Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
fix(memory): tolerate None message content in inline memory parser (#3211)
Abhay Singh5ccec67f0c3a
diff --git a/headroom/memory/inline_extractor.py b/headroom/memory/inline_extractor.pyindex f560ae3ed..0d36de161 100644--- a/headroom/memory/inline_extractor.py+++ b/headroom/memory/inline_extractor.py@@ -56,9 +56,9 @@ Skip for greetings/small talk. If nothing: <memory>{"memories": []}</memory>"""class ParsedResponse:"""Response with extracted memories."""- content: str # The actual response (without memory block)+ content: str | None # The actual response (without memory block); None for tool-call turnsmemories: list[dict[str, Any]] # Extracted memories- raw: str # Original full response+ raw: str | None # Original full responsedef inject_memory_instruction(@@ -101,11 +101,12 @@ def inject_memory_instruction(return messages-def parse_response_with_memory(response_text: str) -> ParsedResponse:+def parse_response_with_memory(response_text: str | None) -> ParsedResponse:"""Parse LLM response to extract memories.Args:- response_text: Raw LLM response+ response_text: Raw LLM response. May be ``None`` when the model answered+ with tool/function calls instead of text.Returns:ParsedResponse with content and memories separated@@ -113,6 +114,15 @@ def parse_response_with_memory(response_text: str) -> ParsedResponse:memories: list[dict[str, Any]] = []content = response_text+ # A chat completion's ``message.content`` is ``None`` whenever the model+ # answers with tool/function calls instead of text, so the two call sites+ # here forward ``None`` (and any non-str payload) straight in. ``re.search``+ # on a non-str raises ``TypeError``, which crashed the whole request. Return+ # the payload untouched — preserving ``None`` so a tool-call response is not+ # coerced to text — with no memories to extract.+ if not isinstance(response_text, str):+ return ParsedResponse(content=response_text, memories=memories, raw=response_text)+# Extract <memory> blockmemory_pattern = r"<memory>\s*(.*?)\s*</memory>"match = re.search(memory_pattern, response_text, re.DOTALL | re.IGNORECASE)@@ -179,7 +189,7 @@ class InlineMemoryWrapper:model: str = "gpt-4o-mini",short_instruction: bool = True,**kwargs: Any,- ) -> tuple[str, list[dict[str, Any]]]:+ ) -> tuple[str | None, list[dict[str, Any]]]:"""Send chat request and extract memories inline.Args:@@ -213,7 +223,7 @@ class InlineMemoryWrapper:messages: list[dict[str, Any]],model: str = "gpt-4o-mini",**kwargs: Any,- ) -> tuple[Any, str, list[dict[str, Any]]]:+ ) -> tuple[Any, str | None, list[dict[str, Any]]]:"""Send chat request and return full response object.Args:diff --git a/tests/test_memory_wrapper.py b/tests/test_memory_wrapper.pyindex 0bd009713..5907766a3 100644--- a/tests/test_memory_wrapper.py+++ b/tests/test_memory_wrapper.py@@ -224,3 +224,17 @@ def test_parse_response_with_memory_tolerates_non_object_memory_block() -> None:)assert parsed.memories == [{"content": "User likes Python"}]assert parsed.content == "text"+++def test_parse_response_with_memory_tolerates_none_content() -> None:+ from headroom.memory.inline_extractor import parse_response_with_memory++ # `chat.completions` returns `message.content == None` whenever the model+ # answers with tool/function calls instead of text. The callers forward that+ # `None` straight in, where `re.search(pattern, None)` used to raise+ # `TypeError` and crash the whole request. It must degrade gracefully and+ # preserve `None` (not coerce a tool-call turn to text).+ parsed = parse_response_with_memory(None)+ assert parsed.content is None+ assert parsed.memories == []+ assert parsed.raw is None