feat: add citation support in research report block and markdown

* feat: add citation support in research report block and markdown

- Enhanced ResearchReportBlock to fetch citations based on researchId and pass them to the Markdown component.
- Introduced CitationLink component to display citation metadata on hover for links in markdown.
- Implemented CitationCard and CitationList components for displaying citation details and lists.
- Updated Markdown component to handle citation links and inline citations.
- Created HoverCard component for displaying citation information in a tooltip-like manner.
- Modified store to manage citations, including setting and retrieving citations for ongoing research.
- Added CitationsEvent type to handle citations in chat events and updated Message type to include citations.

* fix(log): Enable the logging level  when enabling the DEBUG environment variable (#793)

* fix(frontend): render all tool calls in the frontend #796 (#797)

* build(deps): bump jspdf from 3.0.4 to 4.0.0 in /web (#798)

Bumps [jspdf](https://github.com/parallax/jsPDF) from 3.0.4 to 4.0.0.
- [Release notes](https://github.com/parallax/jsPDF/releases)
- [Changelog](https://github.com/parallax/jsPDF/blob/master/RELEASE.md)
- [Commits](https://github.com/parallax/jsPDF/compare/v3.0.4...v4.0.0)

---
updated-dependencies:
- dependency-name: jspdf
  dependency-version: 4.0.0
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* fix(frontend):added the display of the 'analyst' message #800 (#801)

* fix: migrate from deprecated create_react_agent to langchain.agents.create_agent (#802)

* fix: migrate from deprecated create_react_agent to langchain.agents.create_agent

Fixes #799

- Replace deprecated langgraph.prebuilt.create_react_agent with
  langchain.agents.create_agent (LangGraph 1.0 migration)
- Add DynamicPromptMiddleware to handle dynamic prompt templates
  (replaces the 'prompt' callable parameter)
- Add PreModelHookMiddleware to handle pre-model hooks
  (replaces the 'pre_model_hook' parameter)
- Update AgentState import from langchain.agents in template.py
- Update tests to use the new API

* fix:update the code with review comments

* fix: Add runtime parameter to compress_messages method(#803) 

* fix: Add runtime parameter to compress_messages method(#803)

    The compress_messages method was being called by PreModelHookMiddleware
    with both state and runtime parameters, but only accepted state parameter.
    This caused a TypeError when the middleware executed the pre_model_hook.

    Added optional runtime parameter to compress_messages signature to match
    the expected interface while maintaining backward compatibility.

* Update the code with the review comments

* fix: Refactor citation handling and add comprehensive tests for citation features

* refactor: Clean up imports and formatting across citation modules

* fix: Add monkeypatch to clear AGENT_RECURSION_LIMIT in recursion limit tests

* feat: Enhance citation link handling in Markdown component

* fix: Exclude citations from finish reason handling in mergeMessage function

* fix(nodes): update message handling

* fix(citations): improve citation extraction and handling in event processing

* feat(citations): enhance citation extraction and handling with improved merging and normalization

* fix(reporter): update citation formatting instructions for clarity and consistency

* fix(reporter): prioritize using Markdown tables for data presentation and comparison

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: LoftyComet <1277173875@qq。>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

tests/unit/citations/test_citations.py

@@ -0,0 +1,136 @@
+# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
+# SPDX-License-Identifier: MIT
+
+from langchain_core.messages import ToolMessage
+
+from src.citations.collector import CitationCollector
+from src.citations.extractor import (
+    _extract_domain,
+    citations_to_markdown_references,
+    extract_citations_from_messages,
+    merge_citations,
+)
+from src.citations.formatter import CitationFormatter
+from src.citations.models import Citation, CitationMetadata
+
+
+class TestCitationMetadata:
+    def test_initialization(self):
+        meta = CitationMetadata(
+            url="https://example.com/page",
+            title="Example Page",
+            description="An example description",
+        )
+        assert meta.url == "https://example.com/page"
+        assert meta.title == "Example Page"
+        assert meta.description == "An example description"
+        assert meta.domain == "example.com"  # Auto-extracted in post_init
+
+    def test_id_generation(self):
+        meta = CitationMetadata(url="https://example.com", title="Test")
+        # Just check it's a non-empty string, length 12
+        assert len(meta.id) == 12
+        assert isinstance(meta.id, str)
+
+    def test_to_dict(self):
+        meta = CitationMetadata(
+            url="https://example.com", title="Test", relevance_score=0.8
+        )
+        data = meta.to_dict()
+        assert data["url"] == "https://example.com"
+        assert data["title"] == "Test"
+        assert data["relevance_score"] == 0.8
+        assert "id" in data
+
+
+class TestCitation:
+    def test_citation_wrapper(self):
+        meta = CitationMetadata(url="https://example.com", title="Test")
+        citation = Citation(number=1, metadata=meta)
+
+        assert citation.number == 1
+        assert citation.url == "https://example.com"
+        assert citation.title == "Test"
+        assert citation.to_markdown_reference() == "[Test](https://example.com)"
+        assert citation.to_numbered_reference() == "[1] Test - https://example.com"
+
+
+class TestExtractor:
+    def test_extract_from_tool_message_web_search(self):
+        search_result = {
+            "results": [
+                {
+                    "url": "https://example.com/1",
+                    "title": "Result 1",
+                    "content": "Content 1",
+                    "score": 0.9,
+                }
+            ]
+        }
+
+        msg = ToolMessage(
+            content=str(search_result).replace("'", '"'),  # Simple JSON dump simulation
+            tool_call_id="call_1",
+            name="web_search",
+        )
+        # Mocking json structure if ToolMessage content expects stringified JSON
+        import json
+
+        msg.content = json.dumps(search_result)
+
+        citations = extract_citations_from_messages([msg])
+        assert len(citations) == 1
+        assert citations[0]["url"] == "https://example.com/1"
+        assert citations[0]["title"] == "Result 1"
+
+    def test_extract_domain(self):
+        assert _extract_domain("https://www.example.com/path") == "www.example.com"
+        assert _extract_domain("http://example.org") == "example.org"
+
+    def test_merge_citations(self):
+        existing = [{"url": "https://a.com", "title": "A", "relevance_score": 0.5}]
+        new = [
+            {"url": "https://b.com", "title": "B", "relevance_score": 0.6},
+            {
+                "url": "https://a.com",
+                "title": "A New",
+                "relevance_score": 0.7,
+            },  # Better score for A
+        ]
+
+        merged = merge_citations(existing, new)
+        assert len(merged) == 2
+
+        # Check A was updated
+        a_citation = next(c for c in merged if c["url"] == "https://a.com")
+        assert a_citation["relevance_score"] == 0.7
+
+        # Check B is present
+        b_citation = next(c for c in merged if c["url"] == "https://b.com")
+        assert b_citation["title"] == "B"
+
+    def test_citations_to_markdown(self):
+        citations = [{"url": "https://a.com", "title": "A", "description": "Desc A"}]
+        md = citations_to_markdown_references(citations)
+        assert "## Key Citations" in md
+        assert "- [A](https://a.com)" in md
+
+
+class TestCollector:
+    def test_add_citations(self):
+        collector = CitationCollector()
+        results = [
+            {"url": "https://example.com", "title": "Example", "content": "Test"}
+        ]
+        added = collector.add_from_search_results(results, query="test")
+
+        assert len(added) == 1
+        assert added[0].url == "https://example.com"
+        assert collector.count == 1
+
+
+class TestFormatter:
+    def test_format_inline(self):
+        formatter = CitationFormatter(style="superscript")
+        assert formatter.format_inline_marker(1) == "¹"
+        assert formatter.format_inline_marker(12) == "¹²"

tests/unit/config/test_configuration.py

@@ -135,17 +135,18 @@ def test_from_runnable_config_with_boolean_true_values():
     assert config.enable_deep_thinking is True
     assert config.enforce_web_search is True
 
-
-def test_get_recursion_limit_default():
+def test_get_recursion_limit_default(monkeypatch):
     from src.config.configuration import get_recursion_limit
 
+    monkeypatch.delenv("AGENT_RECURSION_LIMIT", raising=False)
     result = get_recursion_limit()
     assert result == 25
 
 
-def test_get_recursion_limit_custom_default():
+def test_get_recursion_limit_custom_default(monkeypatch):
     from src.config.configuration import get_recursion_limit
 
+    monkeypatch.delenv("AGENT_RECURSION_LIMIT", raising=False)
     result = get_recursion_limit(50)
     assert result == 50