Refactor ag-ui-research. Drop human-in-the-loop, use MemoryObjectSendStream to merge the graph and agent streams together

CHANGELOG.md

@@ -21,6 +21,12 @@
 - **CLI AG-UI Flag**: New `--agui` flag for `serve` command to start AG-UI server
 - **Graph Module**: New unified `haiku.rag.graph` module containing all graph-related functionality
 - **Common Graph Nodes**: New factory functions (`create_plan_node`, `create_search_node`) in `haiku.rag.graph.common.nodes` for reusable graph components
+- **AG-UI Research Example**: New full-stack example (`examples/ag-ui-research`) demonstrating agent+graph architecture with CopilotKit frontend
+  - Pydantic AI agent with research tool that invokes the research graph
+  - Custom AG-UI streaming endpoint with anyio memory streams
+  - React/Next.js frontend with split-pane UI showing live research state
+  - Real-time progress tracking of questions, answers, insights, and gaps
+  - Docker Compose setup for easy local development
 
 ### Changed
 

examples/ag-ui-research/.env.example

@@ -3,6 +3,11 @@
 # Must be an absolute path to an existing database created with haiku-rag
 DB_PATH=/absolute/path/to/your/haiku.rag.lancedb
 
+# Ollama API base URL (if using Ollama for local models)
+# If running Ollama on your host machine, use your machine's IP address
+# that the Docker container can reach (not localhost)
+OLLAMA_BASE_URL=http://host.docker.internal:11434
+
 # API keys (set as needed for your QA provider)
 # OPENAI_API_KEY=your-key-here
 # ANTHROPIC_API_KEY=your-key-here

examples/ag-ui-research/README.md

@@ -1,16 +1,16 @@
 # Interactive Research Assistant
 
-Research assistant powered by [haiku.rag](https://ggozad.github.io/haiku.rag/), [Pydantic AI](https://ai.pydantic.dev/), and [AG-UI](https://docs.ag-ui.com/). Ask complex questions and watch the research process unfold in real-time.
+Research assistant powered by [haiku.rag](https://ggozad.github.io/haiku.rag/), [Pydantic Graph](https://ai.pydantic.dev/graph/), and [AG-UI](https://docs.ag-ui.com/). Ask complex questions and watch the research process unfold in real-time.
 
 [Watch demo video](https://vimeo.com/1128874386)
 
 ## Features
 
-- **Multi-step research workflow**: Question decomposition, search, analysis, and synthesis
+- **Multi-iteration research graph**: Automated question decomposition, search, insight extraction, and gap analysis
-- **Human-in-the-loop**: Approve or revise research plans before execution
+- **Intelligent evaluation**: Confidence-based decision making with automatic iteration until sufficient information is gathered
-- **Live state synchronization**: Real-time updates of research progress between backend and frontend
+- **Live state synchronization**: Real-time delta updates of research progress via AG-UI protocol
-- **Context expansion**: Automatically expands top search results for better context
+- **Insight & gap tracking**: Structured insights with provenance and automatic gap identification
-- **Rich reporting**: Generates structured reports with findings, conclusions, and citations
+- **Rich reporting**: Generates comprehensive research reports with findings, conclusions, and sources
 
 ## Quick Start
 
@@ -57,32 +57,67 @@ Research assistant powered by [haiku.rag](https://ggozad.github.io/haiku.rag/),
 ## How It Works
 
 1. **Ask a question**: Type your research question in the chat
-2. **Review the plan**: The agent decomposes your question into 3 sub-questions
+2. **Plan phase**: The research graph automatically:
-3. **Approve or revise**: Choose to approve the plan or request changes
+   - Decomposes your question into targeted sub-questions
-4. **Watch it work**: The agent automatically:
+   - Gathers initial context about the topic
-   - Searches the knowledge base for each sub-question
+3. **Research iterations**: The graph autonomously:
-   - Extracts key insights from search results
+   - Searches the knowledge base for each sub-question in parallel
-   - Evaluates overall confidence in findings
+   - Extracts structured insights with source provenance
-5. **Get your report**: Receive a structured research report with citations
+   - Identifies information gaps and assesses confidence
+   - Generates new follow-up questions for gaps
+   - Iterates until confidence threshold is met or max iterations reached
+4. **Synthesis**: Generates a comprehensive research report with:
+   - Executive summary
+   - Main findings with supporting evidence
+   - Conclusions and recommendations
+   - Source citations
 
 ## Architecture
 
-- **Backend** (Python): Pydantic AI agent with haiku.rag integration
+### Agent + Graph Pattern
-  - Uses published `ghcr.io/ggozad/haiku.rag:latest` Docker image as base
-  - `agent.py`: Research agent with tool definitions
-  - `main.py`: Starlette app serving AG-UI protocol
 
-- **Frontend** (Next.js): CopilotKit/AG-UI interface
+This example demonstrates the **agent+graph** architecture pattern:
-  - Real-time state synchronization with backend
+
-  - Interactive approval workflow
+1. **Conversational Agent** (`agent.py`):
-  - Collapsible research plan and insights display
+   - Pydantic AI agent handles user conversations
+   - Decides when to invoke the research tool based on user intent
+   - Responds directly to greetings/casual chat without tools
+   - Formats research results for the user
+
+2. **Research Graph** (haiku.rag):
+   - Multi-step research workflow invoked by the agent's tool
+   - Autonomous execution with plan → search → analyze → decide → synthesize flow
+   - Emits AG-UI events for real-time progress tracking
+
+3. **Shared Event Stream**:
+   - `AGUIEmitter` is shared between agent and graph
+   - Events from both flow through a single stream to the frontend
+   - Custom streaming endpoint (`main.py`) uses anyio memory streams for proper async handling
+
+### Components
+
+- **Backend** (Python):
+  - Uses published `ghcr.io/ggozad/haiku.rag:latest` Docker image as base
+  - `agent.py`: Pydantic AI agent with `run_research` tool
+  - `main.py`: Custom AG-UI streaming endpoint with anyio memory object streams
+  - Real-time event forwarding from emitter to SSE stream
+  - Filters out `ACTIVITY_SNAPSHOT` events (not yet supported by CopilotKit)
+
+- **Frontend** (Next.js/React):
+  - CopilotKit for AG-UI protocol integration
+  - Split-pane UI: chat on left, live research state on right
+  - Real-time state synchronization via Server-Sent Events (SSE)
+  - `StateDisplay` component with collapsible sections for questions, insights, and gaps
 
 ## Configuration
 
 Configuration is done through `haiku.rag.yaml` (see `haiku.rag.yaml.example`):
 
-- `qa.provider`: LLM provider (default: `ollama`)
+- `research.provider`: LLM provider (default: `ollama`)
-- `qa.model`: Model name (default: `gpt-oss:latest`)
+- `research.model`: Model name (default: `gpt-oss:latest`)
+- `research.max_iterations`: Maximum research iterations (default: `3`)
+- `research.confidence_threshold`: Confidence threshold for completion (default: `0.8`)
+- `research.max_concurrency`: Parallel sub-question processing (default: `1`)
 - `providers.ollama.base_url`: Ollama endpoint (default: `http://host.docker.internal:11434`)
 
 Environment variables (see `.env.example`):

examples/ag-ui-research/backend/Dockerfile

@@ -3,15 +3,13 @@ FROM ghcr.io/ggozad/haiku.rag:latest
 WORKDIR /app
 
 # Copy backend application files
-COPY agent.py main.py ./
+COPY main.py agent.py ./
-COPY pyproject.toml ./
 
-# Install backend dependencies
+# Install additional dependencies for the example
-# Note: haiku-rag is already installed in the base image
+# Note: haiku-rag-slim is already installed in the base image
 RUN pip install --no-cache-dir \
     starlette>=0.45.2 \
     uvicorn[standard]>=0.34.2 \
-    pydantic-ai-slim[ag-ui,openai]>=1.1.0 \
     python-dotenv>=1.0.1
 
 EXPOSE 8000

examples/ag-ui-research/backend/README.md

@@ -1,6 +1,6 @@
 # Haiku.rag Research Assistant Backend
 
-FastAPI backend for the haiku.rag interactive research assistant, using Pydantic AI with AG-UI protocol support.
+Starlette backend for the haiku.rag interactive research assistant, using the research graph with AG-UI protocol support.
 
 ## Setup
 
@@ -11,7 +11,17 @@ uv run python main.py
 
 The server starts on `http://localhost:8000` and uses [haiku.rag configuration](https://ggozad.github.io/haiku.rag/configuration/).
 
+## Architecture
+
+The backend uses `create_agui_server()` from `haiku.rag.graph.agui.server` which provides:
+
+- **Research graph execution**: Multi-iteration research workflow with insight/gap tracking
+- **AG-UI protocol**: Server-Sent Events (SSE) streaming for real-time state updates
+- **Delta state updates**: Efficient incremental state synchronization using JSON Patch operations
+- **Both research and deep_qa endpoints**: `/agent/research` and `/agent/deep_qa`
+
 ## Endpoints
 
-- `GET /health` - Health check
+- `GET /health` - Health check with configuration info
-- `POST /agent` - AG-UI protocol endpoint
+- `POST /agent/research/stream` - Research graph streaming endpoint (AG-UI protocol)
+- `POST /agent/deep_qa/stream` - Deep QA graph streaming endpoint (AG-UI protocol)

examples/ag-ui-research/backend/agent.py

@@ -1,432 +1,111 @@
-import json
+"""Research assistant agent with graph integration."""
-from dataclasses import dataclass
+
+from dataclasses import dataclass
+from pathlib import Path
+from typing import TYPE_CHECKING
 
-from ag_ui.core import EventType, StateSnapshotEvent
-from pydantic import BaseModel
 from pydantic_ai import Agent, RunContext
-from pydantic_ai.ag_ui import StateDeps
 
 from haiku.rag.client import HaikuRAG
-from haiku.rag.config import Config
+from haiku.rag.config import load_yaml_config
+from haiku.rag.config.models import AppConfig
 from haiku.rag.graph.common import get_model
+from haiku.rag.graph.research.dependencies import ResearchContext
+from haiku.rag.graph.research.graph import build_research_graph
+from haiku.rag.graph.research.state import ResearchDeps, ResearchState
 
+if TYPE_CHECKING:
+    from haiku.rag.graph.agui.emitter import AGUIEmitter
+    from haiku.rag.graph.research.models import ResearchReport
 
-class ResearchState(BaseModel):
+# Load config
-    """Shared state between research agent and frontend."""
+config_path = Path("/app/haiku.rag.yaml")
-
+Config = (
-    question: str = ""
+    AppConfig.model_validate(load_yaml_config(config_path))
-    phase: str = "idle"
+    if config_path.exists()
-    status: str = ""
+    else AppConfig()
-    plan: list[dict] = []
+)
-    current_question_index: int = 0
-    insights: list[dict] = []
-    document_registry: dict[str, dict] = {}
-    current_document: dict | None = None
-    confidence: float = 0.0
-    final_report: dict | None = None
 
 
 @dataclass
-class ResearchDeps(StateDeps[ResearchState]):
+class AgentDeps:
-    """Dependencies for the research agent with HaikuRAG client."""
+    """Dependencies for research agent."""
 
     client: HaikuRAG
+    agui_emitter: "AGUIEmitter[ResearchState, ResearchReport] | None" = None
 
 
-def _as_state_snapshot(ctx: RunContext[ResearchDeps]) -> StateSnapshotEvent:
+model = get_model(Config.research.provider, Config.research.model)
-    return StateSnapshotEvent(type=EventType.STATE_SNAPSHOT, snapshot=ctx.deps.state)
 
-
-def create_agent(
-    qa_provider: str = Config.qa.provider, qa_model: str = Config.qa.model
-) -> Agent[ResearchDeps, str]:
-    """Create and configure the research agent.
-
-    Args:
-        qa_provider: QA provider for the agent (default: from Config.qa.provider)
-        qa_model: Model name to use (default: from Config.qa.model)
-    """
-    print(f"[AGENT SETUP] Creating agent with provider={qa_provider}, model={qa_model}")
 agent = Agent(
-        model=get_model(qa_provider, qa_model),
+    model,
-        deps_type=ResearchDeps,
+    deps_type=AgentDeps,
-        instructions="""You are a research co-pilot powered by haiku.rag.
+    system_prompt="""You are an advanced research assistant powered by haiku.rag.
-
-Your workflow MUST follow these exact steps in order:
-1. Call propose_research_plan with the user's question
-2. After propose_research_plan completes, IMMEDIATELY call approve_research_plan (with no arguments)
-3. WAIT for approve_research_plan to return:
-   - If it returns "APPROVED", proceed to step 4
-   - If it returns "REVISE", ask the user "How would you like me to revise the research plan?" and wait for their response
-   - Once you receive their revision feedback, revise the plan and go back to step 1
-4. Once approved, process questions ONE AT A TIME:
-   - Call search_question(question_id=0) and WAIT for it to complete
-   - Then call extract_insights_from_results(question_id=0) and WAIT for it to complete
-   - Then call search_question(question_id=1) and WAIT for it to complete
-   - Then call extract_insights_from_results(question_id=1) and WAIT for it to complete
-   - Then call search_question(question_id=2) and WAIT for it to complete
-   - Then call extract_insights_from_results(question_id=2) and WAIT for it to complete
-5. After all questions are processed, call evaluate_research_confidence
-6. Ask user if they want to finalize or continue researching
-7. When user approves, call synthesize_final_report
 
 CRITICAL RULES:
-- MANDATORY: Call approve_research_plan immediately after propose_research_plan - NO EXCEPTIONS
+1. For greetings (hi, hello, hey, etc) or casual chat: respond directly WITHOUT using any tools
-- If approve_research_plan returns "REVISE", ask the user for revision feedback naturally in chat
+2. For questions about yourself or the system: respond directly WITHOUT using any tools
-- Call ONE tool at a time - wait for each tool to return before calling the next
+3. For substantive questions requiring information: ALWAYS use the run_research tool
-- NEVER call extract_insights_from_results until search_question has completed and returned results
+4. NEVER answer substantive questions from your own knowledge - always use the tool
-- DO NOT explain what you're about to do - just call the tool
-- The state updates will show the user what's happening - you don't need to narrate
-- Process all 3 questions automatically without asking for approval between them
 
-Document Viewing:
+How to decide:
-- When user asks to "show document X", call get_full_document with the document_uri
+- "Hi" / "Hello" / "How are you?" → Respond directly, NO tools
+- "What can you do?" → Respond directly, NO tools
+- "How does X work in the codebase?" → Use run_research tool
+- "Tell me about Y" → Use run_research tool
 
-Remember: Call tools ONE AT A TIME in sequence. Each tool must complete before calling the next.
+When you use run_research, the graph will decompose questions, search the knowledge base,
-""",
+extract insights, and generate a comprehensive report.
+
+Be friendly and conversational in all responses.""",
 )
 
+
 @agent.tool
-    async def propose_research_plan(
+async def run_research(ctx: RunContext[AgentDeps], question: str) -> str:
-        ctx: RunContext[ResearchDeps], question: str
+    """Execute research graph on a substantive question.
-    ) -> StateSnapshotEvent:
-        """Propose a research plan by decomposing the question into sub-questions."""
-        ctx.deps.state.question = question
-        ctx.deps.state.phase = "planning"
-        ctx.deps.state.status = "Decomposing question into sub-questions..."
 
-        decompose_prompt = f"""Break down this research question into exactly 3 specific sub-questions that would help answer it comprehensively.
+    Use for questions requiring knowledge base search.
+    DO NOT use for greetings or casual conversation.
+    """
+    if ctx.deps.agui_emitter:
+        ctx.deps.agui_emitter.log(f"🔍 Starting research on: {question}")
 
-Research Question: {question}
+    graph = build_research_graph(Config)
+    context = ResearchContext(original_question=question)
+    state = ResearchState.from_config(context=context, config=Config)
 
-Return ONLY a JSON array of sub-questions, like: ["Question 1?", "Question 2?", "Question 3?"]"""
+    graph_deps = ResearchDeps(
-
+        client=ctx.deps.client,
-        response = await ctx.deps.client.ask(decompose_prompt)
+        agui_emitter=ctx.deps.agui_emitter,
+    )
 
     try:
-            sub_questions = json.loads(response)
+        result = await graph.run(state=state, deps=graph_deps)
-        except json.JSONDecodeError:
-            sub_questions = [
-                q.strip().lstrip("0123456789.-) ")
-                for q in response.split("\n")
-                if q.strip()
-            ][:3]
 
-        plan = [
+        if ctx.deps.agui_emitter:
-            {"id": i, "question": q, "status": "pending"}
+            ctx.deps.agui_emitter.log("✅ Research complete!")
-            for i, q in enumerate(sub_questions)
-        ]
 
-        ctx.deps.state.plan = plan
+        return f"""Research completed successfully!
-        ctx.deps.state.current_question_index = 0
-        ctx.deps.state.status = f"Proposed plan with {len(plan)} sub-questions"
 
-        return _as_state_snapshot(ctx)
+Question: {question}
 
-    @agent.tool
+Executive Summary: {result.executive_summary}
-    async def search_question(
-        ctx: RunContext[ResearchDeps],
-        question_id: int,
-        search_type: str = "hybrid",
-    ) -> StateSnapshotEvent:
-        """Execute search for a specific sub-question."""
-        plan = ctx.deps.state.plan
-        if question_id >= len(plan):
-            raise ValueError(f"Question ID {question_id} not found in plan")
 
-        question = plan[question_id]["question"]
+Main Findings:
-        ctx.deps.state.phase = "searching"
+{chr(10).join(f"- {finding}" for finding in result.main_findings[:3])}
-        ctx.deps.state.current_question_index = question_id
-        ctx.deps.state.status = f"Searching: {question}"
-        plan[question_id]["status"] = "searching"
 
-        search_results = await ctx.deps.client.search(
+Conclusions:
-            question, limit=5, search_type=search_type
+{chr(10).join(f"- {conclusion}" for conclusion in result.conclusions[:2])}
-        )
 
-        expanded_map = {}
+Total insights gathered: {len(state.context.insights)}
-        if search_results:
+Confidence: {f"{state.last_eval.confidence_score:.0%}" if state.last_eval else "N/A"}
-            expanded_results = await ctx.deps.client.expand_context(
+Iterations completed: {state.iterations}
-                search_results[:3], radius=2
-            )
-            expanded_map = {
-                chunk.id: (chunk, score) for chunk, score in expanded_results
-            }
 
-        results = []
+The full research report with all citations has been provided to the user.
-        for chunk, score in search_results:
+"""
-            doc_uri = chunk.document_uri or "unknown"
-            doc_title = chunk.document_title or chunk.document_uri or "Unknown"
 
-            if doc_uri not in ctx.deps.state.document_registry:
+    except Exception as e:
-                ctx.deps.state.document_registry[doc_uri] = {
+        if ctx.deps.agui_emitter:
-                    "title": doc_title,
+            ctx.deps.agui_emitter.log(f"❌ Research error: {str(e)}")
-                    "chunks_referenced": [],
+        return f"I encountered an error while researching: {str(e)}"
-                }
-
-            if (
-                chunk.id
-                not in ctx.deps.state.document_registry[doc_uri]["chunks_referenced"]
-            ):
-                ctx.deps.state.document_registry[doc_uri]["chunks_referenced"].append(
-                    chunk.id
-                )
-
-            expanded_chunk, _ = (
-                expanded_map[chunk.id] if chunk.id in expanded_map else (chunk, score)
-            )
-            result_data = {
-                "chunk": expanded_chunk.content[:500],
-                "chunk_id": chunk.id,
-                "document_uri": doc_uri,
-                "document_title": doc_title,
-                "chunk_position": chunk.order,
-                "full_chunk_content": expanded_chunk.content,
-                "score": round(score, 3),
-                "expanded": chunk.id in expanded_map,
-            }
-            results.append(result_data)
-
-        plan[question_id]["search_results"] = {
-            "type": search_type,
-            "results": results,
-        }
-        plan[question_id]["status"] = "searched"
-        ctx.deps.state.status = f"Found {len(results)} results"
-
-        return _as_state_snapshot(ctx)
-
-    @agent.tool
-    async def extract_insights_from_results(
-        ctx: RunContext[ResearchDeps],
-        question_id: int,
-    ) -> StateSnapshotEvent:
-        """Extract key insights from search results for a specific question."""
-        plan = ctx.deps.state.plan
-        if question_id >= len(plan):
-            raise ValueError(f"Question ID {question_id} not found in plan")
-
-        question_item = plan[question_id]
-        if "search_results" not in question_item:
-            raise ValueError(
-                f"No search results found for question ID {question_id}. "
-                f"You must call search_question(question_id={question_id}) first."
-            )
-
-        search_results = question_item["search_results"]
-        ctx.deps.state.phase = "analyzing"
-        ctx.deps.state.status = "Extracting insights from results..."
-
-        context_parts = [
-            f"[Result {idx}] [Source: {r['document_title']}] {r['full_chunk_content']}"
-            for idx, r in enumerate(search_results["results"])
-        ]
-        context = "\n\n".join(context_parts)
-
-        class InsightResult(BaseModel):
-            summary: str
-            confidence: float
-            result_indices: list[int]
-
-        class InsightsList(BaseModel):
-            insights: list[InsightResult]
-
-        question_text = question_item["question"]
-        extract_prompt = f"""Analyze these search results and extract 1-3 key insights that help answer the question: "{question_text}"
-
-Search Results:
-{context}
-
-For each insight, reference which result numbers (0, 1, 2, etc.) support it."""
-
-        insight_agent: Agent[None, InsightsList] = Agent(
-            ctx.model,
-            output_type=InsightsList,
-            retries=3,
-        )
-
-        result = await insight_agent.run(extract_prompt)
-        raw_insights = [
-            {
-                "summary": insight.summary,
-                "confidence": insight.confidence,
-                "result_indices": insight.result_indices,
-            }
-            for insight in result.output.insights
-        ]
-
-        new_insights = []
-        for insight in raw_insights:
-            source_refs = []
-            for idx in insight.get("result_indices", []):
-                if 0 <= idx < len(search_results["results"]):
-                    result = search_results["results"][idx]
-                    source_refs.append(
-                        {
-                            "chunk_id": result["chunk_id"],
-                            "document_uri": result["document_uri"],
-                            "document_title": result["document_title"],
-                            "chunk_position": result["chunk_position"],
-                        }
-                    )
-
-            new_insights.append(
-                {
-                    "summary": insight["summary"],
-                    "confidence": insight.get("confidence", 0.7),
-                    "source_refs": source_refs,
-                }
-            )
-
-        ctx.deps.state.insights.extend(new_insights)
-        plan[question_id]["status"] = "done"
-        ctx.deps.state.status = f"Extracted {len(new_insights)} insights"
-
-        return _as_state_snapshot(ctx)
-
-    @agent.tool
-    async def evaluate_research_confidence(
-        ctx: RunContext[ResearchDeps],
-    ) -> StateSnapshotEvent:
-        """Evaluate overall confidence in the research findings."""
-        insights = ctx.deps.state.insights
-        if not insights:
-            raise ValueError("No insights collected yet")
-
-        ctx.deps.state.phase = "evaluating"
-        ctx.deps.state.status = "Evaluating research confidence..."
-
-        confidences = [i.get("confidence", 0.5) for i in insights]
-        overall_confidence = sum(confidences) / len(confidences) if confidences else 0
-
-        eval_prompt = f"""Evaluate if these insights provide a confident answer to: "{ctx.deps.state.question}"
-
-Insights collected:
-{chr(10).join([f"- {i['summary']}" for i in insights])}
-
-Assess:
-1. Do we have enough information to answer the question?
-2. What gaps remain?
-3. Overall confidence (0.0-1.0)
-
-Return JSON: {{"confidence": 0.0-1.0, "gaps": ["gap1", "gap2"], "recommendation": "continue" or "finalize"}}"""
-
-        response = await ctx.deps.client.ask(eval_prompt)
-
-        try:
-            evaluation = json.loads(response)
-            overall_confidence = evaluation.get("confidence", overall_confidence)
-        except json.JSONDecodeError:
-            pass
-
-        ctx.deps.state.confidence = overall_confidence
-        ctx.deps.state.status = f"Confidence: {overall_confidence:.0%}"
-
-        return _as_state_snapshot(ctx)
-
-    @agent.tool
-    async def synthesize_final_report(
-        ctx: RunContext[ResearchDeps],
-    ) -> StateSnapshotEvent:
-        """Generate final research report with citations."""
-        insights = ctx.deps.state.insights
-        if not insights:
-            raise ValueError("No insights to synthesize")
-
-        ctx.deps.state.phase = "synthesizing"
-        ctx.deps.state.status = "Generating final report..."
-
-        insights_summary = []
-        for i in insights:
-            source_titles = [ref["document_title"] for ref in i.get("source_refs", [])]
-            unique_sources = list(dict.fromkeys(source_titles))
-            insights_summary.append(
-                f"- {i['summary']} (sources: {', '.join(unique_sources[:2])})"
-            )
-
-        report_prompt = f"""Generate a comprehensive research report answering: "{ctx.deps.state.question}"
-
-Based on these insights:
-{chr(10).join(insights_summary)}
-
-Create a structured report with:
-- Executive Summary (2-3 sentences)
-- Main Findings (bullet points)
-- Conclusions
-- Sources (list the document titles mentioned above)
-
-Return JSON with format:
-{{
-    "title": "...",
-    "summary": "...",
-    "findings": ["finding1", "finding2", ...],
-    "conclusions": ["conclusion1", ...],
-    "sources": ["source1", "source2", ...]
-}}"""
-
-        response = await ctx.deps.client.ask(report_prompt)
-
-        try:
-            report = json.loads(response)
-        except json.JSONDecodeError:
-            report = {
-                "title": ctx.deps.state.question,
-                "summary": response[:300],
-                "findings": [i["summary"] for i in insights],
-                "conclusions": ["See findings above"],
-                "sources": [],
-            }
-
-        citations = [
-            {
-                "document_uri": doc_uri,
-                "document_title": doc_info["title"],
-                "chunk_ids": doc_info["chunks_referenced"],
-            }
-            for doc_uri, doc_info in ctx.deps.state.document_registry.items()
-        ]
-        report["citations"] = citations
-
-        ctx.deps.state.final_report = report
-        ctx.deps.state.phase = "done"
-        ctx.deps.state.status = "Research complete"
-
-        return _as_state_snapshot(ctx)
-
-    @agent.tool
-    async def get_full_document(
-        ctx: RunContext[ResearchDeps],
-        document_uri: str,
-    ) -> StateSnapshotEvent:
-        """Retrieve and display the full content of a document by its URI."""
-        ctx.deps.state.status = f"Retrieving document: {document_uri}"
-        document = await ctx.deps.client.get_document_by_uri(document_uri)
-
-        if document is None:
-            ctx.deps.state.status = f"Document not found: {document_uri}"
-            ctx.deps.state.current_document = {
-                "uri": document_uri,
-                "title": "Not Found",
-                "content": f"Document with URI '{document_uri}' was not found.",
-                "total_chunks": 0,
-            }
-        else:
-            all_chunks = await ctx.deps.client.search(
-                query="", limit=1000, search_type="fts"
-            )
-            chunks_for_doc = [
-                c for c, _ in all_chunks if c.document_uri == document_uri
-            ]
-
-            ctx.deps.state.current_document = {
-                "uri": document.uri or document_uri,
-                "title": document.title or "Untitled",
-                "content": document.content,
-                "total_chunks": len(chunks_for_doc),
-                "metadata": document.metadata,
-            }
-            ctx.deps.state.status = f"Retrieved: {document.title or document_uri}"
-
-        return _as_state_snapshot(ctx)
-
-    return agent

examples/ag-ui-research/backend/main.py

@@ -1,27 +1,42 @@
 import logging
 import os
-from contextlib import asynccontextmanager
 from pathlib import Path
 
-from agent import ResearchDeps, ResearchState, create_agent
+from agent import AgentDeps, agent
+from anyio import create_memory_object_stream, create_task_group
+from anyio.streams.memory import MemoryObjectSendStream
 from starlette.applications import Starlette
 from starlette.middleware import Middleware
 from starlette.middleware.cors import CORSMiddleware
-from starlette.responses import JSONResponse
+from starlette.requests import Request
-from starlette.routing import Mount, Route
+from starlette.responses import JSONResponse, StreamingResponse
+from starlette.routing import Route
 
 from haiku.rag.client import HaikuRAG
-from haiku.rag.config import Config
+from haiku.rag.config import load_yaml_config
+from haiku.rag.config.models import AppConfig
+from haiku.rag.graph.agui.emitter import AGUIEmitter
+from haiku.rag.graph.agui.server import RunAgentInput, format_sse_event
+from haiku.rag.graph.research.dependencies import ResearchContext
+from haiku.rag.graph.research.models import ResearchReport
+from haiku.rag.graph.research.state import ResearchState
 
+logging.basicConfig(
+    level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+)
 logger = logging.getLogger(__name__)
 
-client: HaikuRAG | None = None
+# Load config from mounted haiku.rag.yaml
-ag_ui_app = None
+config_path = Path("/app/haiku.rag.yaml")
+if config_path.exists():
+    yaml_data = load_yaml_config(config_path)
+    Config = AppConfig.model_validate(yaml_data)
+else:
+    # Fallback to default config
+    Config = AppConfig()
 
 
-@asynccontextmanager
+# Get DB path from environment
-async def lifespan(app):
-    global client
 db_path_str = os.getenv("DB_PATH", "haiku_rag.lancedb")
 db_path = Path(db_path_str)
 
@@ -30,58 +45,127 @@ async def lifespan(app):
     logger.error("Run: haiku-rag add <path-to-documents>")
     raise RuntimeError(f"Database not found: {db_path}")
 
-    logger.info(f"Initializing HaikuRAG client with database: {db_path}")
+logger.info(f"Initializing research assistant with database: {db_path}")
-    client = HaikuRAG(db_path)
+logger.info(
-    logger.info("Research assistant backend ready")
+    f"Research Provider: {Config.research.provider}, Model: {Config.research.model}"
-    logger.info(f"QA Provider: {Config.qa.provider}, Model: {Config.qa.model}")
+)
 
-    yield
+# Store client reference for proper lifecycle management
-
+_client_cache: dict[str, HaikuRAG] = {}
-    if client:
-        logger.info("Closing HaikuRAG client")
-        client.close()
 
 
-agent = create_agent()
+def get_client(effective_db_path: Path) -> HaikuRAG:
+    """Get or create cached client."""
+    path_key = str(effective_db_path)
+    if path_key not in _client_cache:
+        _client_cache[path_key] = HaikuRAG(db_path=effective_db_path, config=Config)
+    return _client_cache[path_key]
 
 
-async def health(request):
+async def stream_research_agent(request: Request) -> StreamingResponse:
-    db_path_str = os.getenv("DB_PATH", "haiku_rag.lancedb")
+    """Agent streaming endpoint with research graph integration."""
+    body = await request.json()
+    input_data = RunAgentInput(**body)
+
+    user_message = ""
+    if input_data.messages:
+        user_message = input_data.messages[-1].get("content", "")
+
+    send_stream, receive_stream = create_memory_object_stream[str]()
+
+    async def run_agent_with_streaming(
+        send_stream: MemoryObjectSendStream[str],
+    ) -> None:
+        """Execute agent and forward emitter events to memory stream."""
+        async with send_stream:
+            try:
+                # Create shared emitter
+                emitter: AGUIEmitter[ResearchState, ResearchReport] = AGUIEmitter(
+                    thread_id=input_data.thread_id,
+                    run_id=input_data.run_id,
+                    use_deltas=False,
+                )
+
+                # Get client
+                effective_db_path = input_data.config.get("db_path") or db_path
+                if isinstance(effective_db_path, str):
+                    effective_db_path = Path(effective_db_path)
+                client = get_client(effective_db_path)
+
+                # Create agent dependencies with shared emitter
+                agent_deps = AgentDeps(client=client, agui_emitter=emitter)
+
+                # Start run with empty initial state
+                emitter.start_run(
+                    initial_state=ResearchState.from_config(
+                        context=ResearchContext(original_question=""),
+                        config=Config,
+                    )
+                )
+
+                # Forward emitter events to stream
+                async def forward_events():
+                    async for event in emitter:
+                        # Filter out ACTIVITY_SNAPSHOT - not supported by CopilotKit
+                        if event.get("type") == "ACTIVITY_SNAPSHOT":
+                            continue
+                        await send_stream.send(format_sse_event(event))
+
+                # Run agent and event forwarding concurrently
+                async with create_task_group() as tg:
+                    tg.start_soon(forward_events)
+
+                    result = await agent.run(user_message, deps=agent_deps)
+                    emitter.log(result.output)
+                    await emitter.close()
+
+            except Exception as e:
+                logger.exception("Error executing agent")
+                try:
+                    await send_stream.send(
+                        format_sse_event({"type": "error", "error": str(e)})
+                    )
+                except Exception:
+                    pass
+
+    async def event_generator():
+        """Generate SSE events from memory stream."""
+        async with create_task_group() as tg:
+            tg.start_soon(run_agent_with_streaming, send_stream)
+            async with receive_stream:
+                async for event_str in receive_stream:
+                    yield event_str
+
+    return StreamingResponse(
+        event_generator(),
+        media_type="text/event-stream",
+        headers={
+            "Cache-Control": "no-cache",
+            "Connection": "keep-alive",
+            "X-Accel-Buffering": "no",
+        },
+    )
+
+
+async def health_check(_: Request) -> JSONResponse:
+    """Health check endpoint with configuration info."""
     return JSONResponse(
         {
             "status": "healthy",
             "agent_model": str(agent.model),
-            "qa_provider": Config.qa.provider,
+            "research_provider": Config.research.provider,
-            "qa_model": Config.qa.model,
+            "research_model": Config.research.model,
-            "ollama_base_url": Config.providers.ollama.base_url,
+            "db_path": str(db_path),
-            "db_path": db_path_str,
+            "db_exists": db_path.exists(),
-            "db_exists": Path(db_path_str).exists(),
         }
     )
 
 
-def get_ag_ui_app():
+# Create Starlette app
-    global ag_ui_app
-    if ag_ui_app is None and client is not None:
-        research_deps = ResearchDeps(client=client, state=ResearchState())
-        logger.info("Creating AG-UI app")
-        ag_ui_app = agent.to_ag_ui(deps=research_deps)
-    return ag_ui_app
-
-
-async def agent_endpoint(scope, receive, send):
-    app = get_ag_ui_app()
-    if app is None:
-        response = JSONResponse({"error": "Client not initialized"}, status_code=503)
-        await response(scope, receive, send)
-        return
-    await app(scope, receive, send)
-
-
 app = Starlette(
     routes=[
-        Route("/health", health),
+        Route("/v1/research/stream", stream_research_agent, methods=["POST"]),
-        Mount("/agent", agent_endpoint),
+        Route("/health", health_check, methods=["GET"]),
     ],
     middleware=[
         Middleware(
@@ -92,17 +176,11 @@ app = Starlette(
             allow_headers=["*"],
         )
     ],
-    lifespan=lifespan,
 )
 
 if __name__ == "__main__":
     import uvicorn
 
-    print("Starting haiku.rag research assistant backend...")
-    print(f"Agent model: {agent.model}")
-    print(f"QA provider: {Config.qa.provider}")
-    print(f"QA model: {Config.qa.model}")
-
     uvicorn.run(
         "main:app",
         host="0.0.0.0",

examples/ag-ui-research/backend/pyproject.toml

@@ -9,7 +9,7 @@ dependencies = [
     "uvicorn[standard]>=0.34.2",
     "pydantic-ai-slim[ag-ui,openai]>=1.1.0",
     "python-dotenv>=1.0.1",
-    "haiku-rag>=0.12.1",
+    "haiku-rag-slim @ file:///Users/ggozad/dev/open-source/haiku.rag-agui/haiku_rag_slim",
 ]
 
 [dependency-groups]
@@ -18,6 +18,9 @@ dev = [
     "ruff>=0.13.0",
 ]
 
+[tool.hatch.metadata]
+allow-direct-references = true
+
 [tool.hatch.build.targets.wheel]
 packages = ["."]
 

examples/ag-ui-research/docker-compose.yml

@@ -10,11 +10,16 @@ services:
       # API keys (set these in your shell or .env file)
       - OPENAI_API_KEY=${OPENAI_API_KEY}
       - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
+      # Ollama connection (use value from .env)
+      - OLLAMA_BASE_URL=${OLLAMA_BASE_URL}
+      # Prevent Python bytecode caching for development
+      - PYTHONDONTWRITEBYTECODE=1
     volumes:
-      - ./backend:/app
-      - /app/.venv
       - ${DB_PATH}:/app/data/haiku.rag.lancedb
       - ./haiku.rag.yaml:/app/haiku.rag.yaml:ro
+      - ./backend/main.py:/app/main.py
+      - ./backend/agent.py:/app/agent.py
+      - ../../haiku_rag_slim/haiku:/app/.venv/lib/python3.13/site-packages/haiku
     networks:
       - ag-ui-network
     extra_hosts:

examples/ag-ui-research/frontend/app/api/copilotkit/route.ts

@@ -13,7 +13,7 @@ const runtime = new CopilotRuntime({
 	agents: {
 		// "research_agent" maps to the agent name used in useCoAgent() on the frontend
 		research_agent: new HttpAgent({
-			url: `${process.env.BACKEND_URL || "http://backend:8000"}/agent`,
+			url: `${process.env.BACKEND_URL || "http://backend:8000"}/v1/research/stream`,
 		}),
 	},
 });

examples/ag-ui-research/frontend/components/Agent.tsx

@@ -1,208 +1,94 @@
 "use client";
 
-import {
+import { CopilotKit, useCoAgent } from "@copilotkit/react-core";
-	CopilotKit,
-	useCoAgent,
-	useCoAgentStateRender,
-	useCopilotAction,
-} from "@copilotkit/react-core";
 import { CopilotChat } from "@copilotkit/react-ui";
 import "@copilotkit/react-ui/styles.css";
 import StateDisplay from "./StateDisplay";
 
-interface SourceRef {
+interface InsightRecord {
-	chunk_id: string;
+	id: string;
-	document_uri: string;
+	summary: string;
-	document_title: string;
+	status: string;
-	chunk_position: number;
+	notes?: string;
+	supporting_sources: string[];
+	originating_questions: string[];
 }
 
-interface ResearchState {
+interface GapRecord {
-	question: string;
+	id: string;
-	phase: string;
+	description: string;
-	status: string;
+	severity: string;
-	plan: Array<{
+	blocking: boolean;
-		id: number;
+	resolved: boolean;
-		question: string;
+	notes?: string;
-		status: string;
+	supporting_sources: string[];
-		search_results?: {
+	resolved_by: string[];
-			type: string;
-			results: Array<{
-				chunk: string;
-				chunk_id: string;
-				document_uri: string;
-				document_title: string;
-				chunk_position: number;
-				full_chunk_content: string;
-				score: number;
-				expanded: boolean;
-			}>;
-		};
-	}>;
-	current_question_index: number;
-	insights: Array<{
-		summary: string;
-		confidence: number;
-		source_refs: SourceRef[];
-	}>;
-	document_registry: Record<
-		string,
-		{
-			title: string;
-			chunks_referenced: string[];
 }
-	>;
+
-	current_document: {
+interface SearchAnswer {
-		uri: string;
+	query: string;
-		title: string;
+	answer: string;
-		content: string;
-		total_chunks: number;
-		metadata?: Record<string, unknown>;
-	} | null;
 	confidence: number;
-	final_report: {
+	context: string[];
-		title: string;
+	sources: string[];
+}
+
+interface ResearchContext {
+	original_question: string;
+	sub_questions: string[];
+	qa_responses: SearchAnswer[];
+	insights: InsightRecord[];
+	gaps: GapRecord[];
+}
+
+interface EvaluationResult {
+	confidence: number;
+	reasoning: string;
+	should_continue: boolean;
+	gaps_identified: string[];
+	follow_up_questions: string[];
+}
+
+interface ResearchReport {
+	question: string;
 	summary: string;
 	findings: string[];
 	conclusions: string[];
-		sources: string[];
+	insights_used: string[];
-		citations: Array<{
+	methodology: string;
-			document_uri: string;
+}
-			document_title: string;
+
-			chunk_ids: string[];
+interface ResearchState {
-		}>;
+	context: ResearchContext;
+	iterations: number;
+	max_iterations: number;
+	confidence_threshold: number;
+	max_concurrency: number;
+	last_eval: EvaluationResult | null;
+	last_analysis: {
+		insights_extracted: InsightRecord[];
+		gaps_identified: GapRecord[];
 	} | null;
+	result?: ResearchReport;
 }
 
 function AgentContent() {
 	const { state } = useCoAgent<ResearchState>({
 		name: "research_agent",
 		initialState: {
-			question: "",
+			context: {
-			phase: "idle",
+				original_question: "",
-			status: "",
+				sub_questions: [],
-			plan: [],
+				qa_responses: [],
-			current_question_index: 0,
 				insights: [],
-			document_registry: {},
+				gaps: [],
-			current_document: null,
-			confidence: 0.0,
-			final_report: null,
 			},
-	});
+			iterations: 0,
-
+			max_iterations: 3,
-	useCopilotAction({
+			confidence_threshold: 0.8,
-		name: "approve_research_plan",
+			max_concurrency: 1,
-		description:
+			last_eval: null,
-			"Request user approval for the research plan. Returns 'APPROVED' if approved or 'REVISE' if user wants to revise.",
+			last_analysis: null,
-		parameters: [],
-		renderAndWaitForResponse: ({ respond, status }) => (
-			<div
-				style={{
-					padding: "1.5rem",
-					background: "white",
-					borderRadius: "8px",
-					border: "2px solid #4299e1",
-					marginBottom: "1rem",
-					boxShadow: "0 2px 8px rgba(0,0,0,0.1)",
-				}}
-			>
-				<h3
-					style={{
-						fontSize: "1.25rem",
-						fontWeight: "bold",
-						marginBottom: "1rem",
-						color: "#2d3748",
-					}}
-				>
-					Research Plan Approval
-				</h3>
-				<p
-					style={{
-						fontSize: "0.875rem",
-						color: "#4a5568",
-						marginBottom: "1rem",
-					}}
-				>
-					Please review the research plan in the right pane.
-				</p>
-
-				<div
-					style={{
-						display: "flex",
-						gap: "1rem",
-					}}
-					className={status !== "executing" ? "hidden" : ""}
-				>
-					<button
-						type="button"
-						onClick={() => respond?.("REVISE")}
-						disabled={status !== "executing"}
-						style={{
-							flex: 1,
-							padding: "0.75rem",
-							background: "white",
-							border: "2px solid #e2e8f0",
-							borderRadius: "6px",
-							fontSize: "0.875rem",
-							fontWeight: "600",
-							cursor: status === "executing" ? "pointer" : "not-allowed",
-							opacity: status === "executing" ? 1 : 0.5,
-						}}
-					>
-						Revise Plan
-					</button>
-					<button
-						type="button"
-						onClick={() => respond?.("APPROVED")}
-						disabled={status !== "executing"}
-						style={{
-							flex: 1,
-							padding: "0.75rem",
-							background: "#4299e1",
-							color: "white",
-							border: "none",
-							borderRadius: "6px",
-							fontSize: "0.875rem",
-							fontWeight: "600",
-							cursor: status === "executing" ? "pointer" : "not-allowed",
-							opacity: status === "executing" ? 1 : 0.5,
-						}}
-					>
-						Approve & Start Research
-					</button>
-				</div>
-			</div>
-		),
-	});
-
-	useCoAgentStateRender<ResearchState>({
-		name: "research_agent",
-		render: ({ state: newState }) => {
-			const phaseMessages: Record<string, string> = {
-				planning: "Planning research...",
-				searching: "Searching...",
-				analyzing: "Extracting insights...",
-				evaluating: `Evaluating confidence: ${(newState.confidence * 100).toFixed(0)}%`,
-				synthesizing: "Generating final report...",
-				done: "Research complete!",
-			};
-			const phaseMessage =
-				phaseMessages[newState.phase] || newState.status || "Ready";
-
-			return (
-				<div
-					style={{
-						padding: "1rem",
-						background: "#e6f7ff",
-						borderRadius: "4px",
-						marginBottom: "0.5rem",
-						border: "1px solid #91d5ff",
-					}}
-				>
-					<strong>Research Update:</strong> {phaseMessage}
-				</div>
-			);
 		},
 	});
 

examples/ag-ui-research/frontend/components/StateDisplay.tsx

@@ -3,68 +3,70 @@
 import { Markdown } from "@copilotkit/react-ui";
 import { useState } from "react";
 
-interface SourceRef {
+interface InsightRecord {
-	chunk_id: string;
+	id: string;
-	document_uri: string;
+	summary: string;
-	document_title: string;
+	status: string;
-	chunk_position: number;
+	notes?: string;
+	supporting_sources: string[];
+	originating_questions: string[];
 }
 
-interface ResearchState {
+interface GapRecord {
-	question: string;
+	id: string;
-	phase: string;
+	description: string;
-	status: string;
+	severity: string;
-	plan: Array<{
+	blocking: boolean;
-		id: number;
+	resolved: boolean;
-		question: string;
+	notes?: string;
-		status: string;
+	supporting_sources: string[];
-		search_results?: {
+	resolved_by: string[];
-			type: string;
-			results: Array<{
-				chunk: string;
-				chunk_id: string;
-				document_uri: string;
-				document_title: string;
-				chunk_position: number;
-				full_chunk_content: string;
-				score: number;
-				expanded: boolean;
-			}>;
-		};
-	}>;
-	current_question_index: number;
-	insights: Array<{
-		summary: string;
-		confidence: number;
-		source_refs: SourceRef[];
-	}>;
-	document_registry: Record<
-		string,
-		{
-			title: string;
-			chunks_referenced: string[];
 }
-	>;
+
-	current_document: {
+interface SearchAnswer {
-		uri: string;
+	sub_question: string;
-		title: string;
+	answer: string;
-		content: string;
-		total_chunks: number;
-		metadata?: Record<string, unknown>;
-	} | null;
 	confidence: number;
-	final_report: {
+	chunks_used: number;
-		title: string;
+}
+
+interface ResearchContext {
+	original_question: string;
+	sub_questions: string[];
+	qa_responses: SearchAnswer[];
+	insights: InsightRecord[];
+	gaps: GapRecord[];
+}
+
+interface EvaluationResult {
+	confidence: number;
+	reasoning: string;
+	should_continue: boolean;
+	gaps_identified: string[];
+	follow_up_questions: string[];
+}
+
+interface ResearchReport {
+	question: string;
 	summary: string;
 	findings: string[];
 	conclusions: string[];
-		sources: string[];
+	insights_used: string[];
-		citations: Array<{
+	methodology: string;
-			document_uri: string;
+}
-			document_title: string;
+
-			chunk_ids: string[];
+interface ResearchState {
-		}>;
+	context: ResearchContext;
+	iterations: number;
+	max_iterations: number;
+	confidence_threshold: number;
+	max_concurrency: number;
+	last_eval: EvaluationResult | null;
+	last_analysis: {
+		insights_extracted: InsightRecord[];
+		gaps_identified: GapRecord[];
 	} | null;
+	result?: ResearchReport;
 }
 
 interface StateDisplayProps {
@@ -75,14 +77,14 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 	const [expandedSections, setExpandedSections] = useState<
 		Record<string, boolean>
 	>({
-		plan: true,
+		questions: true,
 		insights: true,
+		gaps: true,
 		report: true,
-		document: true,
 	});
 
 	const [expandedQuestions, setExpandedQuestions] = useState<
-		Record<number, boolean>
+		Record<string, boolean>
 	>({});
 
 	const toggleSection = (section: string) => {
@@ -92,20 +94,19 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 		}));
 	};
 
-	const toggleQuestion = (questionId: number) => {
+	const toggleQuestion = (questionId: string) => {
 		setExpandedQuestions((prev) => ({
 			...prev,
 			[questionId]: !prev[questionId],
 		}));
 	};
 
-	// Calculate research progress
+	// Calculate research progress based on iterations
-	const completedQuestions = state.plan.filter(
-		(q) => q.status === "done",
-	).length;
-	const totalQuestions = state.plan.length;
 	const researchProgress =
-		totalQuestions > 0 ? (completedQuestions / totalQuestions) * 100 : 0;
+		state.max_iterations > 0
+			? (state.iterations / state.max_iterations) * 100
+			: 0;
+	const confidence = state.last_eval?.confidence || 0;
 
 	return (
 		<div
@@ -115,7 +116,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 				gap: "1rem",
 			}}
 		>
-			{/* Current Phase & Status */}
+			{/* Current Status */}
 			<div
 				style={{
 					background: "white",
@@ -131,57 +132,48 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 						marginBottom: "0.5rem",
 					}}
 				>
-					Current Phase
+					Research Progress
 				</div>
 				<div style={{ display: "flex", gap: "0.75rem", alignItems: "center" }}>
 					<div
 						style={{
 							padding: "0.5rem 1rem",
 							background:
-								state.phase === "idle"
+								state.iterations === 0
 									? "#e2e8f0"
-									: state.phase === "planning"
+									: state.result
-										? "#fef3c7"
+										? "#d1fae5"
-										: state.phase === "searching"
+										: "#dbeafe",
-											? "#dbeafe"
-											: state.phase === "analyzing"
-												? "#e0e7ff"
-												: state.phase === "evaluating"
-													? "#fce7f3"
-													: "#d1fae5",
 							color:
-								state.phase === "idle"
+								state.iterations === 0
 									? "#718096"
-									: state.phase === "planning"
+									: state.result
-										? "#92400e"
+										? "#065f46"
-										: state.phase === "searching"
+										: "#1e40af",
-											? "#1e40af"
-											: state.phase === "analyzing"
-												? "#3730a3"
-												: state.phase === "evaluating"
-													? "#9f1239"
-													: "#065f46",
 							borderRadius: "6px",
 							fontSize: "1rem",
 							fontWeight: "700",
-							textTransform: "capitalize",
 						}}
 					>
-						{state.phase}
+						{state.iterations === 0
+							? "Ready"
+							: state.result
+								? "Complete"
+								: "Researching"}
 					</div>
-					{state.status && (
+					{state.iterations > 0 && (
 						<div
 							style={{
 								fontSize: "0.875rem",
 								color: "#4a5568",
 							}}
 						>
-							{state.status}
+							Iteration {state.iterations} of {state.max_iterations}
 						</div>
 					)}
 				</div>
 				{/* Research Progress Bar */}
-				{totalQuestions > 0 && state.phase !== "idle" && (
+				{state.iterations > 0 && (
 					<div style={{ marginTop: "1rem" }}>
 						<div
 							style={{
@@ -197,7 +189,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 									color: "#718096",
 								}}
 							>
-								Research Progress
+								Iterations
 							</span>
 							<span
 								style={{
@@ -206,7 +198,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 									color: "#2d3748",
 								}}
 							>
-								{completedQuestions}/{totalQuestions} questions
+								{state.iterations}/{state.max_iterations}
 							</span>
 						</div>
 						<div
@@ -231,7 +223,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 			</div>
 
 			{/* Question */}
-			{state.question && (
+			{state.context.original_question && (
 				<div
 					style={{
 						background: "white",
@@ -256,13 +248,13 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 							color: "#2d3748",
 						}}
 					>
-						{state.question}
+						{state.context.original_question}
 					</div>
 				</div>
 			)}
 
 			{/* Confidence Meter */}
-			{state.confidence > 0 && (
+			{confidence > 0 && (
 				<div
 					style={{
 						background: "white",
@@ -292,12 +284,12 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 						>
 							<div
 								style={{
-									width: `${state.confidence * 100}%`,
+									width: `${confidence * 100}%`,
 									height: "100%",
 									background:
-										state.confidence > 0.8
+										confidence > 0.8
 											? "#48bb78"
-											: state.confidence > 0.5
+											: confidence > 0.5
 												? "#ed8936"
 												: "#f56565",
 									transition: "width 0.3s ease",
@@ -309,21 +301,36 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 								fontSize: "1.5rem",
 								fontWeight: "bold",
 								color:
-									state.confidence > 0.8
+									confidence > 0.8
 										? "#48bb78"
-										: state.confidence > 0.5
+										: confidence > 0.5
 											? "#ed8936"
 											: "#f56565",
 							}}
 						>
-							{(state.confidence * 100).toFixed(0)}%
+							{(confidence * 100).toFixed(0)}%
 						</div>
 					</div>
+					{state.last_eval?.reasoning && (
+						<div
+							style={{
+								marginTop: "0.75rem",
+								fontSize: "0.875rem",
+								color: "#4a5568",
+								padding: "0.75rem",
+								background: "#f7fafc",
+								borderRadius: "4px",
+							}}
+						>
+							<Markdown content={state.last_eval.reasoning} />
+						</div>
+					)}
 				</div>
 			)}
 
-			{/* Research Plan */}
+			{/* Sub-Questions and QA Responses */}
-			{state.plan.length > 0 && (
+			{(state.context.sub_questions.length > 0 ||
+				state.context.qa_responses.length > 0) && (
 				<div
 					style={{
 						background: "white",
@@ -334,7 +341,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 				>
 					<button
 						type="button"
-						onClick={() => toggleSection("plan")}
+						onClick={() => toggleSection("questions")}
 						style={{
 							width: "100%",
 							display: "flex",
@@ -350,10 +357,13 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 							color: "#2d3748",
 						}}
 					>
-						<span>Research Plan ({state.plan.length} questions)</span>
+						<span>
-						<span>{expandedSections.plan ? "▼" : "▶"}</span>
+							Sub-Questions ({state.context.sub_questions.length}) • Answers (
+							{state.context.qa_responses.length})
+						</span>
+						<span>{expandedSections.questions ? "▼" : "▶"}</span>
 					</button>
-					{expandedSections.plan && (
+					{expandedSections.questions && (
 						<div
 							style={{
 								padding: "1rem",
@@ -363,9 +373,43 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 								borderRadius: "0 0 4px 4px",
 							}}
 						>
-							{state.plan.map((item) => (
+							{/* Show pending sub_questions */}
+							{state.context.sub_questions.map((question, idx) => (
 								<div
-									key={item.id}
+									key={`pending-${idx}`}
+									style={{
+										marginBottom: "0.5rem",
+										background: "white",
+										borderRadius: "4px",
+										border: "1px solid #e2e8f0",
+										padding: "0.75rem",
+										display: "flex",
+										gap: "0.75rem",
+										alignItems: "center",
+									}}
+								>
+									<div
+										style={{
+											fontSize: "1.25rem",
+											color: "#a0aec0",
+											flexShrink: 0,
+										}}
+									>
+										⏳
+									</div>
+									<div style={{ flex: 1, fontSize: "0.875rem", color: "#4a5568" }}>
+										<Markdown content={question} />
+									</div>
+								</div>
+							))}
+
+							{/* Show all qa_responses (each has query + answer) */}
+							{state.context.qa_responses.map((qaResponse, idx) => {
+								const questionId = `q-${idx}`;
+
+								return (
+									<div
+										key={questionId}
 										style={{
 											marginBottom: "0.5rem",
 											background: "white",
@@ -376,7 +420,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 									>
 										<button
 											type="button"
-										onClick={() => toggleQuestion(item.id)}
+											onClick={() => toggleQuestion(questionId)}
 											style={{
 												width: "100%",
 												display: "flex",
@@ -392,23 +436,11 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 											<div
 												style={{
 													fontSize: "1.25rem",
-												color:
+													color: "#48bb78",
-													item.status === "done"
-														? "#48bb78"
-														: item.status === "searching" ||
-																item.status === "searched"
-															? "#4299e1"
-															: "#a0aec0",
 													flexShrink: 0,
 												}}
 											>
-											{item.status === "done"
+												✓
-												? "✓"
-												: item.status === "searching"
-													? "🔍"
-													: item.status === "searched"
-														? "📊"
-														: "⏳"}
 											</div>
 											<div style={{ flex: 1 }}>
 												<div
@@ -417,9 +449,8 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 														color: "#4a5568",
 													}}
 												>
-												<Markdown content={item.question} />
+													<Markdown content={qaResponse.query} />
 												</div>
-											{item.search_results && (
 												<div
 													style={{
 														fontSize: "0.75rem",
@@ -427,24 +458,21 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 														marginTop: "0.25rem",
 													}}
 												>
-													{item.search_results.results.length} results
+													Confidence: {(qaResponse.confidence * 100).toFixed(0)}%
 												</div>
-											)}
 											</div>
-										{item.search_results && (
 											<span
 												style={{
 													fontSize: "0.875rem",
 													color: "#718096",
 												}}
 											>
-												{expandedQuestions[item.id] ? "▼" : "▶"}
+												{expandedQuestions[questionId] ? "▼" : "▶"}
 											</span>
-										)}
 										</button>
 
-									{/* Search Results nested inside question */}
+										{/* QA Response nested inside question */}
-									{expandedQuestions[item.id] && item.search_results && (
+										{expandedQuestions[questionId] && (
 											<div
 												style={{
 													padding: "1rem",
@@ -460,87 +488,38 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 														fontWeight: "600",
 													}}
 												>
-												Search Type: {item.search_results.type}
+													Answer
 												</div>
-											{item.search_results.results.map((result, idx) => (
 												<div
-													key={`${result.chunk_id}-${idx}`}
 													style={{
 														padding: "0.75rem",
 														background: "white",
 														borderRadius: "4px",
-														marginBottom: "0.5rem",
 														border: "1px solid #e2e8f0",
 													}}
 												>
 													<div
-														style={{
-															display: "flex",
-															justifyContent: "space-between",
-															marginBottom: "0.5rem",
-														}}
-													>
-														<span
 														style={{
 															fontSize: "0.875rem",
-																fontWeight: "600",
 															color: "#2d3748",
+															lineHeight: "1.5",
 														}}
 													>
-															{result.document_title}
+														<Markdown content={qaResponse.answer} />
-														</span>
-														<div style={{ display: "flex", gap: "0.5rem" }}>
-															{result.expanded && (
-																<span
-																	style={{
-																		fontSize: "0.75rem",
-																		padding: "0.125rem 0.5rem",
-																		background: "#bee3f8",
-																		color: "#2c5282",
-																		borderRadius: "4px",
-																	}}
-																>
-																	Expanded
-																</span>
-															)}
-															<span
-																style={{
-																	fontSize: "0.875rem",
-																	fontWeight: "bold",
-																	color:
-																		result.score > 0.8
-																			? "#48bb78"
-																			: result.score > 0.6
-																				? "#ed8936"
-																				: "#a0aec0",
-																}}
-															>
-																{result.score.toFixed(2)}
-															</span>
 													</div>
 												</div>
-													<div
-														style={{
-															fontSize: "0.875rem",
-															color: "#718096",
-															lineHeight: "1.4",
-														}}
-													>
-														<Markdown content={`${result.chunk}...`} />
-													</div>
-												</div>
-											))}
 											</div>
 										)}
 									</div>
-							))}
+								);
+							})}
 						</div>
 					)}
 				</div>
 			)}
 
 			{/* Insights */}
-			{state.insights.length > 0 && (
+			{state.context.insights.length > 0 && (
 				<div
 					style={{
 						background: "white",
@@ -567,7 +546,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 							color: "#2d3748",
 						}}
 					>
-						<span>Key Insights ({state.insights.length})</span>
+						<span>Key Insights ({state.context.insights.length})</span>
 						<span>{expandedSections.insights ? "▼" : "▶"}</span>
 					</button>
 					{expandedSections.insights && (
@@ -580,9 +559,9 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 								borderRadius: "0 0 4px 4px",
 							}}
 						>
-							{state.insights.map((insight, idx) => (
+							{state.context.insights.map((insight) => (
 								<div
-									key={`${insight.summary.substring(0, 30)}-${idx}`}
+									key={insight.id}
 									style={{
 										padding: "0.75rem",
 										background: "white",
@@ -602,12 +581,22 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 											style={{
 												fontSize: "0.75rem",
 												padding: "0.125rem 0.5rem",
-												background: "#c6f6d5",
+												background:
-												color: "#22543d",
+													insight.status === "validated"
+														? "#c6f6d5"
+														: insight.status === "active"
+															? "#bee3f8"
+															: "#fed7d7",
+												color:
+													insight.status === "validated"
+														? "#22543d"
+														: insight.status === "active"
+															? "#2c5282"
+															: "#742a2a",
 												borderRadius: "4px",
 											}}
 										>
-											{(insight.confidence * 100).toFixed(0)}% confidence
+											{insight.status}
 										</span>
 										<span
 											style={{
@@ -615,7 +604,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 												color: "#718096",
 											}}
 										>
-											{insight.source_refs?.length || 0} sources
+											{insight.supporting_sources.length} sources
 										</span>
 									</div>
 									<div
@@ -628,7 +617,19 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 									>
 										<Markdown content={insight.summary} />
 									</div>
-									{insight.source_refs && insight.source_refs.length > 0 && (
+									{insight.notes && (
+										<div
+											style={{
+												fontSize: "0.75rem",
+												color: "#718096",
+												marginTop: "0.5rem",
+												fontStyle: "italic",
+											}}
+										>
+											<Markdown content={insight.notes} />
+										</div>
+									)}
+									{insight.supporting_sources.length > 0 && (
 										<div
 											style={{
 												fontSize: "0.75rem",
@@ -637,12 +638,174 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 											}}
 										>
 											<span style={{ fontWeight: "600" }}>Sources: </span>
-											{insight.source_refs.map((ref, refIdx) => (
+											{insight.supporting_sources.map((source, srcIdx) => (
-												<span key={ref.chunk_id}>
+												<span key={`${insight.id}-src-${srcIdx}`}>
-													{refIdx > 0 && ", "}
+													{srcIdx > 0 && ", "}
-													<span style={{ fontSize: "0.75rem" }}>
+													{source}
-														{ref.document_title}
 												</span>
+											))}
+										</div>
+									)}
+								</div>
+							))}
+						</div>
+					)}
+				</div>
+			)}
+
+			{/* Knowledge Gaps */}
+			{state.context.gaps.length > 0 && (
+				<div
+					style={{
+						background: "white",
+						borderRadius: "8px",
+						boxShadow: "0 1px 3px rgba(0,0,0,0.1)",
+						overflow: "hidden",
+					}}
+				>
+					<button
+						type="button"
+						onClick={() => toggleSection("gaps")}
+						style={{
+							width: "100%",
+							display: "flex",
+							justifyContent: "space-between",
+							alignItems: "center",
+							padding: "0.75rem",
+							background: "#edf2f7",
+							border: "1px solid #e2e8f0",
+							borderRadius: "4px",
+							cursor: "pointer",
+							fontSize: "1rem",
+							fontWeight: "600",
+							color: "#2d3748",
+						}}
+					>
+						<span>Knowledge Gaps ({state.context.gaps.length})</span>
+						<span>{expandedSections.gaps ? "▼" : "▶"}</span>
+					</button>
+					{expandedSections.gaps && (
+						<div
+							style={{
+								padding: "1rem",
+								background: "#f7fafc",
+								border: "1px solid #e2e8f0",
+								borderTop: "none",
+								borderRadius: "0 0 4px 4px",
+							}}
+						>
+							{state.context.gaps.map((gap) => (
+								<div
+									key={gap.id}
+									style={{
+										padding: "0.75rem",
+										background: "white",
+										borderRadius: "4px",
+										marginBottom: "0.5rem",
+										border: "1px solid #e2e8f0",
+									}}
+								>
+									<div
+										style={{
+											display: "flex",
+											justifyContent: "space-between",
+											marginBottom: "0.5rem",
+											gap: "0.5rem",
+											flexWrap: "wrap",
+										}}
+									>
+										<div style={{ display: "flex", gap: "0.5rem" }}>
+											<span
+												style={{
+													fontSize: "0.75rem",
+													padding: "0.125rem 0.5rem",
+													background:
+														gap.severity === "critical"
+															? "#fed7d7"
+															: gap.severity === "high"
+																? "#feebc8"
+																: gap.severity === "medium"
+																	? "#fef5e7"
+																	: "#e6fffa",
+													color:
+														gap.severity === "critical"
+															? "#742a2a"
+															: gap.severity === "high"
+																? "#7c2d12"
+																: gap.severity === "medium"
+																	? "#744210"
+																	: "#234e52",
+													borderRadius: "4px",
+													fontWeight: "600",
+												}}
+											>
+												{gap.severity}
+											</span>
+											{gap.blocking && (
+												<span
+													style={{
+														fontSize: "0.75rem",
+														padding: "0.125rem 0.5rem",
+														background: "#fed7d7",
+														color: "#742a2a",
+														borderRadius: "4px",
+														fontWeight: "600",
+													}}
+												>
+													Blocking
+												</span>
+											)}
+											{gap.resolved && (
+												<span
+													style={{
+														fontSize: "0.75rem",
+														padding: "0.125rem 0.5rem",
+														background: "#c6f6d5",
+														color: "#22543d",
+														borderRadius: "4px",
+														fontWeight: "600",
+													}}
+												>
+													Resolved
+												</span>
+											)}
+										</div>
+									</div>
+									<div
+										style={{
+											fontSize: "0.875rem",
+											color: "#2d3748",
+											lineHeight: "1.5",
+											marginBottom: "0.5rem",
+										}}
+									>
+										<Markdown content={gap.description} />
+									</div>
+									{gap.notes && (
+										<div
+											style={{
+												fontSize: "0.75rem",
+												color: "#718096",
+												marginTop: "0.5rem",
+												fontStyle: "italic",
+											}}
+										>
+											<Markdown content={gap.notes} />
+										</div>
+									)}
+									{gap.resolved && gap.resolved_by.length > 0 && (
+										<div
+											style={{
+												fontSize: "0.75rem",
+												color: "#718096",
+												marginTop: "0.5rem",
+											}}
+										>
+											<span style={{ fontWeight: "600" }}>Resolved by: </span>
+											{gap.resolved_by.map((source, srcIdx) => (
+												<span key={`${gap.id}-resolved-${srcIdx}`}>
+													{srcIdx > 0 && ", "}
+													{source}
 												</span>
 											))}
 										</div>
@@ -655,7 +818,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 			)}
 
 			{/* Final Report */}
-			{state.final_report && (
+			{state.result && (
 				<div
 					style={{
 						background: "white",
@@ -703,7 +866,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 									color: "#2d3748",
 								}}
 							>
-								{state.final_report.title}
+								{state.result.question}
 							</h3>
 							<div style={{ marginBottom: "1.5rem" }}>
 								<h4
@@ -714,7 +877,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 										marginBottom: "0.5rem",
 									}}
 								>
-									Executive Summary
+									Summary
 								</h4>
 								<div
 									style={{
@@ -723,7 +886,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 										lineHeight: "1.6",
 									}}
 								>
-									<Markdown content={state.final_report.summary} />
+									<Markdown content={state.result.summary} />
 								</div>
 							</div>
 							<div style={{ marginBottom: "1.5rem" }}>
@@ -735,7 +898,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 										marginBottom: "0.5rem",
 									}}
 								>
-									Main Findings
+									Key Findings
 								</h4>
 								<ul
 									style={{
@@ -745,7 +908,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 										lineHeight: "1.6",
 									}}
 								>
-									{state.final_report.findings.map((finding, idx) => (
+									{state.result.findings.map((finding, idx) => (
 										<li
 											key={`finding-${idx}-${finding.substring(0, 30)}`}
 											style={{ marginBottom: "0.5rem" }}
@@ -774,7 +937,7 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 										lineHeight: "1.6",
 									}}
 								>
-									{state.final_report.conclusions.map((conclusion, idx) => (
+									{state.result.conclusions.map((conclusion, idx) => (
 										<li
 											key={`conclusion-${idx}-${conclusion.substring(0, 30)}`}
 											style={{ marginBottom: "0.5rem" }}
@@ -784,6 +947,27 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 									))}
 								</ul>
 							</div>
+							<div style={{ marginBottom: "1.5rem" }}>
+								<h4
+									style={{
+										fontSize: "0.875rem",
+										fontWeight: "600",
+										color: "#718096",
+										marginBottom: "0.5rem",
+									}}
+								>
+									Methodology
+								</h4>
+								<div
+									style={{
+										fontSize: "0.875rem",
+										color: "#4a5568",
+										lineHeight: "1.6",
+									}}
+								>
+									<Markdown content={state.result.methodology} />
+								</div>
+							</div>
 							<div>
 								<h4
 									style={{
@@ -793,10 +977,8 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 										marginBottom: "0.5rem",
 									}}
 								>
-									Citations
+									Insights Used ({state.result.insights_used.length})
 								</h4>
-								{state.final_report.citations &&
-								state.final_report.citations.length > 0 ? (
 								<div
 									style={{
 										display: "flex",
@@ -804,9 +986,13 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 										gap: "0.5rem",
 									}}
 								>
-										{state.final_report.citations.map((citation) => (
+									{state.result.insights_used.map((insightId, idx) => {
+										const insight = state.context.insights.find(
+											(i) => i.id === insightId,
+										);
+										return (
 											<div
-												key={citation.document_uri}
+												key={`insight-${idx}-${insightId}`}
 												style={{
 													padding: "0.5rem",
 													background: "#f7fafc",
@@ -814,45 +1000,31 @@ export default function StateDisplay({ state }: StateDisplayProps) {
 													border: "1px solid #e2e8f0",
 												}}
 											>
+												{insight ? (
 													<div
 														style={{
 															fontSize: "0.875rem",
-														fontWeight: "600",
 															color: "#2d3748",
-														marginBottom: "0.25rem",
+															lineHeight: "1.4",
 														}}
 													>
-													{citation.document_title}
+														<Markdown content={insight.summary} />
-												</div>
-												<div
-													style={{
-														fontSize: "0.75rem",
-														color: "#718096",
-													}}
-												>
-													{citation.chunk_ids.length} chunk
-													{citation.chunk_ids.length !== 1 ? "s" : ""}{" "}
-													referenced
-												</div>
-											</div>
-										))}
 													</div>
 												) : (
 													<div
 														style={{
-											fontSize: "0.75rem",
+															fontSize: "0.875rem",
 															color: "#718096",
-											lineHeight: "1.4",
 														}}
 													>
-										{state.final_report.sources?.map((source) => (
+														Insight ID: {insightId}
-											<div key={source} style={{ marginBottom: "0.25rem" }}>
-												{source}
-											</div>
-										))}
 													</div>
 												)}
 											</div>
+										);
+									})}
+								</div>
+							</div>
 						</div>
 					)}
 				</div>

examples/ag-ui-research/frontend/package-lock.json

@@ -42,6 +42,7 @@
 			"version": "0.0.40",
 			"resolved": "https://registry.npmjs.org/@ag-ui/client/-/client-0.0.40.tgz",
 			"integrity": "sha512-4ftyZgMN7DIAX64k7Mdex/KGq7lfz8yxEKzniqosD6TE/xk65k4Z0v3bxTzPk2iS2+Cj2uVBgFkb5lC7k5Loqg==",
+			"peer": true,
 			"dependencies": {
 				"@ag-ui/core": "0.0.39",
 				"@ag-ui/encoder": "0.0.39",
@@ -58,6 +59,7 @@
 			"version": "0.0.39",
 			"resolved": "https://registry.npmjs.org/@ag-ui/core/-/core-0.0.39.tgz",
 			"integrity": "sha512-T5Hp4oFkQ+H5MynWAvSwrX/rNYJOD+PJ4qPQ0o771oSZQAxoIvDDft47Cx5wRyBNNLXAe1RWqJjfWUUwJFNKqA==",
+			"peer": true,
 			"dependencies": {
 				"rxjs": "7.8.1",
 				"zod": "^3.22.4"
@@ -67,6 +69,7 @@
 			"version": "0.0.39",
 			"resolved": "https://registry.npmjs.org/@ag-ui/encoder/-/encoder-0.0.39.tgz",
 			"integrity": "sha512-6fsoFwPWkStK7Uyj3pwBn7+aQjUWf7pbDTSI43cD53sBLvTr5oEFNnoKOzRfC5UqvHc4JjUIuLKPQyjHRwWg4g==",
+			"peer": true,
 			"dependencies": {
 				"@ag-ui/core": "0.0.39",
 				"@ag-ui/proto": "0.0.39"
@@ -92,6 +95,7 @@
 			"version": "0.0.39",
 			"resolved": "https://registry.npmjs.org/@ag-ui/proto/-/proto-0.0.39.tgz",
 			"integrity": "sha512-xlj/PzZHkJ3CgoQC5QP9g7DEl/78wUK1+A2rdkoLKoNAMOkM2g6jKw0N88iFIh5GZhtiCNN2wb8XwRWPYx9XQQ==",
+			"peer": true,
 			"dependencies": {
 				"@ag-ui/core": "0.0.39",
 				"@bufbuild/protobuf": "^2.2.5",
@@ -127,6 +131,7 @@
 			"resolved": "https://registry.npmjs.org/@aws-crypto/sha256-js/-/sha256-js-5.2.0.tgz",
 			"integrity": "sha512-FFQQyu7edu4ufvIZ+OadFpHHOt+eSTBaYaki44c+akjg7qZg9oOQeLlk77F6tSYqjDAFClrHJk9tMf0HdVyOvA==",
 			"license": "Apache-2.0",
+			"peer": true,
 			"dependencies": {
 				"@aws-crypto/util": "^5.2.0",
 				"@aws-sdk/types": "^3.222.0",
@@ -161,6 +166,7 @@
 			"resolved": "https://registry.npmjs.org/@aws-sdk/client-bedrock-agent-runtime/-/client-bedrock-agent-runtime-3.911.0.tgz",
 			"integrity": "sha512-gXxE6CecfTVM9Uuuja2W69WBT0XoEi0AyTHuN4E7RC7s0SbVZvkCmCgtJ60LTsg7akAa8+AEbIn8aNqxkxV7Kw==",
 			"license": "Apache-2.0",
+			"peer": true,
 			"dependencies": {
 				"@aws-crypto/sha256-browser": "5.2.0",
 				"@aws-crypto/sha256-js": "5.2.0",
@@ -240,6 +246,7 @@
 			"resolved": "https://registry.npmjs.org/@aws-sdk/client-bedrock-runtime/-/client-bedrock-runtime-3.911.0.tgz",
 			"integrity": "sha512-DScoogLAX1WaDF7N3sDvA4l7PKUXRqZWTP1sTjUfUK3hwpAm624RfoQFoxgz5wQPv1zs5Slvntmg8WnPo0T9LQ==",
 			"license": "Apache-2.0",
+			"peer": true,
 			"dependencies": {
 				"@aws-crypto/sha256-browser": "5.2.0",
 				"@aws-crypto/sha256-js": "5.2.0",
@@ -325,6 +332,7 @@
 			"resolved": "https://registry.npmjs.org/@aws-sdk/client-kendra/-/client-kendra-3.911.0.tgz",
 			"integrity": "sha512-insxvWLbh5mRsymBvsq+O/yPgpF1RnYUi2cNYzJDLzHnpsvpdtvrKO1Ymg0Trk32Xh5dW/9W7IMrqI1qDMzBrw==",
 			"license": "Apache-2.0",
+			"peer": true,
 			"dependencies": {
 				"@aws-crypto/sha256-browser": "5.2.0",
 				"@aws-crypto/sha256-js": "5.2.0",
@@ -632,6 +640,7 @@
 			"resolved": "https://registry.npmjs.org/@aws-sdk/credential-provider-node/-/credential-provider-node-3.911.0.tgz",
 			"integrity": "sha512-4oGpLwgQCKNtVoJROztJ4v7lZLhCqcUMX6pe/DQ2aU0TktZX7EczMCIEGjVo5b7yHwSNWt2zW0tDdgVUTsMHPw==",
 			"license": "Apache-2.0",
+			"peer": true,
 			"dependencies": {
 				"@aws-sdk/credential-provider-env": "3.911.0",
 				"@aws-sdk/credential-provider-http": "3.911.0",
@@ -1387,7 +1396,6 @@
 			"resolved": "https://registry.npmjs.org/@browserbasehq/sdk/-/sdk-2.6.0.tgz",
 			"integrity": "sha512-83iXP5D7xMm8Wyn66TUaUrgoByCmAJuoMoZQI3sGg3JAiMlTfnCIMqyVBoNSaItaPIkaCnrsj6LiusmXV2X9YA==",
 			"license": "Apache-2.0",
-      "peer": true,
 			"dependencies": {
 				"@types/node": "^18.11.18",
 				"@types/node-fetch": "^2.6.4",
@@ -1403,7 +1411,6 @@
 			"resolved": "https://registry.npmjs.org/@types/node/-/node-18.19.130.tgz",
 			"integrity": "sha512-GRaXQx6jGfL8sKfaIDD6OupbIHBr9jv7Jnaml9tB7l4v068PAOXqfcujMMo5PhbIs6ggR1XODELqahT2R8v0fg==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"undici-types": "~5.26.4"
 			}
@@ -1412,15 +1419,13 @@
 			"version": "5.26.5",
 			"resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",
 			"integrity": "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/@browserbasehq/stagehand": {
 			"version": "1.14.0",
 			"resolved": "https://registry.npmjs.org/@browserbasehq/stagehand/-/stagehand-1.14.0.tgz",
 			"integrity": "sha512-Hi/EzgMFWz+FKyepxHTrqfTPjpsuBS4zRy3e9sbMpBgLPv+9c0R+YZEvS7Bw4mTS66QtvvURRT6zgDGFotthVQ==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"@anthropic-ai/sdk": "^0.27.3",
 				"@browserbasehq/sdk": "^2.0.0",
@@ -1440,7 +1445,6 @@
 			"resolved": "https://registry.npmjs.org/@anthropic-ai/sdk/-/sdk-0.27.3.tgz",
 			"integrity": "sha512-IjLt0gd3L4jlOfilxVXTifn42FnVffMgDC04RJK1KDZpmkBWLv0XC92MVVmkxrFZNS/7l3xWgP/I3nqtX1sQHw==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"@types/node": "^18.11.18",
 				"@types/node-fetch": "^2.6.4",
@@ -1456,7 +1460,6 @@
 			"resolved": "https://registry.npmjs.org/@types/node/-/node-18.19.130.tgz",
 			"integrity": "sha512-GRaXQx6jGfL8sKfaIDD6OupbIHBr9jv7Jnaml9tB7l4v068PAOXqfcujMMo5PhbIs6ggR1XODELqahT2R8v0fg==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"undici-types": "~5.26.4"
 			}
@@ -1465,8 +1468,7 @@
 			"version": "5.26.5",
 			"resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",
 			"integrity": "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/@bufbuild/protobuf": {
 			"version": "2.9.0",
@@ -2087,7 +2089,6 @@
 			"resolved": "https://registry.npmjs.org/@ibm-cloud/watsonx-ai/-/watsonx-ai-1.7.0.tgz",
 			"integrity": "sha512-TmLaoFXmLc7yVFJIQS25mzZcuWfju4JmRXcO62KthDKNENyPpXXJukrHN6gXfv1BotzFt0M2kyRnO1Vt8ZLlxQ==",
 			"license": "Apache-2.0",
-      "peer": true,
 			"dependencies": {
 				"@types/node": "^18.0.0",
 				"extend": "3.0.2",
@@ -2103,7 +2104,6 @@
 			"resolved": "https://registry.npmjs.org/@types/node/-/node-18.19.130.tgz",
 			"integrity": "sha512-GRaXQx6jGfL8sKfaIDD6OupbIHBr9jv7Jnaml9tB7l4v068PAOXqfcujMMo5PhbIs6ggR1XODELqahT2R8v0fg==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"undici-types": "~5.26.4"
 			}
@@ -2112,8 +2112,7 @@
 			"version": "5.26.5",
 			"resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",
 			"integrity": "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/@img/colour": {
 			"version": "1.0.0",
@@ -2558,6 +2557,7 @@
 			"resolved": "https://registry.npmjs.org/@langchain/aws/-/aws-0.1.15.tgz",
 			"integrity": "sha512-oyOMhTHP0rxdSCVI/g5KXYCOs9Kq/FpXMZbOk1JSIUoaIzUg4p6d98lsHu7erW//8NSaT+SX09QRbVDAgt7pNA==",
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@aws-sdk/client-bedrock-agent-runtime": "^3.755.0",
 				"@aws-sdk/client-bedrock-runtime": "^3.840.0",
@@ -3110,6 +3110,7 @@
 			"resolved": "https://registry.npmjs.org/@langchain/core/-/core-0.3.78.tgz",
 			"integrity": "sha512-Nn0x9erQlK3zgtRU1Z8NUjLuyW0gzdclMsvLQ6wwLeDqV91pE+YKl6uQb+L2NUDs4F0N7c2Zncgz46HxrvPzuA==",
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@cfworker/json-schema": "^4.0.2",
 				"ansi-styles": "^5.0.0",
@@ -3203,7 +3204,6 @@
 			"resolved": "https://registry.npmjs.org/@langchain/langgraph-sdk/-/langgraph-sdk-0.1.10.tgz",
 			"integrity": "sha512-9srSCb2bSvcvehMgjA2sMMwX0o1VUgPN6ghwm5Fwc9JGAKsQa6n1S4eCwy1h4abuYxwajH5n3spBw+4I2WYbgw==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"@types/json-schema": "^7.0.15",
 				"p-queue": "^6.6.2",
@@ -3236,7 +3236,6 @@
 				"https://github.com/sponsors/ctavan"
 			],
 			"license": "MIT",
-      "peer": true,
 			"bin": {
 				"uuid": "dist/bin/uuid"
 			}
@@ -4462,6 +4461,7 @@
 			"resolved": "https://registry.npmjs.org/@smithy/util-utf8/-/util-utf8-2.3.0.tgz",
 			"integrity": "sha512-R8Rdn8Hy72KKcebgLiv8jQcQkXoLMOGGv5uI1/k0l+snqkOzQ1R0ChUBCxWMlBsFMekWjq0wRudIweFs7sKT5A==",
 			"license": "Apache-2.0",
+			"peer": true,
 			"dependencies": {
 				"@smithy/util-buffer-from": "^2.2.0",
 				"tslib": "^2.6.2"
@@ -4535,8 +4535,7 @@
 			"version": "0.3.0",
 			"resolved": "https://registry.npmjs.org/@tokenizer/token/-/token-0.3.0.tgz",
 			"integrity": "sha512-OvjF+z51L3ov0OyAU0duzsYuvO01PH7x4t6DJx+guahgTnBHkhJdG7soQeTSFLWN3efnHyibZ4Z8l2EuWwJN3A==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/@types/debug": {
 			"version": "4.1.12",
@@ -4628,6 +4627,7 @@
 			"resolved": "https://registry.npmjs.org/@types/react/-/react-19.2.2.tgz",
 			"integrity": "sha512-6mDvHUFSjyT2B2yeNx2nUgMxh9LtOWvkhIU3uePn2I2oyNymUAX1NIsdgviM4CH+JSrp2D2hsMvJOkxY+0wNRA==",
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"csstype": "^3.0.2"
 			}
@@ -4658,8 +4658,7 @@
 			"version": "4.0.5",
 			"resolved": "https://registry.npmjs.org/@types/tough-cookie/-/tough-cookie-4.0.5.tgz",
 			"integrity": "sha512-/Ad8+nIOV7Rl++6f1BdKxFSMgmoqEoYbHRpPcx3JEfv8VRsQe9Z4mCXeJBzxs7mbHY/XOZZuXlRNfhpVPbs6ZA==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/@types/unist": {
 			"version": "2.0.11",
@@ -5176,6 +5175,7 @@
 			"resolved": "https://registry.npmjs.org/class-validator/-/class-validator-0.14.2.tgz",
 			"integrity": "sha512-3kMVRF2io8N8pY1IFIXlho9r8IPUUIfHe2hYVtiebvAzU2XeQFXTv+XI4WX+TnXmtwXMDcjngcpkiPM0O9PvLw==",
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@types/validator": "^13.11.8",
 				"libphonenumber-js": "^1.11.1",
@@ -5785,6 +5785,7 @@
 				}
 			],
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"strnum": "^2.1.0"
 			},
@@ -5810,7 +5811,6 @@
 			"resolved": "https://registry.npmjs.org/file-type/-/file-type-16.5.4.tgz",
 			"integrity": "sha512-/yFHK0aGjFEgDJjEKP0pWCplsPFPhwyfwevf/pVxiN0tmE4L9LmwWxWukdJSHdoCli4VgQLehjJtwQBnqmsKcw==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"readable-web-to-node-stream": "^3.0.0",
 				"strtok3": "^6.2.4",
@@ -5876,7 +5876,6 @@
 				}
 			],
 			"license": "MIT",
-      "peer": true,
 			"engines": {
 				"node": ">=4.0"
 			},
@@ -5947,6 +5946,20 @@
 				"node": ">= 0.6"
 			}
 		},
+		"node_modules/fsevents": {
+			"version": "2.3.2",
+			"resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz",
+			"integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==",
+			"hasInstallScript": true,
+			"license": "MIT",
+			"optional": true,
+			"os": [
+				"darwin"
+			],
+			"engines": {
+				"node": "^8.16.0 || ^10.6.0 || >=11.0.0"
+			}
+		},
 		"node_modules/function-bind": {
 			"version": "1.1.2",
 			"resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.2.tgz",
@@ -6035,6 +6048,7 @@
 			"resolved": "https://registry.npmjs.org/google-auth-library/-/google-auth-library-8.9.0.tgz",
 			"integrity": "sha512-f7aQCJODJFmYWN6PeNKzgvy9LI2tYmXnzpNDHEjG5sDNPgGb2FXQyTBnXeSH+PAtpKESFD+LmHw3Ox3mN7e1Fg==",
 			"license": "Apache-2.0",
+			"peer": true,
 			"dependencies": {
 				"arrify": "^2.0.0",
 				"base64-js": "^1.3.0",
@@ -6083,6 +6097,7 @@
 			"resolved": "https://registry.npmjs.org/graphql/-/graphql-16.11.0.tgz",
 			"integrity": "sha512-mS1lbMsxgQj6hge1XZ6p7GPhbrtFwUFYi3wRzXAC/FmYnyXMTvvI3td3rjmQ2u8ewXueaSvRPWaEcgVVOT9Jnw==",
 			"license": "MIT",
+			"peer": true,
 			"engines": {
 				"node": "^12.22.0 || ^14.16.0 || ^16.0.0 || >=17.0.0"
 			}
@@ -6117,6 +6132,7 @@
 			"resolved": "https://registry.npmjs.org/graphql-scalars/-/graphql-scalars-1.25.0.tgz",
 			"integrity": "sha512-b0xyXZeRFkne4Eq7NAnL400gStGqG/Sx9VqX0A05nHyEbv57UJnWKsjNnrpVqv5e/8N1MUxkt0wwcRXbiyKcFg==",
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"tslib": "^2.5.0"
 			},
@@ -6132,6 +6148,7 @@
 			"resolved": "https://registry.npmjs.org/graphql-yoga/-/graphql-yoga-5.16.0.tgz",
 			"integrity": "sha512-/R2dJea7WgvNlXRU4F8iFwWd95Qn1mN+R+yC8XBs1wKjUzr0Pvv8cGYtt6UUcVHw5CiDEtu7iQY5oOe3sDAWCQ==",
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@envelop/core": "^5.3.0",
 				"@envelop/instrumentation": "^1.0.0",
@@ -6709,7 +6726,6 @@
 			"resolved": "https://registry.npmjs.org/ibm-cloud-sdk-core/-/ibm-cloud-sdk-core-5.4.3.tgz",
 			"integrity": "sha512-D0lvClcoCp/HXyaFlCbOT4aTYgGyeIb4ncxZpxRuiuw7Eo79C6c49W53+8WJRD9nxzT5vrIdaky3NBcTdBtaEg==",
 			"license": "Apache-2.0",
-      "peer": true,
 			"dependencies": {
 				"@types/debug": "^4.1.12",
 				"@types/node": "^18.19.80",
@@ -6736,7 +6752,6 @@
 			"resolved": "https://registry.npmjs.org/@types/node/-/node-18.19.130.tgz",
 			"integrity": "sha512-GRaXQx6jGfL8sKfaIDD6OupbIHBr9jv7Jnaml9tB7l4v068PAOXqfcujMMo5PhbIs6ggR1XODELqahT2R8v0fg==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"undici-types": "~5.26.4"
 			}
@@ -6745,8 +6760,7 @@
 			"version": "5.26.5",
 			"resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",
 			"integrity": "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/iconv-lite": {
 			"version": "0.4.24",
@@ -6905,8 +6919,7 @@
 			"version": "0.1.2",
 			"resolved": "https://registry.npmjs.org/isstream/-/isstream-0.1.2.tgz",
 			"integrity": "sha512-Yljz7ffyPbrLpLngrMtZ7NduUgVvi6wG9RJ9IUcyCd59YQ911PBJphODUcbOVbqYfxe1wuYf/LJ8PauMRwsM/g==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/jose": {
 			"version": "5.10.0",
@@ -6976,7 +6989,6 @@
 			"resolved": "https://registry.npmjs.org/jsonwebtoken/-/jsonwebtoken-9.0.2.tgz",
 			"integrity": "sha512-PRp66vJ865SSqOlgqS8hujT5U4AOgMfhrwYIuIhfKaoSCZcirrmASQr8CX7cUg+RMih+hgznrjp99o+W4pJLHQ==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"jws": "^3.2.2",
 				"lodash.includes": "^4.3.0",
@@ -6999,7 +7011,6 @@
 			"resolved": "https://registry.npmjs.org/jwa/-/jwa-1.4.2.tgz",
 			"integrity": "sha512-eeH5JO+21J78qMvTIDdBXidBd6nG2kZjg5Ohz/1fpa28Z4CcsWUzJ1ZZyFq/3z3N17aZy+ZuBoHljASbL1WfOw==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"buffer-equal-constant-time": "^1.0.1",
 				"ecdsa-sig-formatter": "1.0.11",
@@ -7011,7 +7022,6 @@
 			"resolved": "https://registry.npmjs.org/jws/-/jws-3.2.2.tgz",
 			"integrity": "sha512-YHlZCB6lMTllWDtSPHz/ZXTsi8S00usEV6v1tjq8tOUZzw7DpSDWVXjXDre6ed1w/pd495ODpHZYSdkRTsa0HA==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"jwa": "^1.4.1",
 				"safe-buffer": "^5.0.1"
@@ -7242,50 +7252,43 @@
 			"version": "4.3.0",
 			"resolved": "https://registry.npmjs.org/lodash.includes/-/lodash.includes-4.3.0.tgz",
 			"integrity": "sha512-W3Bx6mdkRTGtlJISOvVD/lbqjTlPPUDTMnlXZFnVwi9NKJ6tiAk6LVdlhZMm17VZisqhKcgzpO5Wz91PCt5b0w==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/lodash.isboolean": {
 			"version": "3.0.3",
 			"resolved": "https://registry.npmjs.org/lodash.isboolean/-/lodash.isboolean-3.0.3.tgz",
 			"integrity": "sha512-Bz5mupy2SVbPHURB98VAcw+aHh4vRV5IPNhILUCsOzRmsTmSQ17jIuqopAentWoehktxGd9e/hbIXq980/1QJg==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/lodash.isinteger": {
 			"version": "4.0.4",
 			"resolved": "https://registry.npmjs.org/lodash.isinteger/-/lodash.isinteger-4.0.4.tgz",
 			"integrity": "sha512-DBwtEWN2caHQ9/imiNeEA5ys1JoRtRfY3d7V9wkqtbycnAmTvRRmbHKDV4a0EYc678/dia0jrte4tjYwVBaZUA==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/lodash.isnumber": {
 			"version": "3.0.3",
 			"resolved": "https://registry.npmjs.org/lodash.isnumber/-/lodash.isnumber-3.0.3.tgz",
 			"integrity": "sha512-QYqzpfwO3/CWf3XP+Z+tkQsfaLL/EnUlXWVkIk5FUPc4sBdTehEqZONuyRt2P67PXAk+NXmTBcc97zw9t1FQrw==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/lodash.isplainobject": {
 			"version": "4.0.6",
 			"resolved": "https://registry.npmjs.org/lodash.isplainobject/-/lodash.isplainobject-4.0.6.tgz",
 			"integrity": "sha512-oSXzaWypCMHkPC3NvBEaPHf0KsA5mvPrOPgQWDsbg8n7orZ290M0BmC/jgRZ4vcJ6DTAhjrsSYgdsW/F+MFOBA==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/lodash.isstring": {
 			"version": "4.0.1",
 			"resolved": "https://registry.npmjs.org/lodash.isstring/-/lodash.isstring-4.0.1.tgz",
 			"integrity": "sha512-0wJxfxH1wgO3GrbuP+dTTk7op+6L41QCXbGINEmD+ny/G/eCqGzxyCsh7159S+mgDDcoarnBw6PC1PS5+wUGgw==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/lodash.once": {
 			"version": "4.1.1",
 			"resolved": "https://registry.npmjs.org/lodash.once/-/lodash.once-4.1.1.tgz",
 			"integrity": "sha512-Sb487aTOCr9drQVL8pIxOzVhafOjZN9UU54hiN8PU3uAiSV7lx1yYNpbNmex2PK6dSJoNTSJUUswT651yww3Mg==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/long": {
 			"version": "5.3.2",
@@ -8801,6 +8804,7 @@
 			"resolved": "https://registry.npmjs.org/openai/-/openai-4.104.0.tgz",
 			"integrity": "sha512-p99EFNsA/yX6UhVO93f5kJsDRLAg+CTA2RBqdHK4RtK8u5IJw32Hyb2dTGKbnnFmnuoBv5r7Z2CURI9sGZpSuA==",
 			"license": "Apache-2.0",
+			"peer": true,
 			"dependencies": {
 				"@types/node": "^18.11.18",
 				"@types/node-fetch": "^2.6.4",
@@ -8953,7 +8957,6 @@
 			"resolved": "https://registry.npmjs.org/peek-readable/-/peek-readable-4.1.0.tgz",
 			"integrity": "sha512-ZI3LnwUv5nOGbQzD9c2iDG6toheuXSZP5esSHBjopsXH4dg19soufvpUGA3uohi5anFtGb2lhAVdHzH6R/Evvg==",
 			"license": "MIT",
-      "peer": true,
 			"engines": {
 				"node": ">=8"
 			},
@@ -9054,7 +9057,6 @@
 			"resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.56.0.tgz",
 			"integrity": "sha512-1SXl7pMfemAMSDn5rkPeZljxOCYAmQnYLBTExuh6E8USHXGSX3dx6lYZN/xPpTz1vimXmPA9CDnILvmJaB8aSQ==",
 			"license": "Apache-2.0",
-      "peer": true,
 			"bin": {
 				"playwright-core": "cli.js"
 			},
@@ -9192,15 +9194,13 @@
 			"version": "1.1.0",
 			"resolved": "https://registry.npmjs.org/proxy-from-env/-/proxy-from-env-1.1.0.tgz",
 			"integrity": "sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/psl": {
 			"version": "1.15.0",
 			"resolved": "https://registry.npmjs.org/psl/-/psl-1.15.0.tgz",
 			"integrity": "sha512-JZd3gMVBAVQkSs6HdNZo9Sdo0LNcQeMNP3CozBJb3JYC/QUYZTnKxP+f8oWRX4rHP5EurWxqAHTSwUCjlNKa1w==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"punycode": "^2.3.1"
 			},
@@ -9223,7 +9223,6 @@
 			"resolved": "https://registry.npmjs.org/punycode/-/punycode-2.3.1.tgz",
 			"integrity": "sha512-vYt7UD1U9Wg6138shLtLOvdAu+8DsC/ilFtEVHcH+wydcSpNE20AfSOduf6MkRFahL5FY7X1oU7nKVZFtfq8Fg==",
 			"license": "MIT",
-      "peer": true,
 			"engines": {
 				"node": ">=6"
 			}
@@ -9247,8 +9246,7 @@
 			"version": "2.2.0",
 			"resolved": "https://registry.npmjs.org/querystringify/-/querystringify-2.2.0.tgz",
 			"integrity": "sha512-FIqgj2EUvTa7R50u0rGsyTftzjYmv/a3hO345bZNrqabNqjtgiDMgmo4mkUjd+nzU5oF3dClKqFIPUKybUyqoQ==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/quick-format-unescaped": {
 			"version": "4.0.4",
@@ -9285,6 +9283,7 @@
 			"resolved": "https://registry.npmjs.org/react/-/react-19.2.0.tgz",
 			"integrity": "sha512-tmbWg6W31tQLeB5cdIBOicJDJRR2KzXsV7uSK9iNfLWQ5bIZfxuPEHp7M8wiHyHnn0DD1i7w3Zmin0FtkrwoCQ==",
 			"license": "MIT",
+			"peer": true,
 			"engines": {
 				"node": ">=0.10.0"
 			}
@@ -9294,6 +9293,7 @@
 			"resolved": "https://registry.npmjs.org/react-dom/-/react-dom-19.2.0.tgz",
 			"integrity": "sha512-UlbRu4cAiGaIewkPyiRGJk0imDN2T3JjieT6spoL2UeSf5od4n5LB/mQ4ejmxhCFT1tYe8IvaFulzynWovsEFQ==",
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"scheduler": "^0.27.0"
 			},
@@ -9376,7 +9376,6 @@
 			"resolved": "https://registry.npmjs.org/readable-web-to-node-stream/-/readable-web-to-node-stream-3.0.4.tgz",
 			"integrity": "sha512-9nX56alTf5bwXQ3ZDipHJhusu9NTQJ/CVPtb/XHAJCXihZeitfJvIRS4GqQ/mfIoOE3IelHMrpayVrosdHBuLw==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"readable-stream": "^4.7.0"
 			},
@@ -10385,8 +10384,7 @@
 			"version": "1.0.0",
 			"resolved": "https://registry.npmjs.org/requires-port/-/requires-port-1.0.0.tgz",
 			"integrity": "sha512-KigOCHcocU3XODJxsu8i/j8T9tzT4adHiecwORRQ0ZZFcp7ahwXuRU1m+yuO90C5ZUyGeGfocHDI14M3L3yDAQ==",
-      "license": "MIT",
+			"license": "MIT"
-      "peer": true
 		},
 		"node_modules/retry": {
 			"version": "0.13.1",
@@ -10402,7 +10400,6 @@
 			"resolved": "https://registry.npmjs.org/retry-axios/-/retry-axios-2.6.0.tgz",
 			"integrity": "sha512-pOLi+Gdll3JekwuFjXO3fTq+L9lzMQGcSq7M5gIjExcl3Gu1hd4XXuf5o3+LuSBsaULQH7DiNbsqPd1chVpQGQ==",
 			"license": "Apache-2.0",
-      "peer": true,
 			"engines": {
 				"node": ">=10.7.0"
 			},
@@ -10820,7 +10817,6 @@
 			"resolved": "https://registry.npmjs.org/strtok3/-/strtok3-6.3.0.tgz",
 			"integrity": "sha512-fZtbhtvI9I48xDSywd/somNqgUHl2L2cstmXCCif0itOf96jeW18MBSyrLuNicYQVkvpOxkZtkzujiTJ9LW5Jw==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"@tokenizer/token": "^0.3.0",
 				"peek-readable": "^4.1.0"
@@ -10930,7 +10926,6 @@
 			"resolved": "https://registry.npmjs.org/token-types/-/token-types-4.2.1.tgz",
 			"integrity": "sha512-6udB24Q737UD/SDsKAHI9FCRP7Bqc9D/MQUV02ORQg5iskjtLJlZJNdN4kKtcdtwCeWIwIHDGaUsTsCCAa8sFQ==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"@tokenizer/token": "^0.3.0",
 				"ieee754": "^1.2.1"
@@ -10948,7 +10943,6 @@
 			"resolved": "https://registry.npmjs.org/tough-cookie/-/tough-cookie-4.1.4.tgz",
 			"integrity": "sha512-Loo5UUvLD9ScZ6jh8beX1T6sO1w2/MpCRpEP7V280GKMVUQ0Jzar2U3UJPsrdbziLEMMhu3Ujnq//rhiFuIeag==",
 			"license": "BSD-3-Clause",
-      "peer": true,
 			"dependencies": {
 				"psl": "^1.1.33",
 				"punycode": "^2.1.1",
@@ -11255,7 +11249,6 @@
 			"resolved": "https://registry.npmjs.org/universalify/-/universalify-0.2.0.tgz",
 			"integrity": "sha512-CJ1QgKmNg3CwvAv/kOFmtnEN05f0D/cn9QntgNOQlQF9dgvVTHj3t+8JPdjqawCHk7V/KA+fbUqzZ9XWhcqPUg==",
 			"license": "MIT",
-      "peer": true,
 			"engines": {
 				"node": ">= 4.0.0"
 			}
@@ -11280,7 +11273,6 @@
 			"resolved": "https://registry.npmjs.org/url-parse/-/url-parse-1.5.10.tgz",
 			"integrity": "sha512-WypcfiRhfeUP9vvF0j6rw0J3hrWrw6iZv3+22h6iRMJ/8z1Tj6XfLP4DsUix5MhMPnXpiHDoKyoZ/bdCkwBCiQ==",
 			"license": "MIT",
-      "peer": true,
 			"dependencies": {
 				"querystringify": "^2.1.1",
 				"requires-port": "^1.0.0"
@@ -11578,7 +11570,6 @@
 			"resolved": "https://registry.npmjs.org/ws/-/ws-8.18.3.tgz",
 			"integrity": "sha512-PEIGCY5tSlUt50cqyMXfCzX+oOPqN0vuGqWzbcJ2xvnkzkq46oOpz7dQaTDBdfICb4N14+GARUDw2XV2N4tvzg==",
 			"license": "MIT",
-      "peer": true,
 			"engines": {
 				"node": ">=10.0.0"
 			},
@@ -11663,6 +11654,7 @@
 			"resolved": "https://registry.npmjs.org/zod/-/zod-3.25.76.tgz",
 			"integrity": "sha512-gzUt/qt81nXsFGKIFcC3YnfEAx5NkunCfnDlvuBSSFS02bcXu4Lmea0AFIUwbLWxWPx3d9p8S5QoaujKcNQxcQ==",
 			"license": "MIT",
+			"peer": true,
 			"funding": {
 				"url": "https://github.com/sponsors/colinhacks"
 			}

examples/ag-ui-research/haiku.rag.yaml.example

@@ -1,20 +1,23 @@
 # haiku.rag configuration for ag-ui-research example
 # Copy to haiku.rag.yaml and customize
 
-qa:
+research:
   provider: ollama
   model: gpt-oss:latest
+  max_iterations: 3
+  confidence_threshold: 0.8
+  max_concurrency: 1
 
 providers:
   ollama:
     base_url: http://host.docker.internal:11434
 
 # For OpenAI:
-# qa:
+# research:
 #   provider: openai
 #   model: gpt-4o-mini
 
 # For Anthropic:
-# qa:
+# research:
 #   provider: anthropic
 #   model: claude-3-5-haiku-20241022

haiku_rag_slim/haiku/rag/graph/common/nodes.py

@@ -156,8 +156,11 @@ def create_search_node[AgentDepsT: GraphAgentDeps](
         deps: GraphDeps = ctx.deps  # type: ignore[assignment]
         sub_q = ctx.inputs
 
+        # Create unique step name from question text
+        step_name = f"search: {sub_q}"
+
         if deps.agui_emitter and with_step_wrapper:
-            deps.agui_emitter.start_step("search_one")
+            deps.agui_emitter.start_step(step_name)
 
         try:
             # Create semaphore if not already provided