aa

.trash/gen_er_diagram.py

@@ -0,0 +1,290 @@
+#!/usr/bin/env python3
+"""Generate db_schema.svg — an entity-relationship diagram of the alert4k data model.
+
+Hand-curated layout. Re-run to regenerate the SVG after schema changes.
+"""
+
+# ---- visual constants -------------------------------------------------------
+HEADER_H = 28
+ROW_H = 17
+PAD_X = 10
+FONT = "font-family='Menlo, Consolas, monospace'"
+
+# table accent colours
+C_HUB = "#2c3e7a"     # events
+C_DET = "#1f7a4d"     # detection-ish (detections, clip_detections, clip_tracks)
+C_ID = "#9a4d1f"      # identity (object_identities)
+C_REF = "#6a3d8a"     # reference dictionaries (known/tracked objects)
+C_MOT = "#7a1f3d"     # motion / scene infra
+
+# (label, kind) kind: 'pk','fk','col'
+def col(label, kind="col"):
+    return (label, kind)
+
+tables = {
+    "events": {
+        "x": 470, "y": 90, "w": 270, "accent": C_HUB,
+        "subtitle": "ROOT — one row per motion event",
+        "cols": [
+            col("id", "pk"),
+            col("trigger_ts          timestamptz"),
+            col("source_name         varchar"),
+            col("motion_score        float8"),
+            col("snapshot_path       text"),
+            col("clip_path           text"),
+            col("frame4k_path        text"),
+            col("annotated_frame_path text"),
+            col("description         text"),
+            col("false_positive      bool"),
+            col("absorbed / san_suppress bool"),
+            col("clip_duration_seconds f4"),
+            col("motion_roi_x1..y2   float"),
+            col("blob_count/total/min/max"),
+            col("pipeline_stage      varchar"),
+            col("clip_tracks_version int"),
+            col("scene_background_id → scene_backgrounds", "fk"),
+            col("created_at          timestamptz"),
+        ],
+    },
+    "scene_backgrounds": {
+        "x": 70, "y": 70, "w": 250, "accent": C_MOT,
+        "subtitle": "camera calibration backdrop",
+        "cols": [
+            col("id", "pk"),
+            col("camera_id      varchar"),
+            col("image_path     text"),
+            col("scene_version_id int"),
+            col("quality_score  float"),
+            col("pose_signature text"),
+            col("created_at     timestamptz"),
+        ],
+    },
+    "motion_detections": {
+        "x": 70, "y": 420, "w": 250, "accent": C_MOT,
+        "subtitle": "raw MOG2 blobs (motion svc)",
+        "cols": [
+            col("id", "pk"),
+            col("event_id → events (NULL=unclaimed)", "fk"),
+            col("frame_ts        timestamptz"),
+            col("blob_x1..y2     float"),
+            col("area_px         int"),
+            col("motion_ratio    float"),
+        ],
+    },
+    "detections": {
+        "x": 470, "y": 560, "w": 270, "accent": C_DET,
+        "subtitle": "single-frame GDINO @ trigger",
+        "cols": [
+            col("id", "pk"),
+            col("event_id → events", "fk"),
+            col("phrase   varchar"),
+            col("score    float8"),
+            col("cx, cy, w, h  (normalized)"),
+            col("created_at"),
+        ],
+    },
+    "clip_tracks": {
+        "x": 840, "y": 70, "w": 280, "accent": C_DET,
+        "subtitle": "one row per ByteTrack track in clip",
+        "cols": [
+            col("id", "pk"),
+            col("event_id → events", "fk"),
+            col("track_id        int"),
+            col("phrase          varchar"),
+            col("first_seen_s / last_seen_s"),
+            col("frame_count     int"),
+            col("max_score       float"),
+            col("path_json       text [{t,cx,cy}]"),
+            col("tags            jsonb"),
+            col("displacement    float"),
+            col("path_metrics    real[]"),
+            col("quality_metrics real[]"),
+            col("track_embedding bytea (CLIP)"),
+            col("image_quality / caption_quality"),
+            col("tq_suppress     bool"),
+            col("alpha_crop_path text"),
+        ],
+    },
+    "clip_detections": {
+        "x": 840, "y": 540, "w": 280, "accent": C_DET,
+        "subtitle": "per-frame GDINO sampled from clip",
+        "cols": [
+            col("event_id → events", "fk"),
+            col("track_id  → clip_tracks (soft)", "fk"),
+            col("frame_time_s  real"),
+            col("phrase        char(1) code"),
+            col("score         real"),
+            col("cx, cy, w, h  real"),
+            col("created_at"),
+            col("(no PK since V15 — narrow table)"),
+        ],
+    },
+    "object_identities": {
+        "x": 1230, "y": 360, "w": 290, "accent": C_ID,
+        "subtitle": "JUNCTION — recognition result",
+        "cols": [
+            col("id", "pk"),
+            col("event_id → events", "fk"),
+            col("detection_idx   int"),
+            col("phrase          varchar"),
+            col("embedding       bytea (CLIP crop)"),
+            col("crop_path       text"),
+            col("known_object_id → known_objects", "fk"),
+            col("tracked_object_id → tracked_objects", "fk"),
+            col("clip_track_id → clip_tracks", "fk"),
+            col("identity_type  'detection'|'track'"),
+            col("match_score     float8"),
+            col("is_new          bool"),
+            col("created_at"),
+        ],
+    },
+    "known_objects": {
+        "x": 1230, "y": 70, "w": 290, "accent": C_REF,
+        "subtitle": "manually registered named objects",
+        "cols": [
+            col("id", "pk"),
+            col("name        varchar  (e.g. 'my Honda')"),
+            col("phrase      varchar"),
+            col("embedding   bytea (CLIP 512f)"),
+            col("thumbnail_path text"),
+            col("notes       text"),
+            col("created_at"),
+        ],
+    },
+    "tracked_objects": {
+        "x": 1230, "y": 720, "w": 290, "accent": C_REF,
+        "subtitle": "auto-discovered, clustered cross-event",
+        "cols": [
+            col("id", "pk"),
+            col("pseudo_name  varchar UNIQUE"),
+            col("phrase       varchar"),
+            col("embedding    bytea (EMA-updated)"),
+            col("occurrence_count int"),
+            col("first_seen_ts / last_seen_ts"),
+            col("ground_x/y, world_x_m/y_m"),
+            col("sfm_confidence / confidence_score"),
+            col("identity_status text"),
+            col("best_crop_path / thumbnail_path"),
+            col("created_at"),
+        ],
+    },
+}
+
+def table_height(t):
+    return HEADER_H + 14 + ROW_H * len(t["cols"]) + 8
+
+# anchor helpers — return (x,y) on the edge of a table box
+def left(t, row=None):
+    y = t["y"] + HEADER_H + 14 + (ROW_H * row + ROW_H // 2 if row is not None else table_height(t)//2)
+    return (t["x"], y)
+def right(t, row=None):
+    y = t["y"] + HEADER_H + 14 + (ROW_H * row + ROW_H // 2 if row is not None else table_height(t)//2)
+    return (t["x"] + t["w"], y)
+def top(t):
+    return (t["x"] + t["w"]//2, t["y"])
+def bottom(t):
+    return (t["x"] + t["w"]//2, t["y"] + table_height(t))
+
+parts = []
+W, H = 1580, 980
+parts.append(f"<svg xmlns='http://www.w3.org/2000/svg' width='{W}' height='{H}' viewBox='0 0 {W} {H}'>")
+parts.append(f"<rect x='0' y='0' width='{W}' height='{H}' fill='#f7f8fb'/>")
+
+# title
+parts.append(f"<text x='30' y='40' {FONT} font-size='24' font-weight='700' fill='#1a1a2e'>"
+             "alert4k — Relational Data Model (PostgreSQL)</text>")
+parts.append(f"<text x='30' y='62' {FONT} font-size='13' fill='#555'>"
+             "Motion event → clip analysis → per-track CLIP identity → cross-event object clustering. "
+             "Solid = enforced FK · Dashed = soft/logical link.</text>")
+
+# ---- relationship edges (drawn first, under boxes) -------------------------
+def _glyph(x, y, dir_x, sym):
+    """Draw a cardinality glyph at endpoint (x,y). dir_x = +1 if the line
+    extends to the right of the point, -1 if to the left. sym in {'one','many'}."""
+    o = 11 * (1 if dir_x >= 0 else -1)   # offset into the line
+    if sym == "one":
+        bx = x + o * 0.55
+        parts.append(f"<path d='M{bx},{y-6} L{bx},{y+6}' stroke='#444' stroke-width='1.6'/>")
+    else:  # many — crow's foot fanning into (x,y)
+        parts.append(f"<path d='M{x+o},{y-6} L{x},{y} L{x+o},{y+6} M{x+o},{y} L{x},{y}' "
+                     "fill='none' stroke='#444' stroke-width='1.4'/>")
+
+# (from_anchor, to_anchor, label, dashed)
+def edge(p1, p2, label, dashed=False, lx=None, ly=None, start="one", end="many"):
+    dash = " stroke-dasharray='6 4'" if dashed else ""
+    midx = (p1[0] + p2[0]) / 2
+    d = f"M{p1[0]},{p1[1]} L{midx},{p1[1]} L{midx},{p2[1]} L{p2[0]},{p2[1]}"
+    parts.append(f"<path d='{d}' fill='none' stroke='#444' stroke-width='1.5'{dash}/>")
+    _glyph(p1[0], p1[1], 1 if midx >= p1[0] else -1, start)
+    _glyph(p2[0], p2[1], 1 if midx >= p2[0] else -1, end)
+    if lx is None: lx = (p1[0] + p2[0]) / 2
+    if ly is None: ly = (p1[1] + p2[1]) / 2
+    parts.append(f"<rect x='{lx-30}' y='{ly-10}' width='60' height='15' fill='#f7f8fb' opacity='0.85'/>")
+    parts.append(f"<text x='{lx}' y='{ly+1}' {FONT} font-size='10.5' fill='#333' text-anchor='middle'>{label}</text>")
+
+T = tables
+# events -> children (1:N). events.id is the 'one' side.
+edge(left(T["events"], 1), right(T["motion_detections"], 1), "1 : N", dashed=False)
+edge(bottom(T["events"]), top(T["detections"]), "1 : N")
+edge(right(T["events"], 1), left(T["clip_tracks"], 1), "1 : N")
+edge(right(T["events"], 5), left(T["clip_detections"], 0), "1 : N")
+edge(right(T["events"], 9), left(T["object_identities"], 1), "1 : N")
+# events.scene_background_id -> scene_backgrounds (soft, N:1 from events side)
+edge(left(T["events"], 16), right(T["scene_backgrounds"], 1), "N : 1", dashed=True,
+     start="many", end="one")
+
+# clip_detections.track_id -> clip_tracks (soft composite)
+edge(top(T["clip_detections"]), bottom(T["clip_tracks"]), "N : 1", dashed=True,
+     start="many", end="one")
+
+# object_identities FKs (N:1 to the reference tables)
+edge(top(T["object_identities"]), bottom(T["known_objects"]), "N : 1", start="many", end="one")
+edge(bottom(T["object_identities"]), top(T["tracked_objects"]), "N : 1", start="many", end="one")
+edge(left(T["object_identities"], 8), right(T["clip_tracks"], 7), "N : 1", start="many", end="one")
+
+# ---- table boxes -----------------------------------------------------------
+def kind_color(kind):
+    return {"pk": "#1a1a2e", "fk": "#9a4d1f", "col": "#333"}[kind]
+
+for name, t in tables.items():
+    h = table_height(t)
+    x, y, w = t["x"], t["y"], t["w"]
+    parts.append(f"<rect x='{x}' y='{y}' width='{w}' height='{h}' rx='8' fill='white' "
+                 f"stroke='{t['accent']}' stroke-width='2'/>")
+    parts.append(f"<rect x='{x}' y='{y}' width='{w}' height='{HEADER_H}' rx='8' fill='{t['accent']}'/>")
+    parts.append(f"<rect x='{x}' y='{y+HEADER_H-8}' width='{w}' height='8' fill='{t['accent']}'/>")
+    parts.append(f"<text x='{x+PAD_X}' y='{y+19}' {FONT} font-size='14' font-weight='700' fill='white'>{name}</text>")
+    parts.append(f"<text x='{x+PAD_X}' y='{y+HEADER_H+11}' {FONT} font-size='9.5' fill='#888' font-style='italic'>{t['subtitle']}</text>")
+    cy = y + HEADER_H + 14
+    for i, (label, kind) in enumerate(t["cols"]):
+        ry = cy + ROW_H * i
+        if i % 2 == 1:
+            parts.append(f"<rect x='{x+1}' y='{ry}' width='{w-2}' height='{ROW_H}' fill='#f2f3f7'/>")
+        weight = "700" if kind == "pk" else "400"
+        prefix = "PK " if kind == "pk" else ("FK " if kind == "fk" else "   ")
+        deco = " text-decoration='underline'" if kind == "pk" else ""
+        esc = label.replace("&", "&amp;").replace("<", "&lt;").replace(">", "→")
+        parts.append(f"<text x='{x+PAD_X}' y='{ry+12}' {FONT} font-size='10.5' "
+                     f"fill='{kind_color(kind)}' font-weight='{weight}'{deco}>"
+                     f"<tspan fill='#aa7' font-weight='700'>{prefix}</tspan>{esc}</text>")
+
+# ---- legend ----------------------------------------------------------------
+lx, ly = 70, 720
+parts.append(f"<rect x='{lx}' y='{ly}' width='250' height='150' rx='8' fill='white' stroke='#ccc'/>")
+parts.append(f"<text x='{lx+12}' y='{ly+22}' {FONT} font-size='13' font-weight='700' fill='#1a1a2e'>Legend</text>")
+legend = [
+    ("PK  primary key (underlined)", "#1a1a2e"),
+    ("FK  foreign key → target", "#9a4d1f"),
+    ("─── enforced FK constraint", "#444"),
+    ("- -  soft / logical link", "#444"),
+    ("⊢   = 'one'   ⟨  = 'many'", "#444"),
+    ("embedding = CLIP ViT-B/32 512f", "#666"),
+]
+for i, (txt, c) in enumerate(legend):
+    parts.append(f"<text x='{lx+12}' y='{ly+44+i*18}' {FONT} font-size='10.5' fill='{c}'>{txt}</text>")
+
+parts.append("</svg>")
+
+with open("db_schema.svg", "w") as f:
+    f.write("\n".join(parts))
+print("wrote db_schema.svg")

.trash/position_prompts.md

@@ -0,0 +1,30 @@
+token: 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
+
+-  front-facing portrait or frontal portrait.
+- Head-on portrait: person faces directly toward the camera.
+- Straight-on portrait: neutral, camera directly in front.
+- Mugshot-style photo: front-facing, often neutral expression, but has a police/ID connotation.
+- Passport photo or ID photo: front-facing with a plain background and strict framing.
+- front-facing full-body portrait.
+- Full-length portrait: shows the person from head to toe.
+- Straight-on full-body shot: person faces the camera directly.
+- Head-to-toe portrait: informal but clear.
+- a straight-on full-body portrait.
+
+Three-quarter view
+Person is turned partly sideways, often about 45°, but still visible from the front. This is the normal portrait term.
+
+Profile view
+Person is fully sideways, seen from the side.
+
+Frontal view / straight-on view
+Person faces camera directly.
+
+Isometric view
+Mostly used for objects, architecture, games, diagrams: a 3D-looking view with equal axes/angles, not a normal human portrait pose.
+
+- a full-body three-quarter portrait
+- a straight-on full-body portrait in three-quarter view if the body is angled but the person still looks at the camera.
+- Head-on a full-body three-quarter full-nude-body portrait transparent background
+- Head-on straight-on full-nude-body portrait transparent background
+- Head-on straight-on full-body portrait no background