feat: implement summarization (#14)

backend/src/agents/lead_agent/agent.py

@@ -1,4 +1,5 @@
 from langchain.agents import create_agent
+from langchain.agents.middleware import SummarizationMiddleware
 from langchain_core.runnables import RunnableConfig
 
 from src.agents.lead_agent.prompt import apply_prompt_template
@@ -6,12 +7,66 @@ from src.agents.middlewares.clarification_middleware import ClarificationMiddlew
 from src.agents.middlewares.thread_data_middleware import ThreadDataMiddleware
 from src.agents.middlewares.title_middleware import TitleMiddleware
 from src.agents.thread_state import ThreadState
+from src.config.summarization_config import get_summarization_config
 from src.models import create_chat_model
 from src.sandbox.middleware import SandboxMiddleware
 
+
+def _create_summarization_middleware() -> SummarizationMiddleware | None:
+    """Create and configure the summarization middleware from config."""
+    config = get_summarization_config()
+
+    if not config.enabled:
+        return None
+
+    # Prepare trigger parameter
+    trigger = None
+    if config.trigger is not None:
+        if isinstance(config.trigger, list):
+            trigger = [t.to_tuple() for t in config.trigger]
+        else:
+            trigger = config.trigger.to_tuple()
+
+    # Prepare keep parameter
+    keep = config.keep.to_tuple()
+
+    # Prepare model parameter
+    if config.model_name:
+        model = config.model_name
+    else:
+        # Use a lightweight model for summarization to save costs
+        # Falls back to default model if not explicitly specified
+        model = create_chat_model(thinking_enabled=False)
+
+    # Prepare kwargs
+    kwargs = {
+        "model": model,
+        "trigger": trigger,
+        "keep": keep,
+    }
+
+    if config.trim_tokens_to_summarize is not None:
+        kwargs["trim_tokens_to_summarize"] = config.trim_tokens_to_summarize
+
+    if config.summary_prompt is not None:
+        kwargs["summary_prompt"] = config.summary_prompt
+
+    return SummarizationMiddleware(**kwargs)
+
+
 # ThreadDataMiddleware must be before SandboxMiddleware to ensure thread_id is available
+# SummarizationMiddleware should be early to reduce context before other processing
 # ClarificationMiddleware should be last to intercept clarification requests after model calls
-middlewares = [ThreadDataMiddleware(), SandboxMiddleware(), TitleMiddleware(), ClarificationMiddleware()]
+def _build_middlewares():
+    middlewares = [ThreadDataMiddleware(), SandboxMiddleware()]
+
+    # Add summarization middleware if enabled
+    summarization_middleware = _create_summarization_middleware()
+    if summarization_middleware is not None:
+        middlewares.append(summarization_middleware)
+
+    middlewares.extend([TitleMiddleware(), ClarificationMiddleware()])
+    return middlewares
 
 
 def make_lead_agent(config: RunnableConfig):
@@ -24,7 +79,7 @@ def make_lead_agent(config: RunnableConfig):
     return create_agent(
         model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled),
         tools=get_available_tools(),
-        middleware=middlewares,
+        middleware=_build_middlewares(),
         system_prompt=apply_prompt_template(),
         state_schema=ThreadState,
     )

backend/src/agents/lead_agent/prompt.py

@@ -89,7 +89,7 @@ You: "Deploying to staging..." [proceed]
 You have access to skills that provide optimized workflows for specific tasks. Each skill contains best practices, frameworks, and references to additional resources.
 
 **Progressive Loading Pattern:**
-1. When a user query matches a skill's use case, immediately call `view` on the skill's main file using the path attribute provided in the skill tag below
+1. When a user query matches a skill's use case, immediately call `read_file` on the skill's main file using the path attribute provided in the skill tag below
 2. Read and understand the skill's workflow and instructions
 3. The skill file contains references to external resources under the same folder
 4. Load referenced resources only when needed during execution

backend/src/config/app_config.py

@@ -9,6 +9,7 @@ from pydantic import BaseModel, ConfigDict, Field
 from src.config.model_config import ModelConfig
 from src.config.sandbox_config import SandboxConfig
 from src.config.skills_config import SkillsConfig
+from src.config.summarization_config import load_summarization_config_from_dict
 from src.config.title_config import load_title_config_from_dict
 from src.config.tool_config import ToolConfig, ToolGroupConfig
 
@@ -75,6 +76,10 @@ class AppConfig(BaseModel):
         if "title" in config_data:
             load_title_config_from_dict(config_data["title"])
 
+        # Load summarization config if present
+        if "summarization" in config_data:
+            load_summarization_config_from_dict(config_data["summarization"])
+
         result = cls.model_validate(config_data)
         return result
 

backend/src/config/summarization_config.py

@@ -0,0 +1,74 @@
+"""Configuration for conversation summarization."""
+
+from typing import Literal
+
+from pydantic import BaseModel, Field
+
+ContextSizeType = Literal["fraction", "tokens", "messages"]
+
+
+class ContextSize(BaseModel):
+    """Context size specification for trigger or keep parameters."""
+
+    type: ContextSizeType = Field(description="Type of context size specification")
+    value: int | float = Field(description="Value for the context size specification")
+
+    def to_tuple(self) -> tuple[ContextSizeType, int | float]:
+        """Convert to tuple format expected by SummarizationMiddleware."""
+        return (self.type, self.value)
+
+
+class SummarizationConfig(BaseModel):
+    """Configuration for automatic conversation summarization."""
+
+    enabled: bool = Field(
+        default=False,
+        description="Whether to enable automatic conversation summarization",
+    )
+    model_name: str | None = Field(
+        default=None,
+        description="Model name to use for summarization (None = use a lightweight model)",
+    )
+    trigger: ContextSize | list[ContextSize] | None = Field(
+        default=None,
+        description="One or more thresholds that trigger summarization. When any threshold is met, summarization runs. "
+        "Examples: {'type': 'messages', 'value': 50} triggers at 50 messages, "
+        "{'type': 'tokens', 'value': 4000} triggers at 4000 tokens, "
+        "{'type': 'fraction', 'value': 0.8} triggers at 80% of model's max input tokens",
+    )
+    keep: ContextSize = Field(
+        default_factory=lambda: ContextSize(type="messages", value=20),
+        description="Context retention policy after summarization. Specifies how much history to preserve. "
+        "Examples: {'type': 'messages', 'value': 20} keeps 20 messages, "
+        "{'type': 'tokens', 'value': 3000} keeps 3000 tokens, "
+        "{'type': 'fraction', 'value': 0.3} keeps 30% of model's max input tokens",
+    )
+    trim_tokens_to_summarize: int | None = Field(
+        default=4000,
+        description="Maximum tokens to keep when preparing messages for summarization. Pass null to skip trimming.",
+    )
+    summary_prompt: str | None = Field(
+        default=None,
+        description="Custom prompt template for generating summaries. If not provided, uses the default LangChain prompt.",
+    )
+
+
+# Global configuration instance
+_summarization_config: SummarizationConfig = SummarizationConfig()
+
+
+def get_summarization_config() -> SummarizationConfig:
+    """Get the current summarization configuration."""
+    return _summarization_config
+
+
+def set_summarization_config(config: SummarizationConfig) -> None:
+    """Set the summarization configuration."""
+    global _summarization_config
+    _summarization_config = config
+
+
+def load_summarization_config_from_dict(config_dict: dict) -> None:
+    """Load summarization configuration from a dictionary."""
+    global _summarization_config
+    _summarization_config = SummarizationConfig(**config_dict)