[claude] Add web_fetch tool (trafilatura) for full-page content extraction (#973) (#1004)

pyproject.toml

@@ -50,6 +50,7 @@ sounddevice = { version = ">=0.4.6", optional = true }
 sentence-transformers = { version = ">=2.0.0", optional = true }
 numpy = { version = ">=1.24.0", optional = true }
 requests = { version = ">=2.31.0", optional = true }
+trafilatura = { version = ">=1.6.0", optional = true }
 GitPython = { version = ">=3.1.40", optional = true }
 pytest = { version = ">=8.0.0", optional = true }
 pytest-asyncio = { version = ">=0.24.0", optional = true }
@@ -67,6 +68,7 @@ voice = ["pyttsx3", "openai-whisper", "piper-tts", "sounddevice"]
 celery = ["celery"]
 embeddings = ["sentence-transformers", "numpy"]
 git = ["GitPython"]
+research = ["requests", "trafilatura"]
 dev = ["pytest", "pytest-asyncio", "pytest-cov", "pytest-timeout", "pytest-randomly", "pytest-xdist", "selenium"]
 
 [tool.poetry.group.dev.dependencies]