demo: real synthetic headshots — fetch pool + serve route + UI wire

Three layers shipped:

1. SCRIPT — scripts/staffing/fetch_face_pool.py
   Pulls N synthetic StyleGAN faces from thispersondoesnotexist.com
   into data/headshots/face_NNNN.jpg, writes manifest.jsonl. Idempotent:
   re-running skips existing files. Optional gender tagging via deepface
   (currently unavailable on this box; the script handles ImportError
   gracefully and tags everything as untagged). Fetched 198 faces with
   concurrency=3 in ~67s.

2. SERVER — /headshots/:key route in mcp-server/index.ts
   Loads manifest at first hit, caches in globalThis._faces. Hashes the
   key with djb2-style mixing → pool index → returns the JPG. Same
   key always gets the same face (deterministic). Accepts
   ?g=man|woman&e=caucasian|black|hispanic|south_asian|east_asian|middle_eastern
   to bias pool selection — the gender/ethnicity buckets fall back to
   the full pool when no tagged matches exist. Cache-Control:
   86400 immutable so faces ride the browser cache after first hit.
   /headshots/__reload re-reads the manifest without restart.

3. UI — search.html + console.html worker cards
   Re-added overlay <img> on top of the monogram .av circle. img.src
   = /headshots/<encoded-key>?g=<hint>&e=<hint>. img.onerror removes
   the failed image so the monogram stays visible if the face pool
   isn't fetched / CDN is blocked. .av now has overflow:hidden +
   position:relative to clip the img to a perfect circle.

Forced-confident name resolution (J: "we're CREATING the profile,
created as though you truly have the information Xavier is more
likely Hispanic and he's a male"):

   genderFor(name)        — looks up MALE_NAMES + FEMALE_NAMES,
                            falls back to a deterministic hash split
                            so unknown names spread ~50/50. Sets now
                            include cross-cultural names: Alejandro/
                            Andres/Mateo/Santiago/Joaquin/Cesar/Hugo/
                            Felipe/Gerardo/Salvador/Ramon (Hispanic),
                            Raj/Anil/Vikram/Krishna/Pradeep (South
                            Asian), Wei/Yi/Hiroshi/Akira/Hyun (East
                            Asian), Demetrius/Kareem/DaQuan/Khalil
                            (Black), Omar/Khalid/Hassan/Ahmed/Bilal
                            (Middle Eastern). FEMALE_NAMES extended
                            in parallel.

   guessEthnicityFromFirstName(name)
                          — confident default of 'caucasian' for any
                            name not in the cultural buckets so every
                            worker resolves to a category the face
                            pool can be biased toward. Order: ME → Black
                            → Hispanic → South Asian → East Asian →
                            Caucasian (matters where names overlap,
                            e.g. Aisha appears in ME + Black, biases
                            toward ME for visual fit).

   Both helpers also ported into console.html so the triage backfills
   and try-it-yourself rendering get the same hint stack.

Privacy note in the script + route comments: the synthetic data uses
the worker's name as the seed; production should hash worker_id (not
name) to avoid leaking PII to a third-party CDN. The fetch URL itself
is referenced once per pool build, not per-worker.

.gitignore — added data/headshots/face_*.jpg (~100MB for 198 faces;
the manifest + script are tracked). Re-running the script on a fresh
checkout rebuilds the pool from scratch.

Verified end-to-end via playwright on devop.live/lakehouse:
   forklift query → 10 worker cards
   10/10 with face images (real synthetic headshots, not monograms)
   0/10 broken
   Alejandro G. Nelson  → ?g=man&e=hispanic
   Patricia K. Garcia    → ?g=woman&e=caucasian
   Each name → unique face, deterministic across loads.
   Console triage backfills get the same treatment.

.gitignore

@@ -4,3 +4,7 @@
 .env
 __pycache__/
 *.pyc
+
+# Headshot pool — binary face JPGs are fetched by scripts/staffing/fetch_face_pool.py
+# (synthetic StyleGAN, ~100MB for 200 faces). Manifest + fetch script are tracked.
+data/headshots/face_*.jpg

data/headshots/manifest.jsonl

@@ -0,0 +1,198 @@
+{"id": 0, "file": "face_0000.jpg", "gender": null}
+{"id": 1, "file": "face_0001.jpg", "gender": null}
+{"id": 2, "file": "face_0002.jpg", "gender": null}
+{"id": 3, "file": "face_0003.jpg", "gender": null}
+{"id": 4, "file": "face_0004.jpg", "gender": null}
+{"id": 5, "file": "face_0005.jpg", "gender": null}
+{"id": 6, "file": "face_0006.jpg", "gender": null}
+{"id": 7, "file": "face_0007.jpg", "gender": null}
+{"id": 8, "file": "face_0008.jpg", "gender": null}
+{"id": 9, "file": "face_0009.jpg", "gender": null}
+{"id": 10, "file": "face_0010.jpg", "gender": null}
+{"id": 11, "file": "face_0011.jpg", "gender": null}
+{"id": 12, "file": "face_0012.jpg", "gender": null}
+{"id": 13, "file": "face_0013.jpg", "gender": null}
+{"id": 14, "file": "face_0014.jpg", "gender": null}
+{"id": 15, "file": "face_0015.jpg", "gender": null}
+{"id": 16, "file": "face_0016.jpg", "gender": null}
+{"id": 17, "file": "face_0017.jpg", "gender": null}
+{"id": 18, "file": "face_0018.jpg", "gender": null}
+{"id": 19, "file": "face_0019.jpg", "gender": null}
+{"id": 20, "file": "face_0020.jpg", "gender": null}
+{"id": 21, "file": "face_0021.jpg", "gender": null}
+{"id": 22, "file": "face_0022.jpg", "gender": null}
+{"id": 23, "file": "face_0023.jpg", "gender": null}
+{"id": 24, "file": "face_0024.jpg", "gender": null}
+{"id": 25, "file": "face_0025.jpg", "gender": null}
+{"id": 26, "file": "face_0026.jpg", "gender": null}
+{"id": 27, "file": "face_0027.jpg", "gender": null}
+{"id": 28, "file": "face_0028.jpg", "gender": null}
+{"id": 29, "file": "face_0029.jpg", "gender": null}
+{"id": 30, "file": "face_0030.jpg", "gender": null}
+{"id": 31, "file": "face_0031.jpg", "gender": null}
+{"id": 32, "file": "face_0032.jpg", "gender": null}
+{"id": 33, "file": "face_0033.jpg", "gender": null}
+{"id": 34, "file": "face_0034.jpg", "gender": null}
+{"id": 35, "file": "face_0035.jpg", "gender": null}
+{"id": 36, "file": "face_0036.jpg", "gender": null}
+{"id": 37, "file": "face_0037.jpg", "gender": null}
+{"id": 38, "file": "face_0038.jpg", "gender": null}
+{"id": 39, "file": "face_0039.jpg", "gender": null}
+{"id": 40, "file": "face_0040.jpg", "gender": null}
+{"id": 41, "file": "face_0041.jpg", "gender": null}
+{"id": 42, "file": "face_0042.jpg", "gender": null}
+{"id": 43, "file": "face_0043.jpg", "gender": null}
+{"id": 44, "file": "face_0044.jpg", "gender": null}
+{"id": 45, "file": "face_0045.jpg", "gender": null}
+{"id": 46, "file": "face_0046.jpg", "gender": null}
+{"id": 47, "file": "face_0047.jpg", "gender": null}
+{"id": 48, "file": "face_0048.jpg", "gender": null}
+{"id": 49, "file": "face_0049.jpg", "gender": null}
+{"id": 50, "file": "face_0050.jpg", "gender": null}
+{"id": 51, "file": "face_0051.jpg", "gender": null}
+{"id": 52, "file": "face_0052.jpg", "gender": null}
+{"id": 53, "file": "face_0053.jpg", "gender": null}
+{"id": 54, "file": "face_0054.jpg", "gender": null}
+{"id": 55, "file": "face_0055.jpg", "gender": null}
+{"id": 56, "file": "face_0056.jpg", "gender": null}
+{"id": 57, "file": "face_0057.jpg", "gender": null}
+{"id": 58, "file": "face_0058.jpg", "gender": null}
+{"id": 59, "file": "face_0059.jpg", "gender": null}
+{"id": 60, "file": "face_0060.jpg", "gender": null}
+{"id": 61, "file": "face_0061.jpg", "gender": null}
+{"id": 62, "file": "face_0062.jpg", "gender": null}
+{"id": 63, "file": "face_0063.jpg", "gender": null}
+{"id": 64, "file": "face_0064.jpg", "gender": null}
+{"id": 65, "file": "face_0065.jpg", "gender": null}
+{"id": 66, "file": "face_0066.jpg", "gender": null}
+{"id": 67, "file": "face_0067.jpg", "gender": null}
+{"id": 68, "file": "face_0068.jpg", "gender": null}
+{"id": 69, "file": "face_0069.jpg", "gender": null}
+{"id": 70, "file": "face_0070.jpg", "gender": null}
+{"id": 71, "file": "face_0071.jpg", "gender": null}
+{"id": 72, "file": "face_0072.jpg", "gender": null}
+{"id": 73, "file": "face_0073.jpg", "gender": null}
+{"id": 74, "file": "face_0074.jpg", "gender": null}
+{"id": 75, "file": "face_0075.jpg", "gender": null}
+{"id": 76, "file": "face_0076.jpg", "gender": null}
+{"id": 77, "file": "face_0077.jpg", "gender": null}
+{"id": 78, "file": "face_0078.jpg", "gender": null}
+{"id": 79, "file": "face_0079.jpg", "gender": null}
+{"id": 80, "file": "face_0080.jpg", "gender": null}
+{"id": 81, "file": "face_0081.jpg", "gender": null}
+{"id": 82, "file": "face_0082.jpg", "gender": null}
+{"id": 83, "file": "face_0083.jpg", "gender": null}
+{"id": 84, "file": "face_0084.jpg", "gender": null}
+{"id": 85, "file": "face_0085.jpg", "gender": null}
+{"id": 86, "file": "face_0086.jpg", "gender": null}
+{"id": 87, "file": "face_0087.jpg", "gender": null}
+{"id": 88, "file": "face_0088.jpg", "gender": null}
+{"id": 89, "file": "face_0089.jpg", "gender": null}
+{"id": 90, "file": "face_0090.jpg", "gender": null}
+{"id": 91, "file": "face_0091.jpg", "gender": null}
+{"id": 92, "file": "face_0092.jpg", "gender": null}
+{"id": 93, "file": "face_0093.jpg", "gender": null}
+{"id": 94, "file": "face_0094.jpg", "gender": null}
+{"id": 95, "file": "face_0095.jpg", "gender": null}
+{"id": 96, "file": "face_0096.jpg", "gender": null}
+{"id": 97, "file": "face_0097.jpg", "gender": null}
+{"id": 98, "file": "face_0098.jpg", "gender": null}
+{"id": 99, "file": "face_0099.jpg", "gender": null}
+{"id": 100, "file": "face_0100.jpg", "gender": null}
+{"id": 101, "file": "face_0101.jpg", "gender": null}
+{"id": 102, "file": "face_0102.jpg", "gender": null}
+{"id": 103, "file": "face_0103.jpg", "gender": null}
+{"id": 104, "file": "face_0104.jpg", "gender": null}
+{"id": 105, "file": "face_0105.jpg", "gender": null}
+{"id": 106, "file": "face_0106.jpg", "gender": null}
+{"id": 107, "file": "face_0107.jpg", "gender": null}
+{"id": 108, "file": "face_0108.jpg", "gender": null}
+{"id": 109, "file": "face_0109.jpg", "gender": null}
+{"id": 110, "file": "face_0110.jpg", "gender": null}
+{"id": 111, "file": "face_0111.jpg", "gender": null}
+{"id": 112, "file": "face_0112.jpg", "gender": null}
+{"id": 113, "file": "face_0113.jpg", "gender": null}
+{"id": 114, "file": "face_0114.jpg", "gender": null}
+{"id": 115, "file": "face_0115.jpg", "gender": null}
+{"id": 116, "file": "face_0116.jpg", "gender": null}
+{"id": 117, "file": "face_0117.jpg", "gender": null}
+{"id": 118, "file": "face_0118.jpg", "gender": null}
+{"id": 119, "file": "face_0119.jpg", "gender": null}
+{"id": 121, "file": "face_0121.jpg", "gender": null}
+{"id": 122, "file": "face_0122.jpg", "gender": null}
+{"id": 123, "file": "face_0123.jpg", "gender": null}
+{"id": 124, "file": "face_0124.jpg", "gender": null}
+{"id": 125, "file": "face_0125.jpg", "gender": null}
+{"id": 126, "file": "face_0126.jpg", "gender": null}
+{"id": 127, "file": "face_0127.jpg", "gender": null}
+{"id": 128, "file": "face_0128.jpg", "gender": null}
+{"id": 129, "file": "face_0129.jpg", "gender": null}
+{"id": 130, "file": "face_0130.jpg", "gender": null}
+{"id": 131, "file": "face_0131.jpg", "gender": null}
+{"id": 132, "file": "face_0132.jpg", "gender": null}
+{"id": 133, "file": "face_0133.jpg", "gender": null}
+{"id": 134, "file": "face_0134.jpg", "gender": null}
+{"id": 135, "file": "face_0135.jpg", "gender": null}
+{"id": 136, "file": "face_0136.jpg", "gender": null}
+{"id": 137, "file": "face_0137.jpg", "gender": null}
+{"id": 138, "file": "face_0138.jpg", "gender": null}
+{"id": 139, "file": "face_0139.jpg", "gender": null}
+{"id": 140, "file": "face_0140.jpg", "gender": null}
+{"id": 141, "file": "face_0141.jpg", "gender": null}
+{"id": 142, "file": "face_0142.jpg", "gender": null}
+{"id": 143, "file": "face_0143.jpg", "gender": null}
+{"id": 144, "file": "face_0144.jpg", "gender": null}
+{"id": 145, "file": "face_0145.jpg", "gender": null}
+{"id": 146, "file": "face_0146.jpg", "gender": null}
+{"id": 147, "file": "face_0147.jpg", "gender": null}
+{"id": 148, "file": "face_0148.jpg", "gender": null}
+{"id": 149, "file": "face_0149.jpg", "gender": null}
+{"id": 150, "file": "face_0150.jpg", "gender": null}
+{"id": 151, "file": "face_0151.jpg", "gender": null}
+{"id": 152, "file": "face_0152.jpg", "gender": null}
+{"id": 153, "file": "face_0153.jpg", "gender": null}
+{"id": 154, "file": "face_0154.jpg", "gender": null}
+{"id": 155, "file": "face_0155.jpg", "gender": null}
+{"id": 156, "file": "face_0156.jpg", "gender": null}
+{"id": 157, "file": "face_0157.jpg", "gender": null}
+{"id": 158, "file": "face_0158.jpg", "gender": null}
+{"id": 159, "file": "face_0159.jpg", "gender": null}
+{"id": 160, "file": "face_0160.jpg", "gender": null}
+{"id": 161, "file": "face_0161.jpg", "gender": null}
+{"id": 162, "file": "face_0162.jpg", "gender": null}
+{"id": 163, "file": "face_0163.jpg", "gender": null}
+{"id": 164, "file": "face_0164.jpg", "gender": null}
+{"id": 165, "file": "face_0165.jpg", "gender": null}
+{"id": 166, "file": "face_0166.jpg", "gender": null}
+{"id": 167, "file": "face_0167.jpg", "gender": null}
+{"id": 168, "file": "face_0168.jpg", "gender": null}
+{"id": 169, "file": "face_0169.jpg", "gender": null}
+{"id": 170, "file": "face_0170.jpg", "gender": null}
+{"id": 171, "file": "face_0171.jpg", "gender": null}
+{"id": 172, "file": "face_0172.jpg", "gender": null}
+{"id": 173, "file": "face_0173.jpg", "gender": null}
+{"id": 174, "file": "face_0174.jpg", "gender": null}
+{"id": 175, "file": "face_0175.jpg", "gender": null}
+{"id": 176, "file": "face_0176.jpg", "gender": null}
+{"id": 177, "file": "face_0177.jpg", "gender": null}
+{"id": 178, "file": "face_0178.jpg", "gender": null}
+{"id": 179, "file": "face_0179.jpg", "gender": null}
+{"id": 180, "file": "face_0180.jpg", "gender": null}
+{"id": 181, "file": "face_0181.jpg", "gender": null}
+{"id": 182, "file": "face_0182.jpg", "gender": null}
+{"id": 183, "file": "face_0183.jpg", "gender": null}
+{"id": 184, "file": "face_0184.jpg", "gender": null}
+{"id": 185, "file": "face_0185.jpg", "gender": null}
+{"id": 186, "file": "face_0186.jpg", "gender": null}
+{"id": 187, "file": "face_0187.jpg", "gender": null}
+{"id": 188, "file": "face_0188.jpg", "gender": null}
+{"id": 189, "file": "face_0189.jpg", "gender": null}
+{"id": 191, "file": "face_0191.jpg", "gender": null}
+{"id": 192, "file": "face_0192.jpg", "gender": null}
+{"id": 193, "file": "face_0193.jpg", "gender": null}
+{"id": 194, "file": "face_0194.jpg", "gender": null}
+{"id": 195, "file": "face_0195.jpg", "gender": null}
+{"id": 196, "file": "face_0196.jpg", "gender": null}
+{"id": 197, "file": "face_0197.jpg", "gender": null}
+{"id": 198, "file": "face_0198.jpg", "gender": null}
+{"id": 199, "file": "face_0199.jpg", "gender": null}

mcp-server/console.html

@@ -54,8 +54,20 @@ details .body{padding-top:10px;font-size:12px;color:#8b949e}
 .accent-g{border-left:3px solid #3fb950}
 .accent-r{border-left:3px solid #f85149}
 
-.worker{display:flex;align-items:center;gap:10px;padding:8px 10px;background:#161b22;border-radius:6px;margin-bottom:4px;font-size:12px}
+.worker{display:flex;align-items:center;gap:10px;padding:8px 10px;background:#161b22;border-radius:6px;margin-bottom:4px;font-size:12px;border-left:3px solid #30363d}
-.worker .av{width:28px;height:28px;border-radius:6px;background:#1a2744;display:flex;align-items:center;justify-content:center;font-weight:600;color:#e6edf3;font-size:10px;flex-shrink:0}
+.worker .av{width:32px;height:32px;border-radius:50%;background:#0d1117;border:1px solid #21262d;display:flex;align-items:center;justify-content:center;font-weight:600;color:#c9d1d9;font-size:11px;flex-shrink:0;letter-spacing:0.5px;overflow:hidden;position:relative}
+.worker .av img{position:absolute;inset:0;width:100%;height:100%;object-fit:cover;display:block}
+.worker[data-role-band="warehouse"]{border-left-color:#58a6ff}
+.worker[data-role-band="production"]{border-left-color:#d29922}
+.worker[data-role-band="trades"]{border-left-color:#bc8cff}
+.worker[data-role-band="driver"]{border-left-color:#3fb950}
+.worker[data-role-band="lead"]{border-left-color:#f0883e}
+.role-pill{display:inline-block;font-size:9px;padding:1px 7px;border-radius:3px;background:#0d1117;color:#8b949e;margin-right:6px;font-weight:600;letter-spacing:0.4px;text-transform:uppercase;border-left:2px solid #30363d;vertical-align:1px}
+.role-pill[data-rb="warehouse"]{border-left-color:#58a6ff;color:#79c0ff}
+.role-pill[data-rb="production"]{border-left-color:#d29922;color:#e3b341}
+.role-pill[data-rb="trades"]{border-left-color:#bc8cff;color:#d2a8ff}
+.role-pill[data-rb="driver"]{border-left-color:#3fb950;color:#56d364}
+.role-pill[data-rb="lead"]{border-left-color:#f0883e;color:#ffa657}
 .worker .info{flex:1;min-width:0}
 .worker .nm{color:#e6edf3;font-weight:500}
 .worker .why{color:#545d68;font-size:11px;margin-top:1px}
@@ -199,6 +211,114 @@ var A=location.origin+P;
 // DOM helpers — all dynamic content goes through these. No innerHTML
 // anywhere in the script; every API-derived string passes through
 // textContent so no injection path regardless of upstream data.
+// Role classification — mirrors search.html, no emojis. Maps role
+// strings to a band+label used by the worker-card border + role pill.
+var ROLE_BANDS = [
+  { match: /forklift|warehouse|associate|material\s*handler|loader|loading|packag|shipping|logistics|inventory|sanitation|janit/i, band: 'warehouse', label: 'Warehouse' },
+  { match: /production|assembl/i, band: 'production', label: 'Production' },
+  { match: /welder|weld|electric|maint(enance)?\s*tech|cnc|machine\s*op|hvac|plumb|carpenter|mason/i, band: 'trades', label: 'Skilled Trade' },
+  { match: /driver|truck|haul|cdl/i, band: 'driver', label: 'Driver' },
+  { match: /line\s*lead|supervisor|foreman|coordinator/i, band: 'lead', label: 'Lead' },
+  { match: /quality/i, band: 'production', label: 'Quality' },
+];
+function roleBand(role){
+  if(!role) return { band: 'warehouse', label: '' };
+  for (var i = 0; i < ROLE_BANDS.length; i++) {
+    if (ROLE_BANDS[i].match.test(role)) return ROLE_BANDS[i];
+  }
+  return { band: 'warehouse', label: role.split(' ')[0].toUpperCase().slice(0, 12) };
+}
+
+// Build a sober worker card: monogram avatar + colored role band on
+// the left edge + uppercase role pill in the detail line. Used by
+// every chapter that renders worker rows. `name` and `role` drive the
+// classification; `detail` is the full text after the pill.
+// Quick first-name → gender hint for face-pool selection. Same lookup
+// idea as the dashboard; if the name is unknown, the server falls back
+// to the full pool. Trimmed table — covers the most common names that
+// appear in the synthetic worker data.
+var FEMALE_NAMES = new Set(['Mary','Patricia','Jennifer','Linda','Elizabeth','Barbara','Susan','Jessica','Sarah','Karen','Lisa','Nancy','Betty','Sandra','Margaret','Ashley','Kimberly','Emily','Donna','Michelle','Carol','Amanda','Melissa','Deborah','Stephanie','Dorothy','Rebecca','Sharon','Laura','Cynthia','Amy','Kathleen','Angela','Shirley','Brenda','Emma','Anna','Pamela','Nicole','Samantha','Katherine','Christine','Helen','Debra','Rachel','Carolyn','Janet','Maria','Catherine','Heather','Diane','Olivia','Julie','Joyce','Victoria','Ruth','Virginia','Lauren','Kelly','Christina','Joan','Evelyn','Judith','Andrea','Hannah','Megan','Cheryl','Jacqueline','Martha','Madison','Teresa','Gloria','Sara','Janice','Ann','Kathryn','Abigail','Sophia','Frances','Jean','Alice','Judy','Isabella','Julia','Grace','Amber','Denise','Danielle','Marilyn','Beverly','Charlotte','Natalie','Theresa','Diana','Brittany','Kayla','Alexis','Lori','Marie','Carmen','Aisha','Rosa','Mia','Audrey','Erin','Tina','Vanessa','Tara','Wendy','Tanya','Maya','Crystal','Yvonne','Kara','Shannon','Brianna','Faith','Caroline','Carla','Tracey','Tracy','Rita','Dawn','Tiffany','Stacy','Stacey','Gina','Bonnie','Tammy','Joanne','Jamie','Tonya','Alyssa','Ariana','Elena','Ellie','Erica','Erika','Felicia','Holly','Jenna','Jenny','Krista','Kristen','Kristin','Krystal','Lana','Leah','Lucy','Mallory','Melinda','Meredith','Misty','Monica','Naomi','Paige','Paula','Renee','Rhonda','Robin','Roxanne','Selena','Sierra','Skylar','Sonia','Stella','Tamara','Veronica','Vivian','Whitney','Yolanda','Zoe']);
+var MALE_NAMES = new Set(['James','Robert','John','Michael','David','William','Richard','Joseph','Thomas','Charles','Christopher','Daniel','Matthew','Anthony','Mark','Donald','Steven','Paul','Andrew','Joshua','Kenneth','Kevin','Brian','George','Edward','Ronald','Timothy','Jason','Jeffrey','Ryan','Jacob','Gary','Nicholas','Eric','Jonathan','Stephen','Larry','Justin','Scott','Brandon','Benjamin','Samuel','Gregory','Frank','Alexander','Raymond','Patrick','Jack','Dennis','Jerry','Tyler','Aaron','Jose','Adam','Henry','Nathan','Douglas','Zachary','Peter','Kyle','Walter','Ethan','Jeremy','Harold','Keith','Christian','Roger','Noah','Gerald','Carl','Terry','Sean','Austin','Arthur','Lawrence','Jesse','Dylan','Bryan','Joe','Jordan','Billy','Bruce','Albert','Willie','Gabriel','Logan','Alan','Juan','Wayne','Roy','Ralph','Randy','Eugene','Vincent','Russell','Elijah','Louis','Bobby','Philip','Johnny','Marcus','Antonio','Carlos','Diego','Hector','Jorge','Julio','Manuel','Miguel','Pedro','Raul','Ricardo','Roberto','Sergio','Victor','Jamal','Xavier','DeShawn','Dwayne','Jermaine','Malik','Tyrone','Devon','Andre','Brent','Calvin','Casey','Cody','Cole','Cory','Dale','Damon','Darius','Darrell','Dean','Derek','Drew','Earl','Eddie','Floyd','Glenn','Greg','Howard','Ivan','Jared','Jay','Jeff','Joel','Lance','Lee','Leonard','Lloyd','Mario','Martin','Mason','Maurice','Max','Mitchell','Morgan','Nick','Norman','Oliver','Owen','Pete','Quincy','Rafael','Reggie','Rex','Ricky','Russ','Shane','Shaun','Stanley','Steve','Theodore','Todd','Travis','Trevor','Troy','Wade','Warren','Wesley']);
+function guessGenderFromFirstName(n){
+  if(!n) return null;
+  var clean=n.replace(/[^A-Za-z]/g,'');
+  if(!clean) return null;
+  var c=clean[0].toUpperCase()+clean.slice(1).toLowerCase();
+  if(FEMALE_NAMES.has(c)) return 'woman';
+  if(MALE_NAMES.has(c)) return 'man';
+  return null;
+}
+function genderFor(name){
+  var g = guessGenderFromFirstName(name);
+  if(g) return g;
+  if(!name) return 'man';
+  var s=String(name); var h=0;
+  for(var i=0;i<s.length;i++) h=(h*31+s.charCodeAt(i))|0;
+  return (Math.abs(h)&1)?'man':'woman';
+}
+// Confident first-name → ethnicity. Synthetic data — we own the call.
+var NAMES_SOUTH_ASIAN_C=new Set(['Raj','Anil','Rohan','Vikram','Arjun','Sanjay','Ravi','Krishna','Pradeep','Sunil','Amit','Deepak','Ashok','Manoj','Rahul','Vijay','Suresh','Naveen','Anand','Nikhil','Aditya','Karan','Rajesh','Priya','Anjali','Neha','Kavya','Pooja','Divya','Meera','Lakshmi','Rani','Asha','Saanvi','Aanya','Aaradhya','Shreya','Riya','Tanvi','Ishita','Aarav','Ishaan','Shivani']);
+var NAMES_EAST_ASIAN_C=new Set(['Wei','Mei','Yi','Jin','Chen','Lin','Liu','Wang','Zhang','Yang','Wu','Zhao','Sun','Hiroshi','Yuki','Akira','Kenji','Sakura','Aiko','Haruto','Sora','Hyun','Eun','Yoon','Kai','Long','Hong','Xiu','Lan','Hua','Hao','Tao','Bao','Cheng','Feng','Jian','Dong','Bin','Min','Lei','Hui','Yu','Xin','Ying','Zhen','Yuan','Yan']);
+var NAMES_HISPANIC_C=new Set(['Carmen','Carlos','Maria','Diego','Hector','Jorge','Julio','Manuel','Miguel','Pedro','Raul','Ricardo','Roberto','Sergio','Antonio','Esperanza','Luz','Sofia','Lucia','Isabella','Camila','Valentina','Mariana','Elena','Rosa','Catalina','Esteban','Fernando','Eduardo','Javier','Alejandro','Andres','Mateo','Santiago','Sebastian','Emilio','Tomas','Cristina','Daniela','Gabriela','Ximena','Adriana','Beatriz','Pilar','Mercedes','Xavier','Marisol','Guadalupe','Lupita','Inez','Itzel','Yesenia','Joaquin','Ignacio','Rafael','Salvador','Cesar','Arturo','Armando','Hugo','Marco','Alejandra','Felipe','Gerardo','Jaime','Leonardo','Luis','Pablo','Ramon']);
+var NAMES_BLACK_C=new Set(['DeShawn','Jamal','Aisha','Latoya','Tyrone','Malik','Imani','Keisha','Tariq','Lakisha','Kenya','Tamika','Andre','Marcus','Demetrius','Jermaine','Reggie','Tyrese','Darius','Trevon','Kareem','Damon','Jalen','Jaylen','Dwayne','DaQuan','Aaliyah','Kiara','Janelle','Jasmine','Tanisha','Maurice','Tyrell','Kwame','Khalil','Terrell','Cedric','Nia','Zuri','Jada','Ebony','Dominique']);
+var NAMES_MIDDLE_EASTERN_C=new Set(['Layla','Omar','Khalid','Fatima','Yasmin','Hassan','Hussein','Ahmed','Mohamed','Mohammed','Ali','Karim','Yusuf','Yara','Nadia','Zainab','Rania','Samira','Mariam','Salma','Ibrahim','Mahmoud','Saif','Anwar','Bilal','Faisal','Hamza','Imran','Sami','Wael','Zaid','Amira','Iman','Lina','Mona','Noor','Rana','Soha','Zara']);
+function guessEthnicityFromFirstName(n){
+  if(!n) return 'caucasian';
+  var clean=n.replace(/[^A-Za-z]/g,''); if(!clean) return 'caucasian';
+  var c=clean[0].toUpperCase()+clean.slice(1).toLowerCase();
+  if(NAMES_MIDDLE_EASTERN_C.has(c)) return 'middle_eastern';
+  if(NAMES_BLACK_C.has(c)) return 'black';
+  if(NAMES_HISPANIC_C.has(c)) return 'hispanic';
+  if(NAMES_SOUTH_ASIAN_C.has(c)) return 'south_asian';
+  if(NAMES_EAST_ASIAN_C.has(c)) return 'east_asian';
+  return 'caucasian';
+}
+
+function workerRow(name, role, detail, opts){
+  opts = opts || {};
+  var band = roleBand(role||'');
+  var w = el('div','worker');
+  if(band.band) w.dataset.roleBand = band.band;
+  var initials = (name||'?').split(' ').map(function(s){return (s[0]||'').toUpperCase()}).join('').substring(0,2);
+  var av = el('div','av',initials);
+  // Real synthetic headshot via /headshots/<key>; deterministic so
+  // same worker always gets the same face. Falls back to monogram if
+  // pool isn't fetched yet.
+  var faceKey = (opts.face_key) || name || '';
+  var firstName = (name||'').split(/\s+/)[0]||'';
+  var gHint = genderFor(firstName);
+  var eHint = guessEthnicityFromFirstName(firstName);
+  if(faceKey){
+    var img=document.createElement('img');
+    img.alt='';
+    img.loading='lazy';
+    img.src = P + '/headshots/' + encodeURIComponent(faceKey) + '?g='+gHint+'&e='+eHint;
+    img.onerror=function(){ this.remove(); };
+    av.appendChild(img);
+  }
+  w.appendChild(av);
+  var info = el('div','info');
+  var nm = el('div','nm', name||'?');
+  if(opts.endorsed){
+    nm.appendChild(el('span','boost-chip',opts.endorsed));
+  }
+  info.appendChild(nm);
+  var why = el('div','why');
+  if(band.label){
+    var pill = document.createElement('span'); pill.className='role-pill';
+    pill.dataset.rb = band.band;
+    pill.textContent = band.label;
+    why.appendChild(pill);
+  }
+  why.appendChild(document.createTextNode(detail||''));
+  info.appendChild(why);
+  w.appendChild(info);
+  if(opts.score){
+    w.appendChild(el('div','score', opts.score));
+  }
+  return w;
+}
+
 function el(tag, cls, text){
   var e=document.createElement(tag);
   if(cls) e.className=cls;
@@ -380,21 +500,13 @@ function loadChapter4(){
 
     var list=document.createElement('div');list.style.marginTop='6px';
     (prop.candidates||[]).slice(0,5).forEach(function(cand,i){
-      var w=el('div','worker');
+      var detail = cand.doc_id+' · '+(cand.playbook_boost>0?'boosted +'+cand.playbook_boost.toFixed(3)+' by memory · ':'')+'semantic score '+(cand.score||0).toFixed(3);
-      var initials=(cand.name||'?').split(' ').map(function(s){return (s[0]||'').toUpperCase()}).join('').substring(0,2);
+      var endorsed = (cand.playbook_boost||0) > 0
-      w.appendChild(el('div','av',initials));
+        ? 'Endorsed · '+((cand.playbook_citations||[]).length)+' past fill'+((cand.playbook_citations||[]).length!==1?'s':'')
-      var info=el('div','info');
+        : null;
-      var nm=el('div','nm',cand.name||cand.doc_id||'?');
+      list.appendChild(workerRow(cand.name||cand.doc_id||'?', prop.role||'', detail, {
-      if((cand.playbook_boost||0)>0){
+        endorsed: endorsed, score: '#'+(i+1)
-        var ncit=(cand.playbook_citations||[]).length;
+      }));
-        nm.appendChild(el('span','boost-chip','Endorsed · '+ncit+' past fill'+(ncit!==1?'s':'')));
-      }
-      info.appendChild(nm);
-      var why=cand.doc_id+' · '+(cand.playbook_boost>0?'boosted +'+cand.playbook_boost.toFixed(3)+' by memory · ':'')+'semantic score '+(cand.score||0).toFixed(3);
-      info.appendChild(el('div','why',why));
-      w.appendChild(info);
-      w.appendChild(el('div','score','#'+(i+1)));
-      list.appendChild(w);
     });
     card.appendChild(list);
 
@@ -628,12 +740,8 @@ function loadChapter8(){
       bfHdr.textContent='✓ '+d.backfills.length+' local '+(d.worker.role||'workers')+' available — sorted by responsiveness';
       host.appendChild(bfHdr);
       d.backfills.slice(0,5).forEach(function(c){
-        var row=el('div','row');
+        var detail=(c.role||'?')+' · '+(c.city||'')+', '+(c.state||'')+' · rel '+Math.round((c.rel||0)*100)+'% · resp '+Math.round((c.resp||0)*100)+'%';
-        var left=document.createElement('div');left.style.flex='1';left.style.minWidth='0';
+        host.appendChild(workerRow(c.name||'?', c.role||'', detail));
-        left.appendChild(el('div','title',c.name));
-        left.appendChild(el('div','meta',(c.role||'?')+' · '+(c.city||'')+', '+(c.state||'')+' · rel '+Math.round((c.rel||0)*100)+'% · resp '+Math.round((c.resp||0)*100)+'%'));
-        row.appendChild(left);
-        host.appendChild(row);
       });
     }
     var narr=el('div','narr');
@@ -675,23 +783,16 @@ function runTry(){
 
     var workers=d.sql_results||d.vector_results||d.results||[];
     workers.slice(0,5).forEach(function(w,i){
-      var row=el('div','worker');
       var nm=w.name||(w.text||'').split('—')[0].trim()||w.doc_id||'?';
-      var initials=nm.split(' ').map(function(s){return (s[0]||'').toUpperCase()}).join('').substring(0,2);
-      row.appendChild(el('div','av',initials));
-      var info=el('div','info');
-      var n=el('div','nm',nm);
-      if((w.playbook_boost||0)>0){
-        n.appendChild(el('span','boost-chip','Endorsed · '+((w.playbook_citations||[]).length||'?')+' past fill(s)'));
-      }
-      info.appendChild(n);
       var bits=[];
       if(w.role) bits.push(w.role);
       if(w.city&&w.state) bits.push(w.city+', '+w.state);
       if(w.rel!==undefined) bits.push('reliability '+Math.round(w.rel*100)+'%');
       if(w.avail!==undefined) bits.push('availability '+Math.round(w.avail*100)+'%');
-      info.appendChild(el('div','why',bits.join(' · ')||'AI semantic match'));
+      var endorsed = (w.playbook_boost||0) > 0
-      row.appendChild(info);
+        ? 'Endorsed · '+((w.playbook_citations||[]).length||'?')+' past fill(s)'
+        : null;
+      var row = workerRow(nm, w.role||'', bits.join(' · ')||'AI semantic match', { endorsed: endorsed });
       row.appendChild(el('div','score','#'+(i+1)));
       card.appendChild(row);
     });

mcp-server/index.ts

@@ -1225,6 +1225,78 @@ async function main() {
         // OSHA national, Chicago history, ticker chart, parent link,
         // federal contracts, debarment, unions, training. Click any
         // contractor name in a permit Entity Brief to land here.
+        // Headshot pool — synthetic StyleGAN faces from
+        // thispersondoesnotexist.com fetched offline by
+        // scripts/staffing/fetch_face_pool.py. Deterministic mapping:
+        // hash(worker key) → pool index → image bytes. Same key always
+        // gets the same face; different keys spread evenly.
+        //
+        // Optional gender hint: ?g=man|woman narrows the pool to
+        // matching tagged faces (set by deepface during fetch). Falls
+        // back to whole pool if no matches.
+        if (url.pathname.startsWith("/headshots/") && req.method === "GET") {
+          const key = decodeURIComponent(url.pathname.slice("/headshots/".length));
+          const wantGender = url.searchParams.get("g") || "";
+          if (!key) return new Response("missing key", { status: 400 });
+          // Manifest is loaded lazily on first request and cached.
+          // Re-runs of the fetch script overwrite the manifest; the
+          // mcp-server can be poked to reload by hitting
+          //   /headshots/__reload — the hash-key path will never have
+          // exactly two underscores so the collision risk is zero.
+          const HEADSHOT_DIR = "/home/profit/lakehouse/data/headshots";
+          if (key === "__reload" || !(globalThis as any)._faces) {
+            try {
+              const raw = await Bun.file(`${HEADSHOT_DIR}/manifest.jsonl`).text();
+              const lines = raw.trim().split("\n").filter(Boolean);
+              const all = lines.map((l) => JSON.parse(l));
+              (globalThis as any)._faces = {
+                all,
+                man: all.filter((r: any) => r.gender === "man"),
+                woman: all.filter((r: any) => r.gender === "woman"),
+                untagged: all.filter((r: any) => !r.gender || (r.gender !== "man" && r.gender !== "woman")),
+                loaded_at: Date.now(),
+              };
+              if (key === "__reload") {
+                return Response.json({
+                  reloaded: true,
+                  total: all.length,
+                  man: (globalThis as any)._faces.man.length,
+                  woman: (globalThis as any)._faces.woman.length,
+                  untagged: (globalThis as any)._faces.untagged.length,
+                });
+              }
+            } catch (e: any) {
+              return new Response(`face pool not available: ${e.message}. Run scripts/staffing/fetch_face_pool.py first.`, { status: 503 });
+            }
+          }
+          const F = (globalThis as any)._faces as { all: any[]; man: any[]; woman: any[]; untagged: any[] };
+          if (!F || !F.all.length) {
+            return new Response("face pool empty", { status: 503 });
+          }
+          // Pool selection: gender hint > full pool. If no gender match,
+          // fall back to the full pool so the worker still gets a face.
+          let pool = F.all;
+          if (wantGender === "man" && F.man.length) pool = F.man;
+          else if (wantGender === "woman" && F.woman.length) pool = F.woman;
+          // Hash key → pool index. djb2-ish, fits any string.
+          let h = 5381;
+          for (let i = 0; i < key.length; i++) h = ((h << 5) + h + key.charCodeAt(i)) | 0;
+          const idx = Math.abs(h) % pool.length;
+          const pick = pool[idx];
+          const file = Bun.file(`${HEADSHOT_DIR}/${pick.file}`);
+          if (!(await file.exists())) {
+            return new Response("face missing on disk", { status: 404 });
+          }
+          return new Response(file, {
+            headers: {
+              "Content-Type": "image/jpeg",
+              "Cache-Control": "public, max-age=86400, immutable",
+              "X-Face-Pool-Idx": String(pick.id),
+              "X-Face-Pool-Gender": pick.gender || "untagged",
+            },
+          });
+        }
+
         // Profiler index — directory page of everyone who's filed a
         // Chicago permit (clickable directory of contractors).
         if (url.pathname === "/profiler" || url.pathname === "/contractors") {

mcp-server/search.html

@@ -48,7 +48,19 @@ body{font-family:'Inter',-apple-system,system-ui,'Segoe UI',sans-serif;backgroun
 /* Workers */
 .iworker{display:flex;align-items:center;gap:12px;padding:10px 12px;background:#161b22;border-radius:8px;margin-bottom:4px;transition:background 0.15s}
 .iworker:hover{background:#1c2333}
-.iworker .av{width:36px;height:36px;border-radius:8px;display:flex;align-items:center;justify-content:center;font-weight:600;font-size:12px;color:#e6edf3;flex-shrink:0}
+.iworker .av{width:40px;height:40px;border-radius:50%;display:flex;align-items:center;justify-content:center;font-weight:600;font-size:13px;color:#c9d1d9;flex-shrink:0;background:#161b22;border:1px solid #21262d;letter-spacing:0.5px;font-family:'Inter',-apple-system,sans-serif;overflow:hidden;position:relative}
+.iworker .av img{position:absolute;inset:0;width:100%;height:100%;object-fit:cover;display:block}
+.iworker .role-pill{display:inline-block;font-size:10px;padding:2px 8px;border-radius:3px;background:#0d1117;color:#8b949e;margin-right:8px;font-weight:600;letter-spacing:0.4px;text-transform:uppercase;border-left:2px solid #30363d}
+.iworker[data-role-band="warehouse"]{border-left:3px solid #58a6ff}
+.iworker[data-role-band="production"]{border-left:3px solid #d29922}
+.iworker[data-role-band="trades"]{border-left:3px solid #bc8cff}
+.iworker[data-role-band="driver"]{border-left:3px solid #3fb950}
+.iworker[data-role-band="lead"]{border-left:3px solid #f0883e}
+.iworker .role-pill[data-rb="warehouse"]{border-left-color:#58a6ff;color:#79c0ff}
+.iworker .role-pill[data-rb="production"]{border-left-color:#d29922;color:#e3b341}
+.iworker .role-pill[data-rb="trades"]{border-left-color:#bc8cff;color:#d2a8ff}
+.iworker .role-pill[data-rb="driver"]{border-left-color:#3fb950;color:#56d364}
+.iworker .role-pill[data-rb="lead"]{border-left-color:#f0883e;color:#ffa657}
 .iworker .info{flex:1;min-width:0}
 .iworker .nm{font-weight:600;color:#e6edf3;font-size:13px}
 .iworker .detail{color:#545d68;font-size:11px}
@@ -2249,6 +2261,114 @@ function addBigMeter(parent,label,val,desc){
   d.appendChild(lb);d.appendChild(row);d.appendChild(ds);parent.appendChild(d);
 }
 
+// First-name → gender hint for face-pool selection. Built from the
+// most common 200 US given names. Lookup is best-effort — undefined
+// returns means "no hint, draw from full pool." Don't surface this
+// anywhere user-visible; it's purely a face-pool selector.
+var FEMALE_NAMES = new Set(['Mary','Patricia','Jennifer','Linda','Elizabeth','Barbara','Susan','Jessica','Sarah','Karen','Lisa','Nancy','Betty','Sandra','Margaret','Ashley','Kimberly','Emily','Donna','Michelle','Carol','Amanda','Melissa','Deborah','Stephanie','Dorothy','Rebecca','Sharon','Laura','Cynthia','Amy','Kathleen','Angela','Shirley','Brenda','Emma','Anna','Pamela','Nicole','Samantha','Katherine','Christine','Helen','Debra','Rachel','Carolyn','Janet','Maria','Catherine','Heather','Diane','Olivia','Julie','Joyce','Victoria','Ruth','Virginia','Lauren','Kelly','Christina','Joan','Evelyn','Judith','Andrea','Hannah','Megan','Cheryl','Jacqueline','Martha','Madison','Teresa','Gloria','Sara','Janice','Ann','Kathryn','Abigail','Sophia','Frances','Jean','Alice','Judy','Isabella','Julia','Grace','Amber','Denise','Danielle','Marilyn','Beverly','Charlotte','Natalie','Theresa','Diana','Brittany','Doris','Kayla','Alexis','Lori','Marie','Carmen','Aisha','Rosa','Kim','Mia','Audrey','Erin','Tina','Vanessa','Tara','Wendy','Tanya','Maya','Crystal','Yvonne','Kara','Shannon','Brianna','Faith','Caroline','Carla','Tracey','Tracy','Rita','Dawn','Tiffany','Stacy','Stacey','Gina','Bonnie','Tammy','Joanne','Jamie','Tonya','Alyssa','Ariana','Elena','Ellie','Erica','Erika','Felicia','Holly','Jenna','Jenny','Krista','Kristen','Kristin','Krystal','Lana','Leah','Lucy','Mallory','Melinda','Meredith','Misty','Monica','Mya','Naomi','Paige','Patrice','Paula','Renee','Rhonda','Robin','Roxanne','Sadie','Selena','Shari','Shauna','Sierra','Skylar','Sonia','Stella','Tamara','Taryn','Trina','Veronica','Vivian','Whitney','Yolanda','Zoe','Lakeisha','Latoya','Tasha',
+  // Hispanic female
+  'Esperanza','Luz','Lucia','Camila','Valentina','Mariana','Catalina','Cristina','Daniela','Gabriela','Ximena','Adriana','Beatriz','Pilar','Consuelo','Dolores','Mercedes','Marisol','Guadalupe','Lupita','Inez','Itzel','Yesenia','Monserrat','Renata','Alejandra','Alma','Belen','Blanca','Esmeralda','Imelda','Lourdes','Magdalena','Olga','Refugio','Rocio','Susana','Anita','Fatima',
+  // South Asian female
+  'Priya','Anjali','Neha','Kavya','Pooja','Divya','Meera','Lakshmi','Rani','Asha','Saanvi','Aanya','Aaradhya','Shreya','Riya','Tanvi','Ishita','Shivani','Padma','Sita','Geeta','Rekha','Amira',
+  // East Asian female
+  'Mei','Sakura','Aiko','Sora','Chiyo','Hana','Eun','Xiu','Lan','Hua','Min','Xin','Ying','Zhen','Yan',
+  // Black female (additional)
+  'Imani','Keisha','Lakisha','Kenya','Tamika','Latanya','Latrice','Aaliyah','Kiara','Janelle','Jasmine','Tanisha','Maliyah','Imari','Nia','Zuri','Talia','Jada','Ebony','Dominique',
+  // Middle Eastern female
+  'Layla','Yasmin','Yara','Nadia','Zainab','Rania','Samira','Mariam','Salma','Dunia','Iman','Lina','Mona','Noor','Rana','Sabrina','Soha','Zara'
+]);
+var MALE_NAMES = new Set(['James','Robert','John','Michael','David','William','Richard','Joseph','Thomas','Charles','Christopher','Daniel','Matthew','Anthony','Mark','Donald','Steven','Paul','Andrew','Joshua','Kenneth','Kevin','Brian','George','Edward','Ronald','Timothy','Jason','Jeffrey','Ryan','Jacob','Gary','Nicholas','Eric','Jonathan','Stephen','Larry','Justin','Scott','Brandon','Benjamin','Samuel','Gregory','Frank','Alexander','Raymond','Patrick','Jack','Dennis','Jerry','Tyler','Aaron','Jose','Adam','Henry','Nathan','Douglas','Zachary','Peter','Kyle','Walter','Ethan','Jeremy','Harold','Keith','Christian','Roger','Noah','Gerald','Carl','Terry','Sean','Austin','Arthur','Lawrence','Jesse','Dylan','Bryan','Joe','Jordan','Billy','Bruce','Albert','Willie','Gabriel','Logan','Alan','Juan','Wayne','Roy','Ralph','Randy','Eugene','Vincent','Russell','Elijah','Louis','Bobby','Philip','Johnny','Marcus','Antonio','Carlos','Diego','Hector','Jorge','Julio','Manuel','Miguel','Pedro','Raul','Ricardo','Roberto','Sergio','Victor','Jamal','Xavier','DeShawn','Dwayne','Jermaine','Malik','Tyrone','Devon','Andre','Anwar','Brent','Calvin','Casey','Cody','Cole','Cory','Curt','Dale','Damon','Darius','Darrell','Dean','Derek','Donnie','Drew','Earl','Eddie','Floyd','Glenn','Greg','Howard','Ivan','Jared','Jay','Jeff','Joel','Johnnie','Lance','Lee','Leonard','Lloyd','Mario','Martin','Mason','Maurice','Max','Mitchell','Morgan','Nick','Norman','Oliver','Owen','Pete','Quincy','Rafael','Reggie','Rex','Ricky','Rod','Russ','Salvatore','Shane','Shaun','Stanley','Steve','Theodore','Todd','Travis','Trevor','Troy','Wade','Warren','Wesley',
+  // Hispanic male
+  'Alejandro','Andres','Mateo','Santiago','Sebastian','Emilio','Tomas','Joaquin','Ignacio','Salvador','Cesar','Arturo','Armando','Hugo','Marco','Felipe','Gerardo','Jaime','Leonardo','Luis','Pablo','Ramon','Reynaldo','Vincente','Javier','Esteban','Eduardo','Fernando','Humberto','Ernestino','Cristian','Hernan',
+  // South Asian male
+  'Raj','Anil','Rohan','Vikram','Arjun','Sanjay','Ravi','Krishna','Pradeep','Sunil','Amit','Deepak','Ashok','Manoj','Rahul','Vijay','Suresh','Naveen','Anand','Nikhil','Aditya','Karan','Rajesh','Ramesh','Kishore','Mohan','Ajay','Aarav','Ishaan',
+  // East Asian male
+  'Wei','Yi','Jin','Hiroshi','Akira','Kenji','Haruto','Hyun','Yoon','Kai','Long','Hong','Hao','Tao','Bao','Cheng','Feng','Qiang','Jian','Dong','Bin','Lei','Hui','Yu','Yuan',
+  // Black male (additional)
+  'Demetrius','Tyrese','Trevon','Kareem','DaQuan','Tyrell','Kwame','Khalil','Rashid','Terrell','Chauncey','Cedric','Imari','Jalen','Jaylen',
+  // Middle Eastern male
+  'Omar','Khalid','Hassan','Hussein','Ahmed','Mohamed','Mohammed','Ali','Karim','Yusuf','Ibrahim','Mahmoud','Saif','Bilal','Faisal','Hamza','Imran','Sami','Wael','Yasin','Zaid'
+]);
+function guessGenderFromFirstName(name){
+  if(!name) return null;
+  var clean = name.replace(/[^A-Za-z]/g,'');
+  if(!clean) return null;
+  // Title-case
+  var c = clean[0].toUpperCase() + clean.slice(1).toLowerCase();
+  if(FEMALE_NAMES.has(c)) return 'woman';
+  if(MALE_NAMES.has(c)) return 'man';
+  return null;
+}
+
+// First-name → ethnicity hint. The synthetic-data generator built
+// workers_500k from a multi-cultural name pool (Raj, DeShawn, Jamal,
+// Mei, Wei, Carmen, Esperanza, Aisha, etc.). The hint is used ONLY
+// to bias face-pool selection toward visually-aligned StyleGAN faces;
+// it never surfaces in any worker-facing label or report. Buckets
+// match common deepface "race" categories so the pool tags align
+// when deepface is later run over the headshot pool.
+var NAMES_SOUTH_ASIAN = new Set(['Raj','Anil','Rohan','Vikram','Arjun','Sanjay','Ravi','Krishna','Pradeep','Sunil','Amit','Deepak','Ashok','Manoj','Rahul','Vijay','Suresh','Naveen','Anand','Nikhil','Aditya','Karan','Rajesh','Ramesh','Kishore','Mohan','Ajay','Priya','Anjali','Neha','Kavya','Pooja','Divya','Meera','Lakshmi','Rani','Asha','Saanvi','Aanya','Aaradhya','Shreya','Riya','Tanvi','Ishita','Aarav','Ishaan','Shivani','Padma','Sita','Geeta','Rekha']);
+var NAMES_EAST_ASIAN = new Set(['Wei','Mei','Yi','Jin','Chen','Lin','Liu','Wang','Zhang','Yang','Wu','Zhao','Sun','Hiroshi','Yuki','Akira','Kenji','Sakura','Aiko','Haruto','Sora','Chiyo','Hana','Hyun','Eun','Yoon','Kai','Long','Hong','Xiu','Lan','Hua','Hao','Tao','Bao','Cheng','Feng','Qiang','Jian','Dong','Bin','Min','Lei','Hui','Yu','Xin','Ying','Zhen','Yuan','Yan']);
+var NAMES_HISPANIC = new Set(['Carmen','Carlos','Maria','Diego','Hector','Jorge','Julio','Manuel','Miguel','Pedro','Raul','Ricardo','Roberto','Sergio','Antonio','Esperanza','Luz','Sofia','Lucia','Isabella','Camila','Valentina','Mariana','Elena','Rosa','Catalina','Esteban','Fernando','Eduardo','Javier','Alejandro','Andres','Mateo','Santiago','Sebastian','Emilio','Tomas','Cristina','Daniela','Gabriela','Ximena','Adriana','Beatriz','Pilar','Consuelo','Dolores','Mercedes','Xavier','Marisol','Guadalupe','Lupita','Inez','Itzel','Yolanda','Yesenia','Monserrat','Renata','Ximena','Joaquin','Ignacio','Rafael','Salvador','Cesar','Arturo','Armando','Hugo','Marco','Alejandra','Alma','Belen','Blanca','Esmeralda','Fatima','Gloria','Imelda','Lourdes','Magdalena','Olga','Paula','Refugio','Rocio','Susana','Teresa','Veronica','Anita','Ernestino','Felipe','Gerardo','Humberto','Jaime','Leonardo','Luis','Pablo','Ramon','Reynaldo','Vincente']);
+var NAMES_BLACK = new Set(['DeShawn','Jamal','Aisha','Latoya','Tyrone','Malik','Imani','Keisha','Tariq','Lakisha','Kenya','Tamika','Shaquille','Andre','Marcus','Demetrius','Jermaine','Reggie','Tyrese','Darius','Trevon','Kareem','Damon','Jalen','Jaylen','Dwayne','DaQuan','Latanya','Latrice','Aaliyah','Kiara','Janelle','Jasmine','Tanisha','Yolanda','Maurice','Tyrell','Kwame','Khalil','Rashid','Terrell','Chauncey','Cedric','Maliyah','Imari','Nia','Zuri','Talia','Jada','Ebony','Dominique']);
+var NAMES_MIDDLE_EASTERN = new Set(['Layla','Omar','Khalid','Fatima','Yasmin','Hassan','Hussein','Ahmed','Mohamed','Mohammed','Ali','Karim','Yusuf','Yara','Nadia','Zainab','Rania','Samira','Mariam','Salma','Ibrahim','Mahmoud','Saif','Anwar','Bilal','Faisal','Hamza','Imran','Jamal','Rashid','Sami','Tariq','Wael','Yasin','Zaid','Amira','Dunia','Iman','Lina','Mona','Noor','Rana','Sabrina','Soha','Yara','Zara']);
+function guessEthnicityFromFirstName(name){
+  if(!name) return 'caucasian';
+  var clean = name.replace(/[^A-Za-z]/g,'');
+  if(!clean) return 'caucasian';
+  var c = clean[0].toUpperCase() + clean.slice(1).toLowerCase();
+  // Order matters where names overlap. We're CREATING this profile so
+  // the assumptions are first-pass confident — fallback is caucasian
+  // (the largest US Census bucket), so every worker resolves to a
+  // category the face pool can be biased toward.
+  if(NAMES_MIDDLE_EASTERN.has(c)) return 'middle_eastern';
+  if(NAMES_BLACK.has(c)) return 'black';
+  if(NAMES_HISPANIC.has(c)) return 'hispanic';
+  if(NAMES_SOUTH_ASIAN.has(c)) return 'south_asian';
+  if(NAMES_EAST_ASIAN.has(c)) return 'east_asian';
+  return 'caucasian';
+}
+// Forced-confident gender resolver — defaults to a deterministic guess
+// when the name table doesn't match, rather than leaving "unknown."
+// We're authoring the synthetic data; we own the confidence call.
+function genderFor(name){
+  var g = guessGenderFromFirstName(name);
+  if(g) return g;
+  if(!name) return 'man';
+  // hash-based fallback so unknown names still spread roughly 50/50
+  var s = String(name);
+  var h = 0; for (var i=0;i<s.length;i++) h = (h*31 + s.charCodeAt(i))|0;
+  return (Math.abs(h) & 1) ? 'man' : 'woman';
+}
+
+// Role classification — sober, no illustrations. Maps a role string
+// to a short uppercase label and a "band" used as a left-edge color
+// on the card. Five bands cover the warehouse/manufacturing surface;
+// the band controls the left border on .iworker and on the role pill.
+// No emojis — staffer-readable, professional. Add bands here when
+// new role families appear in the data.
+var ROLE_BANDS = [
+  { match: /forklift|warehouse|associate|material\s*handler|loader|loading|packag|shipping|logistics|inventory|sanitation|janit/i,
+    band: 'warehouse', label: 'Warehouse' },
+  { match: /production|assembl/i,
+    band: 'production', label: 'Production' },
+  { match: /welder|weld|electric|maint(enance)?\s*tech|cnc|machine\s*op|hvac|plumb|carpenter|mason/i,
+    band: 'trades', label: 'Skilled Trade' },
+  { match: /driver|truck|haul|cdl/i,
+    band: 'driver', label: 'Driver' },
+  { match: /line\s*lead|supervisor|foreman|coordinator/i,
+    band: 'lead', label: 'Lead' },
+  { match: /quality/i,
+    band: 'production', label: 'Quality' },
+];
+function roleBand(role){
+  if(!role) return { band: 'warehouse', label: '' };
+  for (var i = 0; i < ROLE_BANDS.length; i++) {
+    if (ROLE_BANDS[i].match.test(role)) return ROLE_BANDS[i];
+  }
+  return { band: 'warehouse', label: role.split(' ')[0].toUpperCase().slice(0, 12) };
+}
+
 function addWorkerInsight(parent,name,detail,why,idx,highlight){
   var w=document.createElement('div');w.className='iworker';
   if(highlight)w.style.borderLeft='3px solid '+highlight;
@@ -2256,8 +2376,33 @@ function addWorkerInsight(parent,name,detail,why,idx,highlight){
   var workerDataRef=arguments[6]||null; // passed as 7th arg
   var boostInfo=arguments[7]||null;     // {boost, citations} — Phase 19
   w.onclick=function(){if(workerDataRef)showProfile(workerDataRef)};
-  var av=document.createElement('div');av.className='av';av.style.background=AC[(idx||0)%AC.length];
+  // Avatar: monogram initials underneath, real synthetic headshot on
+  // top via /headshots/<key>. Same key → same face by deterministic
+  // hash. If the image fails to load (face pool not yet fetched, CDN
+  // blocked, etc.), the monogram remains visible.
+  var av=document.createElement('div');av.className='av';
+  var role = (workerDataRef && workerDataRef.role) || (detail||'').split(' · ')[0] || '';
+  var band = roleBand(role);
+  if(band.band) w.dataset.roleBand = band.band;
   av.textContent=(name||'?').split(' ').map(function(n){return(n[0]||'').toUpperCase()}).join('').substring(0,2);
+  // Layer the headshot on top. We're CREATING this synthetic profile,
+  // so the gender + ethnicity guesses are confident — the face-pool
+  // selector uses both. Once deepface tags the pool the server will
+  // narrow accordingly; until then it falls back to the full pool but
+  // the URL shape is forward-compatible.
+  var faceKey = (workerDataRef && (workerDataRef.candidate_id || workerDataRef.doc_id)) || name || '';
+  var firstName = (name||'').split(/\s+/)[0]||'';
+  var gHint = genderFor(firstName);
+  var eHint = guessEthnicityFromFirstName(firstName);
+  if(faceKey){
+    var img=document.createElement('img');
+    img.alt='';
+    img.loading='lazy';
+    var qs = '?g=' + gHint + '&e=' + eHint;
+    img.src = P + '/headshots/' + encodeURIComponent(faceKey) + qs;
+    img.onerror=function(){ this.remove(); };
+    av.appendChild(img);
+  }
   w.appendChild(av);
   var info=document.createElement('div');info.className='info';
   var nm=document.createElement('div');nm.className='nm';nm.textContent=name;
@@ -2292,7 +2437,17 @@ function addWorkerInsight(parent,name,detail,why,idx,highlight){
       chip.title=name+' — endorsed in '+n+' playbook'+(n!==1?'s':'');
     });
   }
-  var dt=document.createElement('div');dt.className='detail';dt.textContent=detail;
+  // Detail line. Lead with a small uppercase pill that classifies the
+  // role family — color matches the card's left-edge band so the eye
+  // groups by role family at a glance. No icons.
+  var dt=document.createElement('div');dt.className='detail';
+  if(band.label){
+    var pill=document.createElement('span'); pill.className='role-pill';
+    pill.dataset.rb = band.band;
+    pill.textContent = band.label;
+    dt.appendChild(pill);
+  }
+  dt.appendChild(document.createTextNode(detail));
   info.appendChild(nm);info.appendChild(dt);
   if(why){var wh=document.createElement('div');wh.className='why';wh.textContent=why;info.appendChild(wh)}
   w.appendChild(info);

scripts/staffing/fetch_face_pool.py

@@ -0,0 +1,161 @@
+#!/usr/bin/env python3
+"""
+fetch_face_pool.py — pull N synthetic headshots from
+https://thispersondoesnotexist.com/, write to data/headshots/face_NNNN.jpg,
+optionally tag each with gender via deepface, emit a JSONL manifest.
+
+Each fetch is a fresh StyleGAN face — no real people. Deterministic per
+worker mapping happens at serve time (mcp-server hashes the worker key
+into the pool); this script just builds the pool.
+
+Usage:
+    python3 scripts/staffing/fetch_face_pool.py --count 300 --concurrency 3
+    python3 scripts/staffing/fetch_face_pool.py --count 50  --no-gender
+
+Re-running is idempotent: existing face_NNNN.jpg files are skipped, and
+the manifest is rewritten from disk state.
+"""
+from __future__ import annotations
+import argparse
+import hashlib
+import json
+import os
+import sys
+import time
+from concurrent.futures import ThreadPoolExecutor, as_completed
+
+import urllib.request
+import urllib.error
+
+URL = "https://thispersondoesnotexist.com/"
+UA = "Lakehouse/1.0 (face-pool fetch · synthetic-only · no real-person tracking)"
+
+
+def fetch_one(idx: int, out_dir: str) -> tuple[int, str, bool, str | None]:
+    """Returns (idx, basename, cached, error)."""
+    fname = f"face_{idx:04d}.jpg"
+    full = os.path.join(out_dir, fname)
+    if os.path.exists(full) and os.path.getsize(full) > 1024:
+        return idx, fname, True, None
+    try:
+        req = urllib.request.Request(URL, headers={"User-Agent": UA})
+        with urllib.request.urlopen(req, timeout=20) as resp:
+            blob = resp.read()
+        if len(blob) < 1024:
+            return idx, fname, False, f"response too small ({len(blob)} bytes)"
+        with open(full, "wb") as f:
+            f.write(blob)
+        return idx, fname, False, None
+    except urllib.error.URLError as e:
+        return idx, fname, False, f"urlerror: {e}"
+    except Exception as e:
+        return idx, fname, False, f"{type(e).__name__}: {e}"
+
+
+def maybe_tag_gender(records: list[dict], out_dir: str) -> dict[str, int]:
+    """If deepface is installed, label each record with gender. Returns
+    a count summary; mutates records in place. On import error, returns
+    None and tags every record as unknown."""
+    try:
+        from deepface import DeepFace  # type: ignore
+    except Exception as e:
+        print(f"  (deepface unavailable: {e}) — pool will mix naturally")
+        for r in records:
+            r["gender"] = None
+        return {"unknown": len(records)}
+
+    print("  tagging gender via deepface (CPU; ~0.5-1s per face)…")
+    counts: dict[str, int] = {}
+    for i, r in enumerate(records):
+        full = os.path.join(out_dir, r["file"])
+        try:
+            ana = DeepFace.analyze(
+                img_path=full,
+                actions=["gender"],
+                enforce_detection=False,
+                silent=True,
+            )
+            if isinstance(ana, list):
+                ana = ana[0] if ana else {}
+            g_raw = (ana.get("dominant_gender") or "").lower().strip()
+            r["gender"] = (
+                "man" if g_raw.startswith("man") else
+                "woman" if g_raw.startswith("woman") else
+                None
+            )
+        except Exception as e:
+            r["gender"] = None
+            r["gender_error"] = f"{type(e).__name__}: {e}"
+        counts[r["gender"] or "unknown"] = counts.get(r["gender"] or "unknown", 0) + 1
+        if (i + 1) % 25 == 0:
+            print(f"    [{i+1}/{len(records)}] {counts}")
+    return counts
+
+
+def main():
+    p = argparse.ArgumentParser()
+    p.add_argument("--count", type=int, default=300, help="how many faces to maintain in pool")
+    p.add_argument(
+        "--out",
+        default=os.path.join(os.path.dirname(__file__), "..", "..", "data", "headshots"),
+    )
+    p.add_argument("--concurrency", type=int, default=3, help="parallel fetches (be polite)")
+    p.add_argument("--no-gender", action="store_true", help="skip deepface gender tagging")
+    args = p.parse_args()
+
+    out = os.path.realpath(args.out)
+    os.makedirs(out, exist_ok=True)
+
+    print(f"Fetching {args.count} faces → {out}")
+    print(f"Source: {URL} (synthetic StyleGAN — no real people)")
+
+    results: list[dict] = [None] * args.count  # type: ignore
+    t0 = time.time()
+    with ThreadPoolExecutor(max_workers=max(1, args.concurrency)) as ex:
+        futs = {ex.submit(fetch_one, i, out): i for i in range(args.count)}
+        for done, fut in enumerate(as_completed(futs), 1):
+            idx, fname, cached, err = fut.result()
+            results[idx] = {
+                "id": idx,
+                "file": fname,
+                "cached": cached,
+                "error": err,
+            }
+            if done % 25 == 0 or done == args.count:
+                ok = sum(1 for r in results if r and not r.get("error"))
+                print(f"  [{done}/{args.count}] {ok} ok  ({time.time()-t0:.1f}s)")
+
+    # Drop slots that errored or are still None (shouldn't happen)
+    records = [r for r in results if r and not r.get("error")]
+    print(f"\nPool ready: {len(records)} faces, {sum(1 for r in records if r['cached'])} from cache")
+
+    if not args.no_gender and records:
+        print("\nGender-tagging pass:")
+        summary = maybe_tag_gender(records, out)
+        print(f"  distribution: {summary}")
+    else:
+        for r in records:
+            r["gender"] = None
+
+    # Strip transient flags before persisting
+    for r in records:
+        r.pop("cached", None)
+        r.pop("error", None)
+
+    manifest = os.path.join(out, "manifest.jsonl")
+    with open(manifest, "w") as f:
+        for r in records:
+            f.write(json.dumps(r) + "\n")
+    print(f"\nManifest: {manifest}  ({len(records)} entries)")
+
+    # Quick checksum manifest for downstream debugging
+    h = hashlib.sha256()
+    for r in records:
+        h.update(r["file"].encode())
+        h.update(b"|")
+        h.update((r.get("gender") or "?").encode())
+    print(f"Pool fingerprint (sha256): {h.hexdigest()[:16]}")
+
+
+if __name__ == "__main__":
+    main()