scheduler: honor pipeline_settings (extraction_enabled, window, max_items)

The dev-side scheduler now snapshots the singleton pipeline_settings row
at the top of run() and applies three DB-driven gates:

- extraction_enabled = false → skip the entire run with a single log line.
  Lets Travis pause extraction from the dashboard without touching the
  config file or restarting anything.
- extraction_active_hours_start/_end → fast-fail if outside the window
  AND (when set) override the static settings.toml [scheduler].window_*
  bounds so the inner loop also respects the dashboard's choice. Either
  side being NULL means "no constraint on that side" — matches the form's
  "leave blank = always active" semantics.
- extraction_max_items_per_run → hard cap on processed items per
  invocation. 0/null means unlimited (existing behavior).

Snapshot semantics are deliberate: a mid-run toggle doesn't half-apply,
same way max_calls_per_hour is tracked locally. Workers re-read on the
next invocation.

alembic/versions/7b3e8a5c1f29_v2_pipeline_settings.py

@@ -0,0 +1,70 @@
+"""v2 second_brain: pipeline_settings table
+
+Revision ID: 7b3e8a5c1f29
+Revises: 4a1e2f6c9d10
+Create Date: 2026-05-25 00:00:00.000000
+
+Adds a single-row `pipeline_settings` table that the web dashboard edits
+and the workers (current dev-side scheduler + future tower-side transcribe
+worker) read at the start of each run. The transcription_* fields persist
+now but are only consumed once the transcribe worker exists — the
+extraction_* fields are wired into the existing scheduler in this commit.
+
+Single-row enforcement: PK is fixed at `id=1` with a CHECK constraint, so
+INSERT-as-upsert-by-PK keeps the table free of stale rows.
+
+Schema/permission notes mirror the v1 migration: lovebug lacks CREATE on
+the petalbrain database, so env.py has already bootstrapped the schema —
+this migration just SETs search_path and emits DDL inside it.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Sequence
+
+from alembic import op
+
+revision: str = "7b3e8a5c1f29"
+down_revision: str | Sequence[str] | None = "4a1e2f6c9d10"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    op.execute("SET search_path TO second_brain")
+
+    op.execute(
+        """
+        CREATE TABLE pipeline_settings (
+            id                                    INTEGER PRIMARY KEY DEFAULT 1,
+            transcription_enabled                 BOOLEAN NOT NULL DEFAULT TRUE,
+            transcription_active_hours_start      TIME,
+            transcription_active_hours_end        TIME,
+            transcription_max_concurrent_gpu_jobs INTEGER NOT NULL DEFAULT 1,
+            transcription_max_video_length_seconds INTEGER,
+            transcription_max_items_per_run       INTEGER NOT NULL DEFAULT 10,
+            extraction_enabled                    BOOLEAN NOT NULL DEFAULT TRUE,
+            extraction_active_hours_start         TIME,
+            extraction_active_hours_end           TIME,
+            extraction_max_items_per_run          INTEGER NOT NULL DEFAULT 20,
+            updated_at                            TIMESTAMP NOT NULL
+                                                  DEFAULT (now() AT TIME ZONE 'UTC'),
+            CONSTRAINT pipeline_settings_singleton CHECK (id = 1)
+        )
+        """
+    )
+
+    # Seed the singleton row with the table's column defaults. Idempotent
+    # via ON CONFLICT so re-running this migration on a partly-applied DB
+    # (or a manual cherry-pick) is safe.
+    op.execute(
+        """
+        INSERT INTO pipeline_settings (id) VALUES (1)
+        ON CONFLICT (id) DO NOTHING
+        """
+    )
+
+
+def downgrade() -> None:
+    op.execute("SET search_path TO second_brain")
+    op.execute("DROP TABLE IF EXISTS pipeline_settings")

pyproject.toml

@@ -15,6 +15,7 @@ dependencies = [
     "psycopg-pool>=3.2",
     "pydantic>=2.0.0",
     "python-dotenv>=1.0.0",
+    "python-multipart>=0.0.20",
     "sqlalchemy>=2.0.0",
     "tomli>=2.0.0",
     "trafilatura>=1.9.0",

src/second_brain/models.py

@@ -14,11 +14,12 @@ Tables:
 from __future__ import annotations
 
 import enum
-from datetime import datetime, timezone
+from datetime import datetime, time, timezone
 from typing import Optional
 
 from sqlalchemy import (
     JSON,
+    Boolean,
     DateTime,
     Enum,
     ForeignKey,
@@ -26,6 +27,7 @@ from sqlalchemy import (
     MetaData,
     String,
     Text,
+    Time,
 )
 from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column, relationship
 
@@ -193,6 +195,64 @@ class WikiPage(Base):
         return f"WikiPage(id={self.id}, vault_path={self.vault_path!r})"
 
 
+class PipelineSettings(Base):
+    """Single-row config the web dashboard edits and workers read.
+
+    The transcription_* fields persist now and will be honored by the
+    tower-side transcribe worker once it exists; the extraction_* fields
+    are already wired into the dev-side scheduler. The row is pinned to
+    `id=1` by a DB-level CHECK so upserts-by-PK keep the table singleton.
+    """
+
+    __tablename__ = "pipeline_settings"
+
+    id: Mapped[int] = mapped_column(Integer, primary_key=True, default=1)
+
+    # Transcription (consumed by the tower-side worker — not yet built).
+    transcription_enabled: Mapped[bool] = mapped_column(
+        Boolean, nullable=False, default=True
+    )
+    transcription_active_hours_start: Mapped[Optional[time]] = mapped_column(
+        Time, nullable=True
+    )
+    transcription_active_hours_end: Mapped[Optional[time]] = mapped_column(
+        Time, nullable=True
+    )
+    transcription_max_concurrent_gpu_jobs: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=1
+    )
+    transcription_max_video_length_seconds: Mapped[Optional[int]] = mapped_column(
+        Integer, nullable=True
+    )
+    transcription_max_items_per_run: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=10
+    )
+
+    # Extraction (consumed by the dev-side scheduler today).
+    extraction_enabled: Mapped[bool] = mapped_column(
+        Boolean, nullable=False, default=True
+    )
+    extraction_active_hours_start: Mapped[Optional[time]] = mapped_column(
+        Time, nullable=True
+    )
+    extraction_active_hours_end: Mapped[Optional[time]] = mapped_column(
+        Time, nullable=True
+    )
+    extraction_max_items_per_run: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=20
+    )
+
+    updated_at: Mapped[datetime] = mapped_column(
+        DateTime, default=utcnow, onupdate=utcnow
+    )
+
+    def __repr__(self) -> str:
+        return (
+            f"PipelineSettings(transcription_enabled={self.transcription_enabled}, "
+            f"extraction_enabled={self.extraction_enabled})"
+        )
+
+
 __all__ = [
     "Base",
     "SCHEMA",
@@ -200,6 +260,7 @@ __all__ = [
     "SourceStatus",
     "SourceType",
     "Extraction",
+    "PipelineSettings",
     "WikiPage",
     "utcnow",
 ]

src/second_brain/scheduler/runner.py

@@ -25,6 +25,7 @@ from datetime import datetime, time as dtime
 from second_brain.config import Config
 from second_brain.database import get_database
 from second_brain.models import Source, SourceStatus, utcnow
+from second_brain.settings_store import get_settings, in_active_window
 
 
 class Scheduler:
@@ -51,6 +52,38 @@ class Scheduler:
         from second_brain.models import Extraction
 
         db = get_database()
+
+        # Pull the DB-side runtime knobs once at the top of the run. The
+        # dashboard edits these; settings.toml is the static fallback. The
+        # values are snapshotted for the duration of this run so a mid-run
+        # toggle doesn't half-apply (consistent with the way max_calls is
+        # tracked locally).
+        with db.session() as sess:
+            settings = get_settings(sess)
+            extraction_enabled = settings.extraction_enabled
+            db_window = (
+                settings.extraction_active_hours_start,
+                settings.extraction_active_hours_end,
+            )
+            max_items = int(settings.extraction_max_items_per_run or 0)
+
+        if not extraction_enabled:
+            print("[Scheduler] extraction_enabled=false in pipeline_settings. Skipping run.")
+            return
+
+        # DB window (if set) overrides the static settings.toml window. If
+        # only one side is set, treat the other as unbounded (no constraint).
+        if db_window[0] is not None or db_window[1] is not None:
+            self.window_start = db_window[0] or dtime(0, 0)
+            self.window_end = db_window[1] or dtime(23, 59)
+
+        if not in_active_window(datetime.now().time(), db_window[0], db_window[1]):
+            print(
+                f"[Scheduler] outside extraction active window "
+                f"{_fmt_opt(db_window[0])}–{_fmt_opt(db_window[1])}. Skipping run."
+            )
+            return
+
         assembler = ContextAssembler(self.config)
         ex_cfg = self.config.extractor
         engine = ExtractionEngine(
@@ -74,10 +107,14 @@ class Scheduler:
         print(
             f"[Scheduler] backend={self.backend} window "
             f"{_fmt(self.window_start)}–{_fmt(self.window_end)} cap {cap_desc} "
-            f"gap {self.min_gap_seconds}s"
+            f"gap {self.min_gap_seconds}s max_items={max_items or '∞'}"
         )
 
         while self._in_window():
+            # DB-side hard cap on items per run (0 = unlimited).
+            if max_items and processed >= max_items:
+                print(f"[Scheduler] reached extraction_max_items_per_run={max_items}. Done.")
+                break
             # Reset hourly buckets
             elapsed = time.time() - hour_start
             if elapsed >= 3600:
@@ -191,4 +228,8 @@ def _fmt(t: dtime) -> str:
     return t.strftime("%H:%M")
 
 
+def _fmt_opt(t: dtime | None) -> str:
+    return t.strftime("%H:%M") if t is not None else "—"
+
+
 __all__ = ["Scheduler"]

src/second_brain/settings_store.py

@@ -0,0 +1,121 @@
+"""Helpers for the singleton `pipeline_settings` row.
+
+The web dashboard edits this row; workers read it at the start of each
+run to decide whether to do anything and how much. DB values override
+the static defaults in `settings.toml`.
+
+All functions take a SQLAlchemy `Session` so the caller owns the
+transaction boundary — matches the rest of the codebase, which keeps
+session lifecycle inside `with db.session()` blocks.
+"""
+
+from __future__ import annotations
+
+from datetime import time
+from typing import Any
+
+from sqlalchemy.orm import Session
+
+from second_brain.models import PipelineSettings, utcnow
+
+
+# Field names allowed in `update_settings`. Anything else is rejected so a
+# malicious form post can't toggle id/updated_at/etc.
+_EDITABLE_FIELDS: tuple[str, ...] = (
+    "transcription_enabled",
+    "transcription_active_hours_start",
+    "transcription_active_hours_end",
+    "transcription_max_concurrent_gpu_jobs",
+    "transcription_max_video_length_seconds",
+    "transcription_max_items_per_run",
+    "extraction_enabled",
+    "extraction_active_hours_start",
+    "extraction_active_hours_end",
+    "extraction_max_items_per_run",
+)
+
+
+def get_settings(sess: Session) -> PipelineSettings:
+    """Return the singleton settings row, creating it on first call.
+
+    The v2 migration seeds the row with all DB-side defaults, so this
+    "create on miss" path only kicks in when somebody bootstrapped the
+    schema without applying the migration (e.g. an unconfigured test
+    using `Base.metadata.create_all`).
+    """
+    row = sess.get(PipelineSettings, 1)
+    if row is None:
+        row = PipelineSettings(id=1)
+        sess.add(row)
+        sess.flush()
+    return row
+
+
+def update_settings(sess: Session, **fields: Any) -> PipelineSettings:
+    """Apply a partial update to the singleton row.
+
+    Unknown keys raise `KeyError`. Empty-string values for nullable fields
+    are normalised to None so the HTML form's blank inputs (active hours,
+    video-length cap) round-trip as NULL rather than as the strings "".
+    """
+    for k in fields:
+        if k not in _EDITABLE_FIELDS:
+            raise KeyError(f"Unknown pipeline_settings field: {k!r}")
+
+    row = get_settings(sess)
+    for k, v in fields.items():
+        if v == "":
+            v = None
+        setattr(row, k, v)
+    row.updated_at = utcnow()
+    return row
+
+
+def parse_time_or_none(raw: str | None) -> time | None:
+    """Parse an HTML <input type=time> value (HH:MM) into a `time`.
+
+    Empty / missing values map to None — `update_settings` will store
+    NULL, which workers interpret as "no window, always active".
+    """
+    if raw is None or raw == "":
+        return None
+    parts = raw.split(":")
+    if len(parts) < 2:
+        raise ValueError(f"Could not parse time: {raw!r}")
+    h, m = int(parts[0]), int(parts[1])
+    return time(h, m)
+
+
+def parse_int_or_none(raw: str | None) -> int | None:
+    if raw is None or raw == "":
+        return None
+    return int(raw)
+
+
+def in_active_window(now_t: time, start: time | None, end: time | None) -> bool:
+    """Return True if `now_t` lies in the [start, end] window.
+
+    Either bound being None means "no constraint on that side", which
+    matches the dashboard's "leave blank = always active" semantics.
+    Handles overnight windows (start > end) by treating them as the
+    complement that crosses midnight.
+    """
+    if start is None and end is None:
+        return True
+    if start is None:
+        return now_t <= end  # type: ignore[operator]
+    if end is None:
+        return now_t >= start
+    if start <= end:
+        return start <= now_t <= end
+    # crosses midnight
+    return now_t >= start or now_t <= end
+
+
+__all__ = [
+    "get_settings",
+    "update_settings",
+    "parse_time_or_none",
+    "parse_int_or_none",
+    "in_active_window",
+]

src/second_brain/web/app.py

@@ -14,14 +14,21 @@ from __future__ import annotations
 from pathlib import Path
 from typing import List, Optional
 
-from fastapi import FastAPI, HTTPException, Request
+from fastapi import FastAPI, Form, HTTPException, Request
 from fastapi.responses import HTMLResponse
 from fastapi.templating import Jinja2Templates
 from pydantic import BaseModel
+from sqlalchemy import func
 
 from second_brain.config import DOMAINS
 from second_brain.database import get_database
 from second_brain.models import Extraction, Source, SourceStatus
+from second_brain.settings_store import (
+    get_settings,
+    parse_int_or_none,
+    parse_time_or_none,
+    update_settings,
+)
 
 # ---------------------------------------------------------------------------
 # App setup
@@ -295,3 +302,176 @@ def _source_to_response(s: Source) -> SourceResponse:
         ingested_at=s.ingested_at.isoformat() if s.ingested_at else "",
         has_extraction=s.extraction is not None,
     )
+
+
+# ---------------------------------------------------------------------------
+# Dashboard — pipeline observability
+# ---------------------------------------------------------------------------
+
+
+@app.get("/dashboard", response_class=HTMLResponse)
+async def dashboard(request: Request):
+    """Overview: status counts, recent activity, and a settings snapshot."""
+    db = get_database()
+    with db.session() as sess:
+        # Counts by status. Materialise inside the session so the keys stay
+        # plain str → int and templates don't try to touch a closed session.
+        rows = (
+            sess.query(Source.status, func.count(Source.id))
+            .group_by(Source.status)
+            .all()
+        )
+        counts = {s.value: 0 for s in SourceStatus}
+        for status, n in rows:
+            counts[status.value] = int(n)
+        total = sum(counts.values())
+
+        recent_rows = (
+            sess.query(Source)
+            .order_by(Source.ingested_at.desc())
+            .limit(10)
+            .all()
+        )
+        recent = [_source_to_dict(s) for s in recent_rows]
+
+        settings_row = get_settings(sess)
+        settings_summary = _settings_to_dict(settings_row)
+
+    return templates.TemplateResponse(
+        request,
+        "dashboard.html",
+        {
+            "counts": counts,
+            "total": total,
+            "recent": recent,
+            "statuses_in_order": [s.value for s in SourceStatus],
+            "settings": settings_summary,
+        },
+    )
+
+
+# ---------------------------------------------------------------------------
+# Settings — view + HTMX save
+# ---------------------------------------------------------------------------
+
+
+@app.get("/settings", response_class=HTMLResponse)
+async def settings_view(request: Request):
+    db = get_database()
+    with db.session() as sess:
+        row = get_settings(sess)
+        ctx = _settings_to_dict(row)
+
+    return templates.TemplateResponse(
+        request,
+        "settings.html",
+        {"settings": ctx, "flash": None, "error": None},
+    )
+
+
+@app.post("/settings/save", response_class=HTMLResponse)
+async def settings_save(
+    request: Request,
+    transcription_enabled: Optional[str] = Form(None),
+    transcription_active_hours_start: Optional[str] = Form(None),
+    transcription_active_hours_end: Optional[str] = Form(None),
+    transcription_max_concurrent_gpu_jobs: Optional[str] = Form(None),
+    transcription_max_video_length_seconds: Optional[str] = Form(None),
+    transcription_max_items_per_run: Optional[str] = Form(None),
+    extraction_enabled: Optional[str] = Form(None),
+    extraction_active_hours_start: Optional[str] = Form(None),
+    extraction_active_hours_end: Optional[str] = Form(None),
+    extraction_max_items_per_run: Optional[str] = Form(None),
+):
+    """HTMX save endpoint — returns the rendered settings card with a flash."""
+    db = get_database()
+    error: Optional[str] = None
+    flash: Optional[str] = None
+
+    try:
+        fields = {
+            # Checkboxes only show up in the form payload when checked. The
+            # template emits a hidden "_present" companion so we can tell
+            # "unchecked" apart from "field missing because of a partial post".
+            "transcription_enabled": transcription_enabled == "on",
+            "transcription_active_hours_start": parse_time_or_none(
+                transcription_active_hours_start
+            ),
+            "transcription_active_hours_end": parse_time_or_none(
+                transcription_active_hours_end
+            ),
+            "transcription_max_concurrent_gpu_jobs": int(
+                transcription_max_concurrent_gpu_jobs or "1"
+            ),
+            "transcription_max_video_length_seconds": parse_int_or_none(
+                transcription_max_video_length_seconds
+            ),
+            "transcription_max_items_per_run": int(
+                transcription_max_items_per_run or "10"
+            ),
+            "extraction_enabled": extraction_enabled == "on",
+            "extraction_active_hours_start": parse_time_or_none(
+                extraction_active_hours_start
+            ),
+            "extraction_active_hours_end": parse_time_or_none(
+                extraction_active_hours_end
+            ),
+            "extraction_max_items_per_run": int(extraction_max_items_per_run or "20"),
+        }
+        # Cheap inline validation — keep counts non-negative and gpu jobs >= 1.
+        if fields["transcription_max_concurrent_gpu_jobs"] < 1:
+            raise ValueError("transcription_max_concurrent_gpu_jobs must be ≥ 1")
+        if fields["transcription_max_items_per_run"] < 0:
+            raise ValueError("transcription_max_items_per_run must be ≥ 0")
+        if fields["extraction_max_items_per_run"] < 0:
+            raise ValueError("extraction_max_items_per_run must be ≥ 0")
+        if (
+            fields["transcription_max_video_length_seconds"] is not None
+            and fields["transcription_max_video_length_seconds"] < 0
+        ):
+            raise ValueError("transcription_max_video_length_seconds must be ≥ 0")
+
+        with db.session() as sess:
+            row = update_settings(sess, **fields)
+            ctx = _settings_to_dict(row)
+        flash = "Saved."
+    except (ValueError, KeyError) as exc:
+        error = str(exc)
+        # Re-render the form using whatever the user submitted so they don't
+        # lose in-progress edits on a validation bounce.
+        with db.session() as sess:
+            ctx = _settings_to_dict(get_settings(sess))
+
+    return templates.TemplateResponse(
+        request,
+        "_settings_card.html",
+        {"settings": ctx, "flash": flash, "error": error},
+    )
+
+
+# ---------------------------------------------------------------------------
+# Settings serialiser
+# ---------------------------------------------------------------------------
+
+
+def _settings_to_dict(row) -> dict:
+    """Render the settings row as a template-friendly dict (no ORM bleed)."""
+
+    def t(v):
+        return v.strftime("%H:%M") if v is not None else ""
+
+    return {
+        "transcription_enabled": row.transcription_enabled,
+        "transcription_active_hours_start": t(row.transcription_active_hours_start),
+        "transcription_active_hours_end": t(row.transcription_active_hours_end),
+        "transcription_max_concurrent_gpu_jobs": row.transcription_max_concurrent_gpu_jobs,
+        "transcription_max_video_length_seconds": row.transcription_max_video_length_seconds,
+        "transcription_max_items_per_run": row.transcription_max_items_per_run,
+        "extraction_enabled": row.extraction_enabled,
+        "extraction_active_hours_start": t(row.extraction_active_hours_start),
+        "extraction_active_hours_end": t(row.extraction_active_hours_end),
+        "extraction_max_items_per_run": row.extraction_max_items_per_run,
+        "updated_at": row.updated_at.strftime("%Y-%m-%d %H:%M:%S")
+        if row.updated_at
+        else "",
+    }

src/second_brain/web/templates/_settings_card.html

@@ -0,0 +1,130 @@
+{# HTMX-replaceable inner card. Posted to /settings/save; swaps itself in place. #}
+<div id="settings-card" class="bg-white rounded-lg shadow-sm p-6">
+    {% if flash %}
+    <div class="mb-4 px-3 py-2 rounded bg-green-50 border border-green-200 text-green-700 text-sm">
+        ✓ {{ flash }}
+    </div>
+    {% endif %}
+    {% if error %}
+    <div class="mb-4 px-3 py-2 rounded bg-red-50 border border-red-200 text-red-700 text-sm">
+        ✗ {{ error }}
+    </div>
+    {% endif %}
+
+    <form hx-post="/settings/save"
+          hx-target="#settings-card"
+          hx-swap="outerHTML"
+          class="space-y-8">
+
+        <!-- Transcription -->
+        <section>
+            <div class="flex items-center justify-between mb-4">
+                <h3 class="text-base font-semibold text-gray-800">Transcription</h3>
+                <p class="text-xs text-gray-400">consumed by tower-side worker (not yet built)</p>
+            </div>
+
+            <div class="grid md:grid-cols-2 gap-x-6 gap-y-4">
+                <!-- enabled -->
+                <label class="flex items-center gap-3 cursor-pointer select-none">
+                    <span class="relative inline-flex items-center">
+                        <input type="checkbox" name="transcription_enabled"
+                               {% if settings.transcription_enabled %}checked{% endif %}
+                               class="peer sr-only">
+                        <span class="w-10 h-5 bg-gray-300 rounded-full peer-checked:bg-indigo-600 transition-colors"></span>
+                        <span class="absolute left-0.5 top-0.5 w-4 h-4 bg-white rounded-full transition-transform peer-checked:translate-x-5"></span>
+                    </span>
+                    <span class="text-sm font-medium text-gray-700">Enabled</span>
+                </label>
+
+                <div class="md:col-span-1"></div>
+
+                <div>
+                    <label class="block text-xs font-medium text-gray-600 mb-1">Active hours — start</label>
+                    <input type="time" name="transcription_active_hours_start"
+                           value="{{ settings.transcription_active_hours_start }}"
+                           class="text-sm border border-gray-300 rounded px-3 py-1.5 focus:outline-none focus:ring-2 focus:ring-indigo-400 w-full">
+                    <p class="text-xs text-gray-400 mt-1">blank = always active</p>
+                </div>
+                <div>
+                    <label class="block text-xs font-medium text-gray-600 mb-1">Active hours — end</label>
+                    <input type="time" name="transcription_active_hours_end"
+                           value="{{ settings.transcription_active_hours_end }}"
+                           class="text-sm border border-gray-300 rounded px-3 py-1.5 focus:outline-none focus:ring-2 focus:ring-indigo-400 w-full">
+                </div>
+
+                <div>
+                    <label class="block text-xs font-medium text-gray-600 mb-1">Max concurrent GPU jobs</label>
+                    <input type="number" min="1" name="transcription_max_concurrent_gpu_jobs"
+                           value="{{ settings.transcription_max_concurrent_gpu_jobs }}"
+                           class="text-sm border border-gray-300 rounded px-3 py-1.5 focus:outline-none focus:ring-2 focus:ring-indigo-400 w-full">
+                </div>
+                <div>
+                    <label class="block text-xs font-medium text-gray-600 mb-1">Max items per run</label>
+                    <input type="number" min="0" name="transcription_max_items_per_run"
+                           value="{{ settings.transcription_max_items_per_run }}"
+                           class="text-sm border border-gray-300 rounded px-3 py-1.5 focus:outline-none focus:ring-2 focus:ring-indigo-400 w-full">
+                </div>
+
+                <div class="md:col-span-2">
+                    <label class="block text-xs font-medium text-gray-600 mb-1">Max video length (seconds)</label>
+                    <input type="number" min="0" name="transcription_max_video_length_seconds"
+                           value="{{ settings.transcription_max_video_length_seconds if settings.transcription_max_video_length_seconds is not none else '' }}"
+                           placeholder="blank = no cap"
+                           class="text-sm border border-gray-300 rounded px-3 py-1.5 focus:outline-none focus:ring-2 focus:ring-indigo-400 w-full max-w-xs">
+                </div>
+            </div>
+        </section>
+
+        <!-- Extraction -->
+        <section>
+            <div class="flex items-center justify-between mb-4">
+                <h3 class="text-base font-semibold text-gray-800">Extraction</h3>
+                <p class="text-xs text-gray-400">consumed by the dev-side scheduler</p>
+            </div>
+
+            <div class="grid md:grid-cols-2 gap-x-6 gap-y-4">
+                <label class="flex items-center gap-3 cursor-pointer select-none">
+                    <span class="relative inline-flex items-center">
+                        <input type="checkbox" name="extraction_enabled"
+                               {% if settings.extraction_enabled %}checked{% endif %}
+                               class="peer sr-only">
+                        <span class="w-10 h-5 bg-gray-300 rounded-full peer-checked:bg-indigo-600 transition-colors"></span>
+                        <span class="absolute left-0.5 top-0.5 w-4 h-4 bg-white rounded-full transition-transform peer-checked:translate-x-5"></span>
+                    </span>
+                    <span class="text-sm font-medium text-gray-700">Enabled</span>
+                </label>
+
+                <div class="md:col-span-1"></div>
+
+                <div>
+                    <label class="block text-xs font-medium text-gray-600 mb-1">Active hours — start</label>
+                    <input type="time" name="extraction_active_hours_start"
+                           value="{{ settings.extraction_active_hours_start }}"
+                           class="text-sm border border-gray-300 rounded px-3 py-1.5 focus:outline-none focus:ring-2 focus:ring-indigo-400 w-full">
+                    <p class="text-xs text-gray-400 mt-1">blank = always active</p>
+                </div>
+                <div>
+                    <label class="block text-xs font-medium text-gray-600 mb-1">Active hours — end</label>
+                    <input type="time" name="extraction_active_hours_end"
+                           value="{{ settings.extraction_active_hours_end }}"
+                           class="text-sm border border-gray-300 rounded px-3 py-1.5 focus:outline-none focus:ring-2 focus:ring-indigo-400 w-full">
+                </div>
+
+                <div>
+                    <label class="block text-xs font-medium text-gray-600 mb-1">Max items per run</label>
+                    <input type="number" min="0" name="extraction_max_items_per_run"
+                           value="{{ settings.extraction_max_items_per_run }}"
+                           class="text-sm border border-gray-300 rounded px-3 py-1.5 focus:outline-none focus:ring-2 focus:ring-indigo-400 w-full">
+                </div>
+            </div>
+        </section>
+
+        <div class="flex items-center justify-between pt-2 border-t border-gray-100">
+            <p class="text-xs text-gray-400">last saved {{ settings.updated_at }}</p>
+            <button type="submit"
+                    class="px-5 py-2 bg-indigo-600 text-white text-sm font-medium rounded hover:bg-indigo-700 transition-colors">
+                Save
+            </button>
+        </div>
+    </form>
+</div>

src/second_brain/web/templates/base.html

@@ -16,8 +16,10 @@
             <p class="text-indigo-200 text-sm mt-0.5">personal knowledge pipeline</p>
         </div>
         <nav class="flex gap-4 text-sm font-medium">
+            <a href="/dashboard" class="hover:text-indigo-200 transition-colors">Dashboard</a>
             <a href="/" class="hover:text-indigo-200 transition-colors">Sources</a>
             <a href="/queue" class="hover:text-indigo-200 transition-colors">Queue</a>
+            <a href="/settings" class="hover:text-indigo-200 transition-colors">Settings</a>
         </nav>
     </div>
 </header>

src/second_brain/web/templates/dashboard.html

@@ -0,0 +1,158 @@
+{% extends "base.html" %}
+
+{% block title %}Dashboard — second-brain{% endblock %}
+
+{% block content %}
+{% set status_colors = {
+    'pending':     'bg-gray-100 text-gray-700',
+    'pulled':      'bg-blue-100 text-blue-700',
+    'transcribed': 'bg-yellow-100 text-yellow-700',
+    'analyzed':    'bg-orange-100 text-orange-700',
+    'accepted':    'bg-green-100 text-green-700',
+    'published':   'bg-purple-100 text-purple-700',
+    'failed':      'bg-red-100 text-red-700'
+} %}
+{% set domain_colors = {
+    'development': 'bg-cyan-50 text-cyan-700 border-cyan-200',
+    'content':     'bg-pink-50 text-pink-700 border-pink-200',
+    'business':    'bg-amber-50 text-amber-700 border-amber-200',
+    'homelab':     'bg-teal-50 text-teal-700 border-teal-200'
+} %}
+
+<div class="mb-6 flex items-center justify-between">
+    <h2 class="text-2xl font-semibold text-gray-800">Dashboard</h2>
+    <span class="text-sm text-gray-500">total sources: {{ total }}</span>
+</div>
+
+<!-- Pipeline overview -->
+<section class="bg-white rounded-lg shadow-sm p-5 mb-6">
+    <h3 class="text-sm font-semibold uppercase tracking-wide text-gray-500 mb-3">
+        Pipeline
+    </h3>
+    <div class="grid grid-cols-2 md:grid-cols-4 lg:grid-cols-7 gap-3">
+        {% for status in statuses_in_order %}
+        <a href="/?status={{ status }}"
+           class="block rounded-lg border border-gray-200 hover:border-indigo-400 hover:shadow-sm transition-all px-3 py-3">
+            <div class="text-2xl font-bold text-gray-900 leading-none">{{ counts.get(status, 0) }}</div>
+            <div class="mt-1.5">
+                <span class="text-xs px-2 py-0.5 rounded-full font-medium
+                    {{ status_colors.get(status, 'bg-gray-100 text-gray-700') }}">
+                    {{ status }}
+                </span>
+            </div>
+        </a>
+        {% endfor %}
+    </div>
+</section>
+
+<!-- Settings snapshot + Recent activity, side by side on wide screens -->
+<div class="grid lg:grid-cols-3 gap-6">
+
+    <!-- Settings snapshot -->
+    <section class="bg-white rounded-lg shadow-sm p-5 lg:col-span-1">
+        <div class="flex items-center justify-between mb-3">
+            <h3 class="text-sm font-semibold uppercase tracking-wide text-gray-500">
+                Settings
+            </h3>
+            <a href="/settings" class="text-xs text-indigo-600 hover:text-indigo-700 font-medium">
+                edit →
+            </a>
+        </div>
+
+        <dl class="text-sm space-y-2">
+            <div class="flex justify-between items-center">
+                <dt class="text-gray-600">Transcription</dt>
+                <dd>
+                    {% if settings.transcription_enabled %}
+                    <span class="text-xs px-2 py-0.5 rounded-full bg-green-100 text-green-700 font-medium">enabled</span>
+                    {% else %}
+                    <span class="text-xs px-2 py-0.5 rounded-full bg-gray-200 text-gray-600 font-medium">paused</span>
+                    {% endif %}
+                </dd>
+            </div>
+            <div class="flex justify-between items-center">
+                <dt class="text-gray-600">  active window</dt>
+                <dd class="text-gray-800 font-mono text-xs">
+                    {% if settings.transcription_active_hours_start or settings.transcription_active_hours_end %}
+                    {{ settings.transcription_active_hours_start or "—" }} – {{ settings.transcription_active_hours_end or "—" }}
+                    {% else %}
+                    always
+                    {% endif %}
+                </dd>
+            </div>
+            <div class="flex justify-between items-center">
+                <dt class="text-gray-600">  GPU jobs</dt>
+                <dd class="text-gray-800 font-mono text-xs">{{ settings.transcription_max_concurrent_gpu_jobs }}</dd>
+            </div>
+            <div class="flex justify-between items-center">
+                <dt class="text-gray-600">  max items/run</dt>
+                <dd class="text-gray-800 font-mono text-xs">{{ settings.transcription_max_items_per_run }}</dd>
+            </div>
+
+            <div class="border-t border-gray-100 pt-2 mt-2"></div>
+
+            <div class="flex justify-between items-center">
+                <dt class="text-gray-600">Extraction</dt>
+                <dd>
+                    {% if settings.extraction_enabled %}
+                    <span class="text-xs px-2 py-0.5 rounded-full bg-green-100 text-green-700 font-medium">enabled</span>
+                    {% else %}
+                    <span class="text-xs px-2 py-0.5 rounded-full bg-gray-200 text-gray-600 font-medium">paused</span>
+                    {% endif %}
+                </dd>
+            </div>
+            <div class="flex justify-between items-center">
+                <dt class="text-gray-600">  active window</dt>
+                <dd class="text-gray-800 font-mono text-xs">
+                    {% if settings.extraction_active_hours_start or settings.extraction_active_hours_end %}
+                    {{ settings.extraction_active_hours_start or "—" }} – {{ settings.extraction_active_hours_end or "—" }}
+                    {% else %}
+                    always
+                    {% endif %}
+                </dd>
+            </div>
+            <div class="flex justify-between items-center">
+                <dt class="text-gray-600">  max items/run</dt>
+                <dd class="text-gray-800 font-mono text-xs">{{ settings.extraction_max_items_per_run }}</dd>
+            </div>
+        </dl>
+
+        <p class="text-xs text-gray-400 mt-4">
+            updated {{ settings.updated_at }}
+        </p>
+    </section>
+
+    <!-- Recent activity -->
+    <section class="bg-white rounded-lg shadow-sm p-5 lg:col-span-2">
+        <h3 class="text-sm font-semibold uppercase tracking-wide text-gray-500 mb-3">
+            Recent activity
+        </h3>
+        {% if recent %}
+        <div class="divide-y divide-gray-100">
+            {% for source in recent %}
+            <a href="/sources/{{ source.id }}"
+               class="flex items-start justify-between gap-3 py-2.5 hover:bg-gray-50 -mx-2 px-2 rounded transition-colors">
+                <div class="min-w-0 flex-1">
+                    <p class="text-sm font-medium text-gray-900 truncate">{{ source.title }}</p>
+                    <p class="text-xs text-gray-400 truncate">{{ source.url }}</p>
+                </div>
+                <div class="flex flex-col items-end gap-1 flex-shrink-0">
+                    <span class="text-xs px-2 py-0.5 rounded-full font-medium
+                        {{ status_colors.get(source.status, 'bg-gray-100 text-gray-700') }}">
+                        {{ source.status }}
+                    </span>
+                    <span class="text-xs px-2 py-0.5 rounded border font-medium
+                        {{ domain_colors.get(source.domain, 'bg-gray-50 text-gray-600 border-gray-200') }}">
+                        {{ source.domain }}
+                    </span>
+                    <span class="text-xs text-gray-400">{{ source.ingested_at }}</span>
+                </div>
+            </a>
+            {% endfor %}
+        </div>
+        {% else %}
+        <p class="text-sm text-gray-400 py-8 text-center">No sources yet.</p>
+        {% endif %}
+    </section>
+</div>
+{% endblock %}

src/second_brain/web/templates/settings.html

@@ -0,0 +1,14 @@
+{% extends "base.html" %}
+
+{% block title %}Settings — second-brain{% endblock %}
+
+{% block content %}
+<div class="mb-6">
+    <h2 class="text-2xl font-semibold text-gray-800">Settings</h2>
+    <p class="text-sm text-gray-500 mt-1">
+        Workers read these at the start of each run. DB values override <code class="bg-gray-100 px-1 rounded text-xs">settings.toml</code>.
+    </p>
+</div>
+
+{% include "_settings_card.html" %}
+{% endblock %}

uv.lock

@@ -1385,6 +1385,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/0b/d7/1959b9648791274998a9c3526f6d0ec8fd2233e4d4acce81bbae76b44b2a/python_dotenv-1.2.2-py3-none-any.whl", hash = "sha256:1d8214789a24de455a8b8bd8ae6fe3c6b69a5e3d64aa8a8e5d68e694bbcb285a", size = 22101, upload-time = "2026-03-01T16:00:25.09Z" },
 ]
 
+[[package]]
+name = "python-multipart"
+version = "0.0.29"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/4e/fe/70bd71a6738b09a0bdf6480ca6436b167469ca4578b2a0efbe390b4b0e70/python_multipart-0.0.29.tar.gz", hash = "sha256:643e93849196645e2dbdd81a0f8829a23123ad7f797a84a364c6fb3563f18904", size = 45678, upload-time = "2026-05-17T17:29:47.654Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/8f/cb/769cfc37177252872a45a71f3fbdde9d51b471a3f3c14bfe95dde3407386/python_multipart-0.0.29-py3-none-any.whl", hash = "sha256:2ddcc971cef266225f54f552d8fa10bcfbb1f14446caec199060daac59ff2d69", size = 29640, upload-time = "2026-05-17T17:29:45.69Z" },
+]
+
 [[package]]
 name = "pytz"
 version = "2026.2"
@@ -1584,6 +1593,7 @@ dependencies = [
     { name = "psycopg-pool" },
     { name = "pydantic" },
     { name = "python-dotenv" },
+    { name = "python-multipart" },
     { name = "sqlalchemy" },
     { name = "tomli" },
     { name = "trafilatura" },
@@ -1617,6 +1627,7 @@ requires-dist = [
     { name = "psycopg-pool", specifier = ">=3.2" },
     { name = "pydantic", specifier = ">=2.0.0" },
     { name = "python-dotenv", specifier = ">=1.0.0" },
+    { name = "python-multipart", specifier = ">=0.0.20" },
     { name = "sqlalchemy", specifier = ">=2.0.0" },
     { name = "tomli", specifier = ">=2.0.0" },
     { name = "trafilatura", specifier = ">=1.9.0" },