web: show "Re-extract only" for articles too

Gate was source_type == 'video', but the service-layer reset already
accepts any source with transcript_text — articles store the
trafilatura-extracted body there, so they're equally valid candidates
for an extract-only retry. Caught by a-review.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

reviews/a-review-2026-05-25.md

@@ -0,0 +1,37 @@
+# a-review — 2026-05-25
+
+**Model:** gemini
+**Diff base:** `HEAD~1` (5 files changed, 615 insertions(+), 30 deletions(-))
+**Session reference:** none
+**Context:** CLAUDE.md + session notes + expanded diff
+
+---
+
+Excellent work. The changes are well-structured, follow existing project conventions, and include a comprehensive test suite. This is a high-quality contribution. I have only one minor finding and one informational note.
+
+### [WARNING] Logic Error
+
+*   **File:** `src/second_brain/web/templates/source_detail.html`
+*   **Location:** Line 151
+*   **Issue:** The "Re-extract only" button is conditionally rendered with `{% if source.has_transcript and source.source_type == 'video' %}`. This is too restrictive. The backend service function `reset_source_for_retry` correctly allows an "extract" retry for any source that has content in `transcript_text`, which includes processed articles. Limiting this feature to only videos in the UI prevents a valid and useful action for non-video sources.
+*   **Suggestion:** Change the conditional to `{% if source.has_transcript %}`. This will correctly show the button for any source (article or video) that has been pulled and has content ready for extraction, which matches the backend's capability.
+
+```html
+    <!-- Change this -->
+    {% if source.has_transcript and source.source_type == 'video' %}
+    
+    <!-- To this -->
+    {% if source.has_transcript %}
+```
+
+### [INFO] Security
+
+*   **Files:** `src/second_brain/web/app.py`, `src/second_brain/web/templates/source_detail.html`
+*   **Observation:** The changes introduce new endpoints (`/edit`, `/retry`) that modify database state. According to `CLAUDE.md`, the application has "No auth" and relies on being deployed in a trusted, LAN-only environment. These new endpoints increase the number of ways an unauthorized user on the network could alter data.
+*   **Context:** This is not a new vulnerability, but an expansion of the existing trust model. As long as the application remains on a trusted network, this is acceptable per the project's documented security posture. It's worth keeping in mind that no CSRF protection is being used for these HTMX `POST` actions.
+
+### Summary
+
+The overall code quality is very high. The changes are thoughtfully implemented, with a clean separation between the CLI, the web layer, and a shared service layer. The refactoring in `web/app.py` to create `_render_source_detail` is a good move for maintainability. The addition of a thorough, live-DB test suite for the new service functions is commendable and demonstrates a commitment to quality.
+
+Once the minor template logic issue is resolved, this change will be in perfect shape.

src/second_brain/main.py

@@ -4,6 +4,7 @@ second-brain CLI entry point.
 Commands:
   add       — queue a source URL (video or article)
   process   — run the full pipeline on pending/pulled/transcribed sources
+  retry     — reset a source so the pipeline re-processes it
   serve     — launch the FastAPI web UI
   compile   — run the wiki compiler on accepted sources
   schedule  — start the overnight scheduler
@@ -307,6 +308,47 @@ def serve(host: str, port: int, reload: bool) -> None:
     )
 
 
+# ---------------------------------------------------------------------------
+# retry
+# ---------------------------------------------------------------------------
+
+
+@cli.command()
+@click.argument("source_id", type=int)
+@click.option(
+    "--mode",
+    type=click.Choice(["full", "extract"]),
+    default="full",
+    show_default=True,
+    help="`full` resets to PENDING (re-pull + re-process); "
+    "`extract` resets to TRANSCRIBED (requires existing transcript).",
+)
+def retry(source_id: int, mode: str) -> None:
+    """Reset a source so the pipeline re-processes it.
+
+    Clears the claim pair and error_message and rewinds status to the
+    appropriate stage. Parity with the dashboard re-run buttons.
+    """
+    from second_brain.sources_service import reset_source_for_retry
+
+    db = get_database()
+    try:
+        with db.session() as sess:
+            source = reset_source_for_retry(
+                sess, source_id=source_id, mode=mode
+            )
+            new_status = source.status.value
+            url = source.url
+    except LookupError as exc:
+        click.echo(f"[retry] {exc}", err=True)
+        sys.exit(2)
+    except ValueError as exc:
+        click.echo(f"[retry] {exc}", err=True)
+        sys.exit(2)
+
+    click.echo(f"[retry] id={source_id} status → {new_status}  ({url})")
+
+
 # ---------------------------------------------------------------------------
 # compile
 # ---------------------------------------------------------------------------

src/second_brain/sources_service.py

@@ -275,14 +275,126 @@ def add_playlist(
     return result
 
 
+# ---------------------------------------------------------------------------
+# Edit + retry helpers (shared by web routes and CLI)
+# ---------------------------------------------------------------------------
+
+
+# Fields the edit-mode form is allowed to mutate. URL is intentionally
+# excluded — it's the UNIQUE dedupe key and editing it risks collisions
+# plus breaks the embeddings 4-tuple identity (source_id is stable but
+# semantic identity drifts).
+EDITABLE_METADATA_FIELDS = ("domain", "title", "focus")
+
+
+def update_source_metadata(
+    sess: Session,
+    *,
+    source_id: int,
+    domain: Optional[str] = None,
+    title: Optional[str] = None,
+    focus: Optional[str] = None,
+) -> Source:
+    """Update editable metadata on a source row.
+
+    Empty strings collapse to NULL for title/focus (matches `add_source`
+    semantics). Domain is required to stay in the configured set —
+    bumping the constraint is a separate decision.
+
+    Raises ValueError on validation failures and LookupError if the row
+    is missing. Caller owns the transaction boundary.
+    """
+    source = sess.query(Source).filter(Source.id == source_id).first()
+    if source is None:
+        raise LookupError(f"source id={source_id} not found")
+
+    if domain is not None:
+        if domain not in DOMAINS:
+            raise ValueError(
+                f"unknown domain {domain!r}; valid: {', '.join(DOMAINS)}"
+            )
+        source.domain = domain
+
+    if title is not None:
+        source.title = title.strip() or None
+
+    if focus is not None:
+        source.focus = focus.strip() or None
+
+    source.updated_at = utcnow()
+    sess.flush()
+    return source
+
+
+# Retry modes — keep the surface small. Anything else is a separate ask.
+RETRY_FULL = "full"
+RETRY_EXTRACT = "extract"
+RETRY_MODES = (RETRY_FULL, RETRY_EXTRACT)
+
+
+def reset_source_for_retry(
+    sess: Session,
+    *,
+    source_id: int,
+    mode: str = RETRY_FULL,
+) -> Source:
+    """Reset a source so the pipeline re-processes it.
+
+    Modes:
+      - "full": status → PENDING. Article pull or video download +
+        transcribe will happen again on the appropriate worker.
+      - "extract": status → TRANSCRIBED. Requires the row to already
+        carry a transcript (transcript_text). The dev scheduler will
+        re-run extraction without re-pulling the source. Cheap.
+
+    Always clears `claimed_by` / `claimed_at` / `error_message` so the
+    queue dance can pick it up cleanly and stale errors don't bleed
+    into the UI.
+
+    Raises ValueError on bad mode / missing transcript for extract mode,
+    and LookupError if the row is missing.
+    """
+    if mode not in RETRY_MODES:
+        raise ValueError(
+            f"unknown retry mode {mode!r}; valid: {', '.join(RETRY_MODES)}"
+        )
+
+    source = sess.query(Source).filter(Source.id == source_id).first()
+    if source is None:
+        raise LookupError(f"source id={source_id} not found")
+
+    if mode == RETRY_EXTRACT:
+        if not (source.transcript_text and source.transcript_text.strip()):
+            raise ValueError(
+                "extract-only retry requires an existing transcript; "
+                "use full retry instead"
+            )
+        source.status = SourceStatus.TRANSCRIBED
+    else:
+        source.status = SourceStatus.PENDING
+
+    source.claimed_by = None
+    source.claimed_at = None
+    source.error_message = None
+    source.updated_at = utcnow()
+    sess.flush()
+    return source
+
+
 __all__ = [
     "AddResult",
     "DEFAULT_PLAYLIST_MAX_ITEMS",
+    "EDITABLE_METADATA_FIELDS",
     "PlaylistAddResult",
+    "RETRY_EXTRACT",
+    "RETRY_FULL",
+    "RETRY_MODES",
     "add_playlist",
     "add_source",
     "expand_youtube_playlist",
     "is_article_url",
     "is_youtube_playlist_url",
+    "reset_source_for_retry",
+    "update_source_metadata",
     "validate_url",
 ]

src/second_brain/web/app.py

@@ -31,9 +31,14 @@ from second_brain.settings_store import (
 )
 from second_brain.sources_service import (
     DEFAULT_PLAYLIST_MAX_ITEMS,
+    RETRY_EXTRACT,
+    RETRY_FULL,
+    RETRY_MODES,
     add_playlist,
     add_source,
     is_youtube_playlist_url,
+    reset_source_for_retry,
+    update_source_metadata,
 )
 
 # ---------------------------------------------------------------------------
@@ -120,16 +125,33 @@ async def index(
     )
 
 
-@app.get("/sources/{source_id}", response_class=HTMLResponse)
+def _render_source_detail(
-async def source_detail(request: Request, source_id: int):
+    request: Request,
-    """Source detail page with extraction results and accept/reject actions."""
+    source_id: int,
+    *,
+    edit: bool = False,
+    flash: Optional[str] = None,
+    error: Optional[str] = None,
+    form_overrides: Optional[dict] = None,
+) -> HTMLResponse:
+    """Single render path for /sources/{id} — used by GET + every HTMX
+    mutation endpoint so each action gets a consistent re-render.
+
+    `form_overrides` lets a failed edit-save bounce show the user's
+    in-progress values instead of the row's stored values.
+    """
     db = get_database()
     with db.session() as sess:
         source = sess.query(Source).filter(Source.id == source_id).first()
         if not source:
             raise HTTPException(status_code=404, detail="Source not found")
         source_data = _source_to_dict(source)
-        extraction_data = _extraction_to_dict(source.extraction) if source.extraction else None
+        extraction_data = (
+            _extraction_to_dict(source.extraction) if source.extraction else None
+        )
+
+    if form_overrides:
+        source_data = {**source_data, **form_overrides}
 
     return templates.TemplateResponse(
         request,
@@ -137,10 +159,25 @@ async def source_detail(request: Request, source_id: int):
         {
             "source": source_data,
             "extraction": extraction_data,
+            "edit_mode": edit,
+            "flash": flash,
+            "error": error,
+            "domains": DOMAINS,
         },
     )
 
 
+@app.get("/sources/{source_id}", response_class=HTMLResponse)
+async def source_detail(request: Request, source_id: int, edit: bool = False):
+    """Source detail page with extraction results and accept/reject actions.
+
+    `?edit=1` opens the metadata editor inline. Editing exposes domain,
+    title, and focus — URL stays read-only since it's the UNIQUE dedupe
+    key for the queue and the embeddings identity tuple.
+    """
+    return _render_source_detail(request, source_id, edit=edit)
+
+
 _IN_FLIGHT_STATUSES = [
     SourceStatus.PENDING,
     SourceStatus.PULLED,
@@ -192,17 +229,11 @@ async def accept_source(request: Request, source_id: int):
         if not source:
             raise HTTPException(status_code=404, detail="Source not found")
         source.status = SourceStatus.ACCEPTED
-        source_data = _source_to_dict(source)
-        extraction_data = _extraction_to_dict(source.extraction) if source.extraction else None
 
-    return templates.TemplateResponse(
+    return _render_source_detail(
         request,
-        "source_detail.html",
+        source_id,
-        {
+        flash="Accepted — will be included in next wiki compile.",
-            "source": source_data,
-            "extraction": extraction_data,
-            "flash": "Accepted — will be included in next wiki compile.",
-        },
     )
 
 
@@ -215,19 +246,80 @@ async def reject_source(request: Request, source_id: int):
         if not source:
             raise HTTPException(status_code=404, detail="Source not found")
         source.status = SourceStatus.FAILED
-        source_data = _source_to_dict(source)
-        extraction_data = _extraction_to_dict(source.extraction) if source.extraction else None
 
-    return templates.TemplateResponse(
+    return _render_source_detail(request, source_id, flash="Rejected.")
+
+
+@app.post("/sources/{source_id}/edit", response_class=HTMLResponse)
+async def edit_source_metadata(
+    request: Request,
+    source_id: int,
+    domain: str = Form(...),
+    title: Optional[str] = Form(None),
+    focus: Optional[str] = Form(None),
+):
+    """HTMX edit-mode save. Updates domain/title/focus only — URL is
+    intentionally not editable (see service-layer comment)."""
+    db = get_database()
+    try:
+        with db.session() as sess:
+            update_source_metadata(
+                sess,
+                source_id=source_id,
+                domain=domain,
+                title=title,
+                focus=focus,
+            )
+    except LookupError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+    except ValueError as exc:
+        # Bounce back to edit mode with the user's in-progress values so
+        # they don't have to retype them.
+        return _render_source_detail(
             request,
-        "source_detail.html",
+            source_id,
-        {
+            edit=True,
-            "source": source_data,
+            error=str(exc),
-            "extraction": extraction_data,
+            form_overrides={
-            "flash": "Rejected.",
+                "domain": domain,
+                "title": title or "",
+                "focus": focus or "",
             },
         )
 
+    return _render_source_detail(request, source_id, flash="Saved.")
+
+
+@app.post("/sources/{source_id}/retry", response_class=HTMLResponse)
+async def retry_source(
+    request: Request,
+    source_id: int,
+    mode: str = Form(RETRY_FULL),
+):
+    """HTMX retry/re-run. `mode=full` → PENDING (re-pull + re-process).
+    `mode=extract` → TRANSCRIBED (re-extract only; requires an existing
+    transcript). Always clears the claim pair and error_message."""
+    if mode not in RETRY_MODES:
+        raise HTTPException(status_code=400, detail=f"unknown mode {mode!r}")
+
+    db = get_database()
+    try:
+        with db.session() as sess:
+            source = reset_source_for_retry(
+                sess, source_id=source_id, mode=mode
+            )
+            new_status = source.status.value
+    except LookupError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+    except ValueError as exc:
+        return _render_source_detail(request, source_id, error=str(exc))
+
+    if mode == RETRY_EXTRACT:
+        flash = f"Re-queued for extraction (status → {new_status})."
+    else:
+        flash = f"Re-queued from scratch (status → {new_status})."
+    return _render_source_detail(request, source_id, flash=flash)
+
 
 # ---------------------------------------------------------------------------
 # JSON API endpoints
@@ -286,6 +378,7 @@ def _source_to_dict(s: Source) -> dict:
         "focus": s.focus,
         "ingested_at": s.ingested_at.strftime("%Y-%m-%d %H:%M") if s.ingested_at else "",
         "has_extraction": s.extraction is not None,
+        "has_transcript": bool((s.transcript_text or "").strip()),
         "error_message": s.error_message,
     }
 

src/second_brain/web/templates/source_detail.html

@@ -11,9 +11,19 @@
         </svg>
         Back to sources
     </a>
-    <h2 class="text-2xl font-semibold text-gray-900">{{ source.title }}</h2>
+    <div class="flex items-start justify-between gap-4">
+        <div class="min-w-0">
+            <h2 class="text-2xl font-semibold text-gray-900 break-words">{{ source.title }}</h2>
             <a href="{{ source.url }}" target="_blank"
                class="text-sm text-indigo-500 hover:text-indigo-700 break-all">{{ source.url }}</a>
+        </div>
+        {% if not edit_mode %}
+        <a href="/sources/{{ source.id }}?edit=1"
+           class="shrink-0 px-3 py-1.5 text-sm border border-gray-300 text-gray-700 rounded hover:bg-gray-50 transition-colors">
+            Edit
+        </a>
+        {% endif %}
+    </div>
 </div>
 
 {% if flash %}
@@ -21,7 +31,54 @@
     {{ flash }}
 </div>
 {% endif %}
+{% if error %}
+<div class="mb-4 px-4 py-3 bg-red-50 border border-red-200 text-red-800 rounded text-sm">
+    {{ error }}
+</div>
+{% endif %}
 
+{% if edit_mode %}
+<!-- Edit mode: domain / title / focus. URL is intentionally read-only -->
+<form hx-post="/sources/{{ source.id }}/edit"
+      hx-target="body"
+      hx-swap="innerHTML"
+      class="mb-8 bg-white rounded-lg border border-gray-200 p-5 space-y-4">
+    <div>
+        <label class="block text-xs font-semibold text-gray-500 uppercase tracking-wide mb-1">URL <span class="font-normal normal-case text-gray-400">(read-only — dedupe key)</span></label>
+        <input type="text" value="{{ source.url }}" disabled
+               class="w-full px-3 py-2 border border-gray-200 bg-gray-50 text-gray-500 text-sm rounded">
+    </div>
+    <div>
+        <label for="edit-title" class="block text-xs font-semibold text-gray-500 uppercase tracking-wide mb-1">Title</label>
+        <input type="text" id="edit-title" name="title" value="{{ source.title or '' }}"
+               class="w-full px-3 py-2 border border-gray-300 text-sm rounded focus:outline-none focus:ring-2 focus:ring-indigo-300">
+    </div>
+    <div>
+        <label for="edit-domain" class="block text-xs font-semibold text-gray-500 uppercase tracking-wide mb-1">Domain</label>
+        <select id="edit-domain" name="domain"
+                class="w-full px-3 py-2 border border-gray-300 text-sm rounded focus:outline-none focus:ring-2 focus:ring-indigo-300">
+            {% for d in domains %}
+            <option value="{{ d }}" {% if d == source.domain %}selected{% endif %}>{{ d }}</option>
+            {% endfor %}
+        </select>
+    </div>
+    <div>
+        <label for="edit-focus" class="block text-xs font-semibold text-gray-500 uppercase tracking-wide mb-1">Focus</label>
+        <textarea id="edit-focus" name="focus" rows="3"
+                  class="w-full px-3 py-2 border border-gray-300 text-sm rounded focus:outline-none focus:ring-2 focus:ring-indigo-300">{{ source.focus or '' }}</textarea>
+    </div>
+    <div class="flex gap-2 pt-1">
+        <button type="submit"
+                class="px-4 py-2 bg-indigo-600 text-white text-sm font-semibold rounded hover:bg-indigo-700 transition-colors">
+            Save
+        </button>
+        <a href="/sources/{{ source.id }}"
+           class="px-4 py-2 border border-gray-300 text-gray-700 text-sm font-semibold rounded hover:bg-gray-50 transition-colors">
+            Cancel
+        </a>
+    </div>
+</form>
+{% else %}
 <!-- Meta row -->
 <div class="flex flex-wrap gap-2 mb-6">
     {% set status_colors = {
@@ -60,9 +117,9 @@
 </div>
 {% endif %}
 
-<!-- Accept / Reject actions (only when analyzed) -->
+<!-- Actions row: accept/reject (when analyzed) + retry (always) -->
-{% if source.status == 'analyzed' %}
+<div class="flex flex-wrap gap-3 mb-8">
-<div class="flex gap-3 mb-8">
+    {% if source.status == 'analyzed' %}
     <button hx-post="/sources/{{ source.id }}/accept"
             hx-target="body"
             hx-swap="innerHTML"
@@ -75,6 +132,31 @@
             class="px-5 py-2 bg-red-500 text-white text-sm font-semibold rounded hover:bg-red-600 transition-colors">
         Reject
     </button>
+    {% endif %}
+
+    <!-- Re-run: full reset → PENDING. Re-pulls and re-processes from scratch. -->
+    <button hx-post="/sources/{{ source.id }}/retry"
+            hx-vals='{"mode": "full"}'
+            hx-target="body"
+            hx-swap="innerHTML"
+            hx-confirm="Re-run this source from scratch? Status will reset to PENDING and the pipeline will re-pull{% if source.source_type == 'video' %} and re-transcribe (expensive){% endif %}."
+            class="px-5 py-2 bg-amber-500 text-white text-sm font-semibold rounded hover:bg-amber-600 transition-colors">
+        Re-run from scratch
+    </button>
+
+    {% if source.has_transcript %}
+    <!-- Light retry: skip the re-pull, just re-run LLM extraction. Works
+         for any source with stored body text (videos have transcripts,
+         articles have the trafilatura-extracted body). -->
+    <button hx-post="/sources/{{ source.id }}/retry"
+            hx-vals='{"mode": "extract"}'
+            hx-target="body"
+            hx-swap="innerHTML"
+            hx-confirm="Re-extract only — keep the existing transcript/body and re-run the LLM extraction?"
+            class="px-5 py-2 bg-amber-100 text-amber-800 text-sm font-semibold rounded hover:bg-amber-200 border border-amber-300 transition-colors">
+        Re-extract only
+    </button>
+    {% endif %}
 </div>
 {% endif %}
 

tests/test_source_edit_retry.py

@@ -0,0 +1,258 @@
+"""Tests for the source edit-metadata + retry-reset service helpers.
+
+Live-DB pattern matches `tests/test_claim.py` / `tests/test_playlist.py`:
+both groups auto-skip when no petalbrain connection is configured. The
+service layer is where edit/retry logic lives (the web routes + CLI are
+thin wrappers around it), so this is where the meaningful coverage is.
+"""
+
+from __future__ import annotations
+
+import os
+import uuid
+
+import psycopg
+import pytest
+
+
+def _db_reachable() -> bool:
+    url = os.environ.get("SECOND_BRAIN_DATABASE_URL") or os.environ.get(
+        "HERBYLAB_DATABASE_URL"
+    )
+    if not url:
+        return False
+    raw = url.replace("postgresql+psycopg://", "postgresql://", 1)
+    try:
+        with psycopg.connect(raw, connect_timeout=2):
+            return True
+    except Exception:
+        return False
+
+
+pytestmark = pytest.mark.skipif(
+    not _db_reachable(),
+    reason="needs SECOND_BRAIN_DATABASE_URL pointed at a real petalbrain",
+)
+
+
+def _seed_source(db, **overrides):
+    """Insert a Source row and return (id, url). Caller cleans up by id."""
+    from second_brain.models import Source, SourceStatus, SourceType, utcnow
+
+    tag = uuid.uuid4().hex[:8]
+    defaults = dict(
+        url=f"https://example.test/edit-retry/{tag}",
+        title=f"seed-{tag}",
+        domain="development",
+        source_type=SourceType.ARTICLE,
+        status=SourceStatus.PENDING,
+        ingested_at=utcnow(),
+    )
+    defaults.update(overrides)
+    with db.session() as sess:
+        src = Source(**defaults)
+        sess.add(src)
+        sess.flush()
+        return src.id, src.url
+
+
+def _cleanup(db, source_id):
+    from second_brain.models import Source
+
+    with db.session() as sess:
+        sess.query(Source).filter(Source.id == source_id).delete(
+            synchronize_session=False
+        )
+
+
+# ---------------------------------------------------------------------------
+# update_source_metadata
+# ---------------------------------------------------------------------------
+
+
+def test_update_metadata_writes_domain_title_focus():
+    from second_brain.database import Database, reset_database_singleton
+    from second_brain.models import Source
+    from second_brain.sources_service import update_source_metadata
+
+    reset_database_singleton()
+    db = Database()
+    sid, _ = _seed_source(db)
+    try:
+        with db.session() as sess:
+            update_source_metadata(
+                sess,
+                source_id=sid,
+                domain="homelab",
+                title="new title",
+                focus="new focus directive",
+            )
+        with db.session() as sess:
+            row = sess.query(Source).filter(Source.id == sid).first()
+            assert row.domain == "homelab"
+            assert row.title == "new title"
+            assert row.focus == "new focus directive"
+            assert row.updated_at is not None
+    finally:
+        _cleanup(db, sid)
+        reset_database_singleton()
+
+
+def test_update_metadata_blank_strings_become_null():
+    from second_brain.database import Database, reset_database_singleton
+    from second_brain.models import Source
+    from second_brain.sources_service import update_source_metadata
+
+    reset_database_singleton()
+    db = Database()
+    sid, _ = _seed_source(db)
+    try:
+        with db.session() as sess:
+            update_source_metadata(
+                sess, source_id=sid, domain="development", title="   ", focus=""
+            )
+        with db.session() as sess:
+            row = sess.query(Source).filter(Source.id == sid).first()
+            assert row.title is None
+            assert row.focus is None
+    finally:
+        _cleanup(db, sid)
+        reset_database_singleton()
+
+
+def test_update_metadata_rejects_unknown_domain():
+    from second_brain.database import Database, reset_database_singleton
+    from second_brain.sources_service import update_source_metadata
+
+    reset_database_singleton()
+    db = Database()
+    sid, _ = _seed_source(db)
+    try:
+        with db.session() as sess:
+            with pytest.raises(ValueError, match="unknown domain"):
+                update_source_metadata(sess, source_id=sid, domain="not-a-domain")
+    finally:
+        _cleanup(db, sid)
+        reset_database_singleton()
+
+
+def test_update_metadata_missing_source_raises_lookup():
+    from second_brain.database import Database, reset_database_singleton
+    from second_brain.sources_service import update_source_metadata
+
+    reset_database_singleton()
+    db = Database()
+    try:
+        with db.session() as sess:
+            with pytest.raises(LookupError):
+                update_source_metadata(
+                    sess, source_id=-99999, domain="development"
+                )
+    finally:
+        reset_database_singleton()
+
+
+# ---------------------------------------------------------------------------
+# reset_source_for_retry
+# ---------------------------------------------------------------------------
+
+
+def test_retry_full_resets_to_pending_and_clears_claim():
+    from second_brain.database import Database, reset_database_singleton
+    from second_brain.models import Source, SourceStatus, utcnow
+    from second_brain.sources_service import reset_source_for_retry
+
+    reset_database_singleton()
+    db = Database()
+    sid, _ = _seed_source(
+        db,
+        status=SourceStatus.FAILED,
+        error_message="boom",
+        claimed_by="worker-x",
+        claimed_at=utcnow(),
+    )
+    try:
+        with db.session() as sess:
+            reset_source_for_retry(sess, source_id=sid, mode="full")
+        with db.session() as sess:
+            row = sess.query(Source).filter(Source.id == sid).first()
+            assert row.status == SourceStatus.PENDING
+            assert row.claimed_by is None
+            assert row.claimed_at is None
+            assert row.error_message is None
+    finally:
+        _cleanup(db, sid)
+        reset_database_singleton()
+
+
+def test_retry_extract_sets_transcribed_when_transcript_present():
+    from second_brain.database import Database, reset_database_singleton
+    from second_brain.models import Source, SourceStatus
+    from second_brain.sources_service import reset_source_for_retry
+
+    reset_database_singleton()
+    db = Database()
+    sid, _ = _seed_source(
+        db,
+        status=SourceStatus.ANALYZED,
+        transcript_text="word " * 50,
+        error_message="prior failure",
+    )
+    try:
+        with db.session() as sess:
+            reset_source_for_retry(sess, source_id=sid, mode="extract")
+        with db.session() as sess:
+            row = sess.query(Source).filter(Source.id == sid).first()
+            assert row.status == SourceStatus.TRANSCRIBED
+            assert row.error_message is None
+            assert row.transcript_text  # transcript preserved
+    finally:
+        _cleanup(db, sid)
+        reset_database_singleton()
+
+
+def test_retry_extract_without_transcript_raises():
+    from second_brain.database import Database, reset_database_singleton
+    from second_brain.models import SourceStatus
+    from second_brain.sources_service import reset_source_for_retry
+
+    reset_database_singleton()
+    db = Database()
+    sid, _ = _seed_source(db, status=SourceStatus.PENDING, transcript_text=None)
+    try:
+        with db.session() as sess:
+            with pytest.raises(ValueError, match="requires an existing transcript"):
+                reset_source_for_retry(sess, source_id=sid, mode="extract")
+    finally:
+        _cleanup(db, sid)
+        reset_database_singleton()
+
+
+def test_retry_unknown_mode_raises():
+    from second_brain.database import Database, reset_database_singleton
+    from second_brain.sources_service import reset_source_for_retry
+
+    reset_database_singleton()
+    db = Database()
+    sid, _ = _seed_source(db)
+    try:
+        with db.session() as sess:
+            with pytest.raises(ValueError, match="unknown retry mode"):
+                reset_source_for_retry(sess, source_id=sid, mode="bogus")
+    finally:
+        _cleanup(db, sid)
+        reset_database_singleton()
+
+
+def test_retry_missing_source_raises_lookup():
+    from second_brain.database import Database, reset_database_singleton
+    from second_brain.sources_service import reset_source_for_retry
+
+    reset_database_singleton()
+    db = Database()
+    try:
+        with db.session() as sess:
+            with pytest.raises(LookupError):
+                reset_source_for_retry(sess, source_id=-99999, mode="full")
+    finally:
+        reset_database_singleton()