feat(research): multi-note pipeline — outline + parallel section synthesis + index note

Replaces the single monolithic research note with topic-driven section notes
plus an index note. Two new LLM calls: _generate_outline (JSON outline, 3-8
sections) and _synthesize_section (300-600 word focused note per section,
parallelised via asyncio.gather). Public signature of run_research_pipeline
unchanged; falls back to single-note synthesis on outline failure or if all
sections fail.

Also extracts _build_sources_block helper and adds full test suite.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/fabledassistant/services/research.py

@@ -21,6 +21,106 @@ MAX_SYNTHESIS_SOURCES = 12  # deduplicated sources passed to synthesis LLM
 CHARS_PER_SOURCE = 2000     # content chars per source sent to synthesis
 
 
+def _build_sources_block(sources: list[dict]) -> str:
+    """Format fetched sources into a text block for LLM prompts."""
+    parts = []
+    for i, s in enumerate(sources, 1):
+        content = (s.get("content") or s.get("snippet") or "")[:CHARS_PER_SOURCE]
+        parts.append(
+            f"[Source {i}] {s['title']}\nURL: {s['url']}\nSearch query: {s['query']}\n\n{content}"
+        )
+    return "\n\n" + ("─" * 60) + "\n\n".join(parts)
+
+
+async def _generate_outline(topic: str, sources: list[dict], model: str) -> list[dict]:
+    """Generate a topic outline from fetched research sources.
+
+    Returns a list of {"title": str, "focus": str} dicts (3–8 entries).
+    Returns [] on failure — callers must fall back to single-note synthesis.
+    """
+    import json as _json
+
+    sources_block = _build_sources_block(sources) if sources else "(no sources)"
+    messages = [
+        {
+            "role": "system",
+            "content": (
+                "You are a research organizer. Given research sources on a topic, produce a JSON array "
+                "of section objects that together cover the topic comprehensively from distinct angles.\n\n"
+                "Rules:\n"
+                "- Return exactly 3–7 sections\n"
+                "- Each section must cover a unique angle — no overlap between sections\n"
+                "- Titles must work as standalone note titles (specific, not generic like 'Overview')\n"
+                "- focus: one sentence describing exactly what this section covers\n"
+                "- Respond with ONLY a JSON array, no other text\n\n"
+                'Example: [{"title": "CRISPR: Molecular Mechanisms", "focus": "How Cas9 identifies and cuts DNA at guide-RNA-specified sites"}]'
+            ),
+        },
+        {
+            "role": "user",
+            "content": f"Topic: {topic}\n\nSources:\n{sources_block}",
+        },
+    ]
+    try:
+        raw = await generate_completion(messages, model, max_tokens=400)
+        raw = raw.strip()
+        raw = re.sub(r"^```(?:json)?\s*", "", raw)
+        raw = re.sub(r"\s*```$", "", raw)
+        idx = raw.find("[")
+        if idx >= 0:
+            parsed, _ = _json.JSONDecoder().raw_decode(raw[idx:])
+            if isinstance(parsed, list):
+                sections = [
+                    s for s in parsed
+                    if isinstance(s, dict) and s.get("title") and s.get("focus")
+                ]
+                if len(sections) >= 3:
+                    return sections[:8]
+    except Exception:
+        logger.warning("Outline generation failed for topic '%s'", topic, exc_info=True)
+    return []
+
+
+async def _synthesize_section(
+    section_title: str,
+    section_focus: str,
+    sources: list[dict],
+    model: str,
+) -> tuple[str, str]:
+    """Synthesize one focused note section.
+
+    Returns (section_title, body_markdown). Does not stream.
+    """
+    sources_block = _build_sources_block(sources) if sources else "(no sources provided)"
+    messages = [
+        {
+            "role": "system",
+            "content": (
+                "You are a focused research writer. Write a single well-structured note section "
+                "on the specific topic provided.\n\n"
+                "Requirements:\n"
+                f"- Focus strictly on: {section_focus}\n"
+                "- 300–600 words of substantive prose\n"
+                "- Use ### for subsections only when they genuinely aid clarity\n"
+                "- Do NOT include a top-level # heading — the title is set separately\n"
+                "- Write in detailed prose paragraphs — not bullet points\n"
+                "- End with a '## Sources' section listing relevant source URLs as markdown hyperlinks\n"
+                "- Ignore source material that falls outside your assigned focus"
+            ),
+        },
+        {
+            "role": "user",
+            "content": (
+                f"Section title: {section_title}\n"
+                f"Focus: {section_focus}\n\n"
+                f"Sources:\n{sources_block}"
+            ),
+        },
+    ]
+    raw = await generate_completion(messages, model, max_tokens=2048, num_ctx=16384)
+    return section_title, raw.strip()
+
+
 async def run_research_pipeline(
     topic: str,
     user_id: int,
@@ -28,14 +128,17 @@ async def run_research_pipeline(
     buf=None,
     project_id: int | None = None,
 ) -> Note:
-    """Full research pipeline: search → fetch → synthesize → create note.
+    """Full research pipeline: search → fetch → outline → section notes → index note.
 
-    Emits status events via buf.append_event throughout (when buf is provided).
+    Emits status events via buf throughout (when buf is provided).
-    Returns the created Note.
+    Returns the index note (or a single fallback note on outline failure).
     """
+    def _status(msg: str) -> None:
+        if buf is not None:
+            buf.append_event("status", {"status": msg})
+
     # Step 1: Generate sub-queries
-    if buf is not None:
+    _status("Generating search queries...")
-        buf.append_event("status", {"status": "Generating search queries..."})
     queries = await _generate_sub_queries(topic, model)
     logger.info("Research: generated %d sub-queries for topic '%s'", len(queries), topic)
 
@@ -43,8 +146,7 @@ async def run_research_pipeline(
     async def _search_with_stagger(i: int, query: str) -> tuple[str, list[dict]]:
         if i > 0:
             await asyncio.sleep(0.2 * i)
-        if buf is not None:
+        _status(f"Searching: {query}...")
-            buf.append_event("status", {"status": f"Searching: {query}..."})
         results = await _search_searxng(query)
         logger.info("Research: query '%s' → %d results", query, len(results))
         return query, results
@@ -66,8 +168,7 @@ async def run_research_pipeline(
     # Fetch all unique URLs in parallel
     async def _fetch_source(url: str, result: dict, query: str) -> dict:
         title = result.get("title", url)
-        if buf is not None:
+        _status(f"Reading: {title[:60]}...")
-            buf.append_event("status", {"status": f"Reading: {title[:60]}..."})
         content = await fetch_url_content(url)
         return {
             "url": url,
@@ -84,39 +185,97 @@ async def run_research_pipeline(
     if not all_sources:
         raise ValueError(f"No results found for '{topic}'")
 
-    # Step 3: Filter failed fetches
+    good_sources = [s for s in all_sources if not s["content"].startswith("[Failed to fetch")]
-    good_sources = [
-        s for s in all_sources
-        if not s["content"].startswith("[Failed to fetch")
-    ]
 
     if not good_sources:
         raise ValueError(f"Could not read any sources for '{topic}'")
 
-    # Limit to top N sources for synthesis (already deduplicated by URL)
     synthesis_sources = good_sources[:MAX_SYNTHESIS_SOURCES]
     logger.info(
         "Research: %d/%d sources successfully fetched, using %d for synthesis",
         len(good_sources), len(all_sources), len(synthesis_sources),
     )
 
-    # Step 4: Synthesize (streams tokens into chat as the note is being written)
+    # Step 3: Generate topic outline
-    if buf is not None:
+    _status("Generating outline...")
-        buf.append_event("status", {"status": f"Synthesizing report from {len(synthesis_sources)} sources..."})
+    outline = await _generate_outline(topic, synthesis_sources, model)
-    title, body = await _synthesize_note(topic, synthesis_sources, model, buf)
 
-    # Step 5: Create note
+    # Fallback: outline failed or too short → single monolithic note
-    if buf is not None:
+    if not outline:
-        buf.append_event("status", {"status": "Saving note..."})
+        logger.warning("Research outline empty, falling back to single note for '%s'", topic)
-    note = await create_note(
+        _status("Synthesizing report...")
+        title, body = await _synthesize_note(topic, synthesis_sources, model, buf=None)
+        note = await create_note(
+            user_id=user_id, title=title, body=body, tags=["research"], project_id=project_id,
+        )
+        logger.info("Research (fallback): created note id=%d title='%s'", note.id, note.title)
+        return note
+
+    # Step 4: Synthesize each section in parallel
+    for section in outline:
+        _status(f"Writing: {section['title']}...")
+
+    raw_results = await asyncio.gather(
+        *[_synthesize_section(s["title"], s["focus"], synthesis_sources, model) for s in outline],
+        return_exceptions=True,
+    )
+
+    # Step 5: Create section notes sequentially
+    _status(f"Saving {len(outline)} notes...")
+    section_note_pairs: list[tuple[dict, Note]] = []
+    for section, result in zip(outline, raw_results):
+        if isinstance(result, Exception):
+            logger.warning("Section synthesis failed for '%s': %s", section["title"], result)
+            continue
+        sec_title, sec_body = result
+        try:
+            note = await create_note(
+                user_id=user_id,
+                title=sec_title,
+                body=sec_body,
+                tags=["research"],
+                project_id=project_id,
+            )
+            section_note_pairs.append((section, note))
+        except Exception:
+            logger.warning("Failed to save section note '%s'", sec_title, exc_info=True)
+
+    # All sections failed — fall back to single note
+    if not section_note_pairs:
+        logger.warning("All section syntheses failed, falling back to single note for '%s'", topic)
+        _status("Synthesizing report (fallback)...")
+        title, body = await _synthesize_note(topic, synthesis_sources, model, buf=None)
+        note = await create_note(
+            user_id=user_id, title=title, body=body, tags=["research"], project_id=project_id,
+        )
+        return note
+
+    # Step 6: Create index note
+    from datetime import date as _date
+    index_lines = [
+        f"Research overview for **{topic}** — {_date.today().isoformat()}",
+        "",
+        f"Generated from {len(synthesis_sources)} web sources across {len(section_note_pairs)} sections.",
+        "",
+        "## Sections",
+        "",
+    ]
+    for section, note in section_note_pairs:
+        index_lines.append(f"- **{note.title}** — {section['focus']}")
+    index_lines += ["", "*Search for any section title to read it.*"]
+
+    index_note = await create_note(
         user_id=user_id,
-        title=title,
+        title=f"Research: {topic}",
-        body=body,
+        body="\n".join(index_lines),
-        tags=["research"],
+        tags=["research", "research-index"],
         project_id=project_id,
     )
-    logger.info("Research: created note id=%d title='%s'", note.id, note.title)
+    logger.info(
-    return note
+        "Research: created %d section notes + index id=%d for topic '%s'",
+        len(section_note_pairs), index_note.id, topic,
+    )
+    return index_note
 
 
 async def _generate_sub_queries(topic: str, model: str) -> list[str]:
@@ -248,13 +407,7 @@ async def _synthesize_note(
     When buf is provided, tokens are streamed into the chat buffer in real time
     so the user can see the note being written. Uses an extended context window.
     """
-    sources_text_parts = []
+    sources_block = _build_sources_block(sources)
-    for i, s in enumerate(sources, 1):
-        content = (s.get("content") or s.get("snippet") or "")[:CHARS_PER_SOURCE]
-        sources_text_parts.append(
-            f"[Source {i}] {s['title']}\nURL: {s['url']}\nSearch query: {s['query']}\n\n{content}"
-        )
-    sources_block = "\n\n" + ("─" * 60) + "\n\n".join(sources_text_parts)
 
     messages = [
         {

tests/test_research_pipeline.py

@@ -0,0 +1,186 @@
+"""Tests for the multi-note research pipeline."""
+import json
+import pytest
+from unittest.mock import AsyncMock, patch
+
+
+@pytest.mark.asyncio
+async def test_generate_outline_parses_valid_json():
+    """_generate_outline returns parsed sections when model returns valid JSON."""
+    from fabledassistant.services.research import _generate_outline
+
+    outline_json = json.dumps([
+        {"title": "Section One", "focus": "Focus one"},
+        {"title": "Section Two", "focus": "Focus two"},
+        {"title": "Section Three", "focus": "Focus three"},
+    ])
+    with patch("fabledassistant.services.research.generate_completion", new_callable=AsyncMock, return_value=outline_json):
+        result = await _generate_outline("test topic", [], "test-model")
+
+    assert len(result) == 3
+    assert result[0]["title"] == "Section One"
+    assert result[0]["focus"] == "Focus one"
+
+
+@pytest.mark.asyncio
+async def test_generate_outline_returns_empty_on_parse_failure():
+    """_generate_outline returns [] when model output is not parseable JSON."""
+    from fabledassistant.services.research import _generate_outline
+
+    with patch("fabledassistant.services.research.generate_completion", new_callable=AsyncMock, return_value="not json at all"):
+        result = await _generate_outline("test topic", [], "test-model")
+
+    assert result == []
+
+
+@pytest.mark.asyncio
+async def test_generate_outline_returns_empty_when_fewer_than_3_sections():
+    """_generate_outline returns [] when model returns fewer than 3 valid sections."""
+    from fabledassistant.services.research import _generate_outline
+
+    outline_json = json.dumps([{"title": "Only One", "focus": "Focus"}])
+    with patch("fabledassistant.services.research.generate_completion", new_callable=AsyncMock, return_value=outline_json):
+        result = await _generate_outline("test topic", [], "test-model")
+
+    assert result == []
+
+
+@pytest.mark.asyncio
+async def test_generate_outline_truncates_to_8():
+    """_generate_outline truncates results to at most 8 sections."""
+    from fabledassistant.services.research import _generate_outline
+
+    sections = [{"title": f"Section {i}", "focus": f"Focus {i}"} for i in range(10)]
+    with patch("fabledassistant.services.research.generate_completion", new_callable=AsyncMock, return_value=json.dumps(sections)):
+        result = await _generate_outline("test topic", [], "test-model")
+
+    assert len(result) == 8
+
+
+@pytest.mark.asyncio
+async def test_generate_outline_skips_malformed_entries():
+    """_generate_outline filters out entries missing title or focus."""
+    from fabledassistant.services.research import _generate_outline
+
+    outline_json = json.dumps([
+        {"title": "Good One", "focus": "Good focus"},
+        {"title": "Missing focus"},
+        {"focus": "Missing title"},
+        {"title": "Good Two", "focus": "Good focus two"},
+        {"title": "Good Three", "focus": "Good focus three"},
+    ])
+    with patch("fabledassistant.services.research.generate_completion", new_callable=AsyncMock, return_value=outline_json):
+        result = await _generate_outline("test topic", [], "test-model")
+
+    assert len(result) == 3
+    assert all(s["title"] and s["focus"] for s in result)
+
+
+@pytest.mark.asyncio
+async def test_synthesize_section_returns_title_and_body():
+    """_synthesize_section returns (section_title, body) from model output."""
+    from fabledassistant.services.research import _synthesize_section
+
+    with patch("fabledassistant.services.research.generate_completion", new_callable=AsyncMock, return_value="The body of this section."):
+        title, body = await _synthesize_section(
+            section_title="Quantum Entanglement: Mechanisms",
+            section_focus="How entanglement works at the particle level",
+            sources=[],
+            model="test-model",
+        )
+
+    assert title == "Quantum Entanglement: Mechanisms"
+    assert body == "The body of this section."
+
+
+@pytest.mark.asyncio
+async def test_synthesize_section_strips_whitespace():
+    """_synthesize_section strips leading/trailing whitespace from body."""
+    from fabledassistant.services.research import _synthesize_section
+
+    with patch("fabledassistant.services.research.generate_completion", new_callable=AsyncMock, return_value="\n\n  body text  \n\n"):
+        title, body = await _synthesize_section("Title", "Focus", [], "model")
+
+    assert body == "body text"
+
+
+@pytest.mark.asyncio
+async def test_pipeline_creates_section_notes_and_index():
+    """run_research_pipeline creates N section notes + 1 index note, returns index."""
+    from unittest.mock import MagicMock
+
+    outline = [
+        {"title": "Section A", "focus": "Focus A"},
+        {"title": "Section B", "focus": "Focus B"},
+        {"title": "Section C", "focus": "Focus C"},
+    ]
+
+    note_id_counter = iter(range(10, 20))
+
+    def _make_note(user_id, title, body, tags, project_id=None):
+        n = MagicMock()
+        n.id = next(note_id_counter)
+        n.title = title
+        return n
+
+    with patch("fabledassistant.services.research._generate_sub_queries", new_callable=AsyncMock, return_value=["q1"]), \
+         patch("fabledassistant.services.research._search_searxng", new_callable=AsyncMock, return_value=[{"url": "http://x.com", "title": "X", "snippet": "s"}]), \
+         patch("fabledassistant.services.research.fetch_url_content", new_callable=AsyncMock, return_value="content"), \
+         patch("fabledassistant.services.research._generate_outline", new_callable=AsyncMock, return_value=outline), \
+         patch("fabledassistant.services.research._synthesize_section", new_callable=AsyncMock, side_effect=lambda t, f, s, m: (t, f"Body for {t}")), \
+         patch("fabledassistant.services.research.create_note", new_callable=AsyncMock, side_effect=_make_note):
+
+        from fabledassistant.services.research import run_research_pipeline
+        result = await run_research_pipeline("test topic", user_id=1, model="test-model")
+
+    assert result.title == "Research: test topic"
+
+
+@pytest.mark.asyncio
+async def test_pipeline_falls_back_to_single_note_when_outline_empty():
+    """run_research_pipeline falls back to single-note synthesis when _generate_outline returns []."""
+    from unittest.mock import MagicMock
+
+    single_note = MagicMock()
+    single_note.id = 99
+    single_note.title = "Research: test topic"
+
+    with patch("fabledassistant.services.research._generate_sub_queries", new_callable=AsyncMock, return_value=["q1"]), \
+         patch("fabledassistant.services.research._search_searxng", new_callable=AsyncMock, return_value=[{"url": "http://x.com", "title": "X", "snippet": "s"}]), \
+         patch("fabledassistant.services.research.fetch_url_content", new_callable=AsyncMock, return_value="content"), \
+         patch("fabledassistant.services.research._generate_outline", new_callable=AsyncMock, return_value=[]), \
+         patch("fabledassistant.services.research._synthesize_note", new_callable=AsyncMock, return_value=("Research: test topic", "body")), \
+         patch("fabledassistant.services.research.create_note", new_callable=AsyncMock, return_value=single_note):
+
+        from fabledassistant.services.research import run_research_pipeline
+        result = await run_research_pipeline("test topic", user_id=1, model="test-model")
+
+    assert result.id == 99
+
+
+@pytest.mark.asyncio
+async def test_pipeline_falls_back_when_all_sections_fail():
+    """run_research_pipeline falls back to single note when all section syntheses raise."""
+    from unittest.mock import MagicMock
+
+    outline = [
+        {"title": "Section A", "focus": "Focus A"},
+        {"title": "Section B", "focus": "Focus B"},
+        {"title": "Section C", "focus": "Focus C"},
+    ]
+    fallback_note = MagicMock()
+    fallback_note.id = 77
+    fallback_note.title = "Research: test topic"
+
+    with patch("fabledassistant.services.research._generate_sub_queries", new_callable=AsyncMock, return_value=["q1"]), \
+         patch("fabledassistant.services.research._search_searxng", new_callable=AsyncMock, return_value=[{"url": "http://x.com", "title": "X", "snippet": "s"}]), \
+         patch("fabledassistant.services.research.fetch_url_content", new_callable=AsyncMock, return_value="content"), \
+         patch("fabledassistant.services.research._generate_outline", new_callable=AsyncMock, return_value=outline), \
+         patch("fabledassistant.services.research._synthesize_section", new_callable=AsyncMock, side_effect=RuntimeError("synthesis failed")), \
+         patch("fabledassistant.services.research._synthesize_note", new_callable=AsyncMock, return_value=("Research: test topic", "body")), \
+         patch("fabledassistant.services.research.create_note", new_callable=AsyncMock, return_value=fallback_note):
+
+        from fabledassistant.services.research import run_research_pipeline
+        result = await run_research_pipeline("test topic", user_id=1, model="test-model")
+
+    assert result.id == 77