Use previous context in summarization

haiku_rag_slim/haiku/rag/agents/chat/context.py

@@ -11,12 +11,15 @@ from haiku.rag.utils import get_model
 async def summarize_session(
     qa_history: list[QAResponse],
     config: AppConfig,
+    current_context: str | None = None,
 ) -> str:
     """Summarize qa_history into compact context.
 
     Args:
         qa_history: List of Q&A pairs from the conversation.
         config: AppConfig for model selection.
+        current_context: Previous context to incorporate (background_context or
+            previous session_context.summary). The summarizer will build upon this.
 
     Returns:
         Markdown summary of the conversation history.
@@ -33,6 +36,8 @@ async def summarize_session(
     )
 
     history_text = _format_qa_history(qa_history)
+    if current_context:
+        history_text = f"## Current Context\n{current_context}\n\n{history_text}"
     result = await agent.run(history_text)
     return result.output
 
@@ -49,7 +54,18 @@ async def update_session_context(
         config: AppConfig for model selection.
         session_state: The session state to update.
     """
-    summary = await summarize_session(qa_history, config)
+    # Determine current context to incorporate:
+    # 1. If session_context already exists, use its summary
+    # 2. Otherwise, use background_context (if available)
+    current_context: str | None = None
+    if session_state.session_context and session_state.session_context.summary:
+        current_context = session_state.session_context.summary
+    elif session_state.background_context:
+        current_context = session_state.background_context
+
+    summary = await summarize_session(
+        qa_history, config, current_context=current_context
+    )
     session_state.session_context = SessionContext(
         summary=summary,
         last_updated=datetime.now(),

haiku_rag_slim/haiku/rag/agents/chat/prompts.py

@@ -39,7 +39,9 @@ You can optionally specify a limit parameter (default 5).
 
 IMPORTANT: You must make actual tool calls. Do not output "run_search(...)" as text."""
 
-SESSION_SUMMARY_PROMPT = """You are a session summarizer. Given a conversation history of Q&A pairs, produce a structured summary that captures key information for future context.
+SESSION_SUMMARY_PROMPT = """You are a session summarizer. Given a conversation history of Q&A pairs (and optionally existing context), produce a structured summary that captures key information for future context.
+
+If a "Current Context" section is provided at the start of the input, incorporate that context into your summary. This might be initial background context from the user or a previous summary - build upon it rather than discard it.
 
 Your summary should be concise (aim for 500-1500 tokens) and include:
 
@@ -49,6 +51,7 @@ Your summary should be concise (aim for 500-1500 tokens) and include:
 
 Rules:
 - Extract only high-signal information that would help answer follow-up questions
+- When building on existing context, merge new information with prior context
 - Omit small talk, greetings, or low-confidence answers
 - Use bullet points for clarity
 - Keep technical details but compress verbose explanations

tests/agents/chat/test_context.py

@@ -172,6 +172,37 @@ class TestSummarizeSession:
         assert "key facts" in result_lower or "established" in result_lower
         assert "documents" in result_lower or "sources" in result_lower
 
+    @pytest.mark.asyncio
+    @pytest.mark.vcr()
+    async def test_summarize_session_with_current_context(self, allow_model_requests):
+        """Test summarize_session incorporates current_context into the summary."""
+        from haiku.rag.agents.chat.context import summarize_session
+
+        qa_history = [
+            QAResponse(
+                question="What's the rate limit?",
+                answer="100 requests per minute.",
+                confidence=0.9,
+            )
+        ]
+
+        # Provide current_context (e.g., background_context or previous summary)
+        current_context = "Focus on Python APIs. User is building a web application."
+
+        result = await summarize_session(
+            qa_history=qa_history,
+            config=Config,
+            current_context=current_context,
+        )
+
+        # Summary should be non-empty and ideally incorporate context about Python/web
+        assert len(result) > 0
+        # The context about "Python" or "web application" should influence the summary
+        result_lower = result.lower()
+        assert (
+            "rate" in result_lower or "limit" in result_lower or "100" in result_lower
+        )
+
 
 class TestUpdateSessionContext:
     """Tests for update_session_context function."""

tests/cassettes/test_chat_context/TestSummarizeSession.test_summarize_session_with_current_context.yaml

@@ -0,0 +1,89 @@
+interactions:
+- request:
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1581'
+      content-type:
+      - application/json
+      host:
+      - localhost:11434
+    method: POST
+    parsed_body:
+      messages:
+      - content: |-
+          You are a session summarizer. Given a conversation history of Q&A pairs (and optionally existing context), produce a structured summary that captures key information for future context.
+
+          If a "Current Context" section is provided at the start of the input, incorporate that context into your summary. This might be initial background context from the user or a previous summary - build upon it rather than discard it.
+
+          Your summary should be concise (aim for 500-1500 tokens) and include:
+
+          1. **Key Facts Established** - Specific facts, data, or conclusions learned during the conversation
+          2. **Documents Referenced** - Documents or sources that were cited, with brief notes on what they contain
+          3. **Current Focus** - What topic or question thread the user is currently exploring
+
+          Rules:
+          - Extract only high-signal information that would help answer follow-up questions
+          - When building on existing context, merge new information with prior context
+          - Omit small talk, greetings, or low-confidence answers
+          - Use bullet points for clarity
+          - Keep technical details but compress verbose explanations
+          - Preserve document names/titles when mentioned in sources
+
+          Output the summary directly in markdown format. Do not include meta-commentary about the summary itself.
+        role: system
+      - content: |
+          ## Current Context
+          Focus on Python APIs. User is building a web application.
+
+          ## Q1: What's the rate limit?
+          **Answer** (confidence: 90%):
+          100 requests per minute.
+        role: user
+      model: gpt-oss
+      reasoning_effort: low
+      stream: false
+    uri: http://localhost:11434/v1/chat/completions
+  response:
+    headers:
+      content-length:
+      - '682'
+      content-type:
+      - application/json
+    parsed_body:
+      choices:
+      - finish_reason: stop
+        index: 0
+        message:
+          content: |-
+            ## Summary
+
+            - **Key Facts Established**
+              - The user is building a web application and is focused on Python APIs.
+              - The relevant rate limit is **100 requests per minute** (confidence 90%).
+
+            - **Documents Referenced**
+              - None cited in this exchange.
+
+            - **Current Focus**
+              - Understanding and managing API rate limits for the Python-based web application.
+          reasoning: We need summary.
+          role: assistant
+      created: 1769164539
+      id: chatcmpl-369
+      model: gpt-oss
+      object: chat.completion
+      system_fingerprint: fp_ollama
+      usage:
+        completion_tokens: 91
+        prompt_tokens: 362
+        total_tokens: 453
+    status:
+      code: 200
+      message: OK
+version: 1