fix: address all CodeRabbit Phase 8 review feedback

Actionable issue:
- Forward additional_properties in run_stream for consistent metadata

Nitpicks addressed:
- Report event now uses actual agent message instead of hardcoded text
- Citation validator: documented in-place mutation, use exact title match
- Log truncation uses constant _MAX_URL_DISPLAY_LENGTH
- Test asserts final_report is stored
- Handle empty lists in markdown (hypotheses, drugs, limitations, refs)
- Edge case: show "Untested" when supported==contradicted==0
- Document citations field in ReportSection as reserved for future use

src/agents/report_agent.py

@@ -133,4 +133,8 @@ class ReportAgent(BaseAgent):  # type: ignore[misc]
     ) -> AsyncIterable[AgentRunResponseUpdate]:
         """Streaming wrapper."""
         result = await self.run(messages, thread=thread, **kwargs)
-        yield AgentRunResponseUpdate(messages=result.messages, response_id=result.response_id)
+        yield AgentRunResponseUpdate(
+            messages=result.messages,
+            response_id=result.response_id,
+            additional_properties=result.additional_properties,
+        )

src/orchestrator_magentic.py

@@ -266,7 +266,7 @@ The final output should be a complete research report with:
         elif "report" in agent_name.lower():
             return AgentEvent(
                 type="synthesizing",
-                message="Report generated successfully.",
+                message=f"Report agent: {_truncate(msg_text)}" if msg_text else "Report generated.",
                 iteration=iteration,
             )
         return AgentEvent(

src/utils/citation_validator.py

@@ -12,22 +12,29 @@ if TYPE_CHECKING:
 
 logger = logging.getLogger(__name__)
 
+# Max characters to display for URLs in log messages
+_MAX_URL_DISPLAY_LENGTH = 80
+
 
 def validate_references(report: "ResearchReport", evidence: list["Evidence"]) -> "ResearchReport":
     """Ensure all references actually exist in collected evidence.
 
     CRITICAL: Prevents LLM hallucination of citations.
 
+    Note:
+        This function MUTATES report.references in-place and returns the same
+        report object. This is intentional for efficiency.
+
     Args:
-        report: The generated research report
+        report: The generated research report (will be mutated)
         evidence: All evidence collected during research
 
     Returns:
-        Report with only valid references (hallucinated ones removed)
+        The same report object with references updated in-place
     """
     # Build set of valid URLs from evidence
     valid_urls = {e.citation.url for e in evidence}
-    # Also check titles (case-insensitive) as fallback
+    # Also check titles (case-insensitive, exact match) as fallback
     valid_titles = {e.citation.title.lower() for e in evidence}
 
     validated_refs = []
@@ -40,14 +47,19 @@ def validate_references(report: "ResearchReport", evidence: list["Evidence"]) ->
         # Check if URL matches collected evidence
         if ref_url in valid_urls:
             validated_refs.append(ref)
-        # Fallback: check title match (URLs might differ slightly)
-        elif ref_title and any(ref_title in t or t in ref_title for t in valid_titles):
+        # Fallback: exact title match (case-insensitive)
+        elif ref_title and ref_title in valid_titles:
             validated_refs.append(ref)
         else:
             removed_count += 1
+            # Truncate URL for display
+            if len(ref_url) > _MAX_URL_DISPLAY_LENGTH:
+                url_display = ref_url[:_MAX_URL_DISPLAY_LENGTH] + "..."
+            else:
+                url_display = ref_url
             logger.warning(
                 f"Removed hallucinated reference: '{ref.get('title', 'Unknown')}' "
-                f"(URL: {ref_url[:50]}...)"
+                f"(URL: {url_display})"
             )
 
     if removed_count > 0:

src/utils/models.py

@@ -177,6 +177,7 @@ class ReportSection(BaseModel):
 
     title: str
     content: str
+    # Reserved for future inline citation tracking within sections
     citations: list[str] = Field(default_factory=list)
 
 
@@ -224,10 +225,17 @@ class ResearchReport(BaseModel):
 
         # Hypotheses
         sections.append("## Hypotheses Tested\n")
+        if not self.hypotheses_tested:
+            sections.append("*No hypotheses tested yet.*\n")
         for h in self.hypotheses_tested:
             supported = h.get("supported", 0)
             contradicted = h.get("contradicted", 0)
-            status = "✅ Supported" if supported > contradicted else "⚠️ Mixed"
+            if supported == 0 and contradicted == 0:
+                status = "❓ Untested"
+            elif supported > contradicted:
+                status = "✅ Supported"
+            else:
+                status = "⚠️ Mixed"
             sections.append(
                 f"- **{h.get('mechanism', 'Unknown')}** ({status}): "
                 f"{supported} supporting, {contradicted} contradicting\n"
@@ -239,26 +247,35 @@ class ResearchReport(BaseModel):
 
         # Drug candidates
         sections.append("## Drug Candidates\n")
-        for drug in self.drug_candidates:
-            sections.append(f"- **{drug}**\n")
+        if self.drug_candidates:
+            for drug in self.drug_candidates:
+                sections.append(f"- **{drug}**\n")
+        else:
+            sections.append("*No drug candidates identified.*\n")
 
         # Limitations
         sections.append("## Limitations\n")
-        for lim in self.limitations:
-            sections.append(f"- {lim}\n")
+        if self.limitations:
+            for lim in self.limitations:
+                sections.append(f"- {lim}\n")
+        else:
+            sections.append("*No limitations documented.*\n")
 
         # Conclusion
         sections.append(f"## Conclusion\n{self.conclusion}\n")
 
         # References
         sections.append("## References\n")
-        for i, ref in enumerate(self.references, 1):
-            sections.append(
-                f"{i}. {ref.get('authors', 'Unknown')}. "
-                f"*{ref.get('title', 'Untitled')}*. "
-                f"{ref.get('source', '')} ({ref.get('date', '')}). "
-                f"[Link]({ref.get('url', '#')})\n"
-            )
+        if self.references:
+            for i, ref in enumerate(self.references, 1):
+                sections.append(
+                    f"{i}. {ref.get('authors', 'Unknown')}. "
+                    f"*{ref.get('title', 'Untitled')}*. "
+                    f"{ref.get('source', '')} ({ref.get('date', '')}). "
+                    f"[Link]({ref.get('url', '#')})\n"
+                )
+        else:
+            sections.append("*No references available.*\n")
 
         # Metadata footer
         sections.append("\n---\n")

tests/unit/agents/test_report_agent.py

@@ -109,6 +109,8 @@ async def test_report_agent_generates_report(
         assert "Executive Summary" in response.messages[0].text
         assert "Methodology" in response.messages[0].text
         assert "References" in response.messages[0].text
+        # Verify report is stored in evidence store
+        assert "final_report" in store
 
 
 @pytest.mark.asyncio