Develop

.dockerignore

@@ -9,22 +9,20 @@
 # MCP servers have their own build contexts (./mcp/*) and are unaffected.
 
 .git/
-node_modules/
-chroma_data/
 data/
 src/
 mcp/
 scripts/
 
+# Node.js dependencies and build artifacts
+src/node_modules
+src/dist
+
 # Python virtual environments and caches
-backend/venv/
-backend/.venv/
-backend/__pycache__/
-**/__pycache__/
-**/*.pyc
-**/*.pyo
-**/*.pyd
+backend/venv
+backend/.venv
+backend/__pycache__
 
 # Runtime data that should not be baked into the image
-backend/logs/
+backend/logs
 backend/.env

.gitignore

@@ -31,4 +31,5 @@ backend/logs/sessions/*.json
 # Generated reports and retrieved docs
 data/reports/*
 data/benchmarks/*
-data/documents/*
+data/documents/*
+data/neo4j_data/*

backend/Dockerfile

@@ -53,10 +53,8 @@ COPY docs /app/docs
 # written inside the container are immediately visible on the host.
 RUN mkdir -p /app/logs/sessions
 
-
 # Expose API port
 EXPOSE 9999
 
 # Run the API server
-CMD ["uvicorn", "api_server:app", "--host", "0.0.0.0", "--port", "9999"]
-
+CMD ["uvicorn", "api_server:app", "--host", "0.0.0.0", "--port", "9999"]

backend/orchestrator.py

@@ -868,8 +868,15 @@ async def plan(self, query: str) -> AsyncIterator[ResponseMessage]:
                 "\n\nRelevant prior research context (from long-term memory — "
                 "use to avoid re-investigating already-covered ground):\n"
                 + prior_memories
+                + "\n\n"
             )
 
+        # Inject the current date to aid root agent with its temporal reasoning and source evaluation
+        # (e.g. "if your training cutoff is in 2021 but today's date is 2024, you should prioritize
+        #  current sources and be skeptical of outdated info in your training data").
+        current_time = datetime.now(timezone.utc).today().strftime("%m:%d:%Y")
+        plan_prompt += f"\n\nCurrent date: {current_time}\n\n"
+
         root_messages = [
             Message(role="system", content=self._root_system_prompt()),
             Message(role="user", content=plan_prompt),
@@ -1797,7 +1804,7 @@ async def synthesize(self) -> AsyncIterator[ResponseMessage]:
             "- A short section title\n"
             "- One sentence describing what the section will cover\n\n"
             "Return a JSON object:\n"
-            '{"sections": [{"title": "...", "description": "..."}, ...]}'
+            '{"report_title": "...", "sections": [{"title": "...", "description": "..."}, ...]}'
         )
 
         outline_response = await self.agents.report.run(
@@ -1822,6 +1829,7 @@ async def synthesize(self) -> AsyncIterator[ResponseMessage]:
         # Guard against None/empty content — both produce a JSONDecodeError or
         # TypeError that the except block would swallow silently.
         sections: List[Dict[str, str]] = []
+        report_title: str = query
         try:
             raw = outline_response.content or ""
             if raw.startswith("```"):
@@ -1831,7 +1839,9 @@ async def synthesize(self) -> AsyncIterator[ResponseMessage]:
             elif "```" in raw:
                 raw = raw.split("```")[1].split("```")[0].strip()
             if raw:
-                sections = json.loads(raw).get("sections", [])
+                parsed = json.loads(raw)
+                sections = parsed.get("sections", [])
+                report_title = parsed.get("report_title", query)
             else:
                 logger.warning(
                     "[Orchestrator] Outline response was empty after retry; using defaults"
@@ -2103,7 +2113,7 @@ async def synthesize(self) -> AsyncIterator[ResponseMessage]:
         ]
 
         doc_parts: List[str] = [
-            f"RESEARCH REPORT",
+            f"RESEARCH REPORT: {report_title}",
             f"Query: {query}",
             "",
         ]
@@ -2147,14 +2157,13 @@ async def synthesize(self) -> AsyncIterator[ResponseMessage]:
         try:
             from report_exporter import export_report_pdf
 
-            await export_report_pdf(document, query, self.session_id)
+            await export_report_pdf(document, query, report_title, self.session_id)
         except Exception as _pdf_exc:
             logger.warning("[Orchestrator] PDF export error: %s", _pdf_exc)
 
         # ── Extract structured metadata for downstream consumers ────────────
-        # title: query is the ground truth; report header carries no LLM-derived
-        # title in the multi-pass flow, so use the query directly.
-        report_title = query
+        # title was derived from the outline prompt during Phase A; falls back
+        # to the original query if the LLM did not supply one.
 
         # key_findings: content of the first section whose title contains
         # "finding" (case-insensitive), empty string if no such section exists.

backend/report_exporter.py

@@ -229,6 +229,7 @@ def footer(self) -> None:
 async def export_report_pdf(
     document: str,
     query: str,
+    title: str = "",
     session_id: Optional[str] = None,
 ) -> Optional[Path]:
     """
@@ -244,7 +245,8 @@ async def export_report_pdf(
     try:
         reports_dir = _get_reports_dir()
         date_str = datetime.now(timezone.utc).strftime("%Y-%m-%d")
-        slug = _query_to_slug(query)
+        slug_base = title or query
+        slug = _query_to_slug(slug_base)
         sid_part = (session_id or "cli")[:8]
         filename = f"{date_str}_{sid_part}_{slug}.pdf"
         output_path = reports_dir / filename

docker-compose-full.yml

@@ -58,7 +58,7 @@ services:
       - NEO4J_PLUGINS=["apoc"]
       - NEO4J_server_memory_heap_max__size=1G
     volumes:
-      - neo4j_data:/data
+      - ./data/neo4j_data:/data
     restart: unless-stopped
     networks:
       - research-network
@@ -103,7 +103,7 @@ services:
     networks:
       - research-network
     healthcheck:
-      test: [ "CMD", "curl", "-f", "http://localhost:9393/health" ]
+      test: ["CMD", "curl", "-f", "http://localhost:9393/health"]
       interval: 5s
       timeout: 3s
       retries: 10
@@ -120,7 +120,7 @@ services:
     networks:
       - research-network
     healthcheck:
-      test: [ "CMD", "curl", "-f", "http://localhost:9292/health" ]
+      test: ["CMD", "curl", "-f", "http://localhost:9292/health"]
       interval: 5s
       timeout: 3s
       retries: 10
@@ -139,7 +139,7 @@ services:
     networks:
       - research-network
     healthcheck:
-      test: [ "CMD", "curl", "-f", "http://localhost:9191/health" ]
+      test: ["CMD", "curl", "-f", "http://localhost:9191/health"]
       interval: 5s
       timeout: 3s
       retries: 10