembic", "matplotlib", "backoff", "aiolimiter", "sentry-sdk", "openai", "koji"]
-server-testing = ["fastapi", "sqlalchemy", "psycopg2-binary", "alembic", "matplotlib", "backoff", "pytest-asyncio", "sentry-sdk", "openai", "koji"]
+server-testing = [
+    "fastapi",
+    "sqlalchemy",
+    "psycopg2-binary",
+    "alembic",
+    "matplotlib",
+    "backoff",
+    "sentry-sdk",
+    "openai",
+    "koji",
+    "pytest-mock",
+    "responses",
+]
+testing = ["pytest", "pytest-asyncio", "aioresponses", "flexmock"]
 
 [build-system]
 requires = ["poetry-core"]