feat: auto-accumulating villain dossiers + player lookup (poker B)

Named players in recorded hands now auto-enrich a persistent dossier, and stats
emerge once the sample is big enough — laying groundwork for A.

- poker: player_observations table (per named player per hand: vpip/pfr/saw_flop/
  showed/cards/summary); record_hand auto-links named players via link_hand_players;
  player_profile(name) returns dossier + reads + shown hands, with inferred
  VPIP/PFR/WTSD gated behind MIN_STATS_SAMPLE (12) so thin samples don't lie;
  list_players()
- player_profile tool ("what do I know about X"); thin files return a blunt
  "don't generalize" directive
- persona: she MUST call player_profile before discussing an opponent and answer
  only from it — fixes observed confabulation (she invented a whole read from one
  hand / from memory). Verified: now reports only the real logged hand.
- tests: observation linking, profile, stat-emergence at sample threshold

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

lyra/personas/lyra.md

@@ -103,6 +103,12 @@ inventing a mechanism — same rule as not inventing numbers.
   qualitative read and flag that the exact number needs the calc. Approximate
   reasoning is fine if you label it as approximate.
 - You don't pretend to remember things you don't. If you're not sure, say so.
+- **You don't invent reads on players.** Before you say *anything* about a
+  specific opponent, you MUST call the `player_profile` tool and answer ONLY from
+  what it returns — never from memory, vibes, or generic "player types." If the
+  file is thin or empty, say plainly that you've barely seen them (or have nothing
+  yet) and report just the hand(s) on record. Never fabricate tendencies, stats,
+  or a playing style. A made-up read is worse than "I don't know him yet."
 - You don't moralize about gambling. Brian's a serious player. Meet him there.
 
 ## Right now

lyra/poker.py

@@ -80,8 +80,29 @@ CREATE TABLE IF NOT EXISTS player_reads (
     note TEXT NOT NULL,
     created_at TEXT NOT NULL
 );
+
+-- One row per named player per recorded hand — structured enough to (a) build
+-- their qualitative dossier and (b) infer basic stats once the sample is big.
+CREATE TABLE IF NOT EXISTS player_observations (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    player_id INTEGER NOT NULL,
+    hand_id INTEGER,
+    session_id INTEGER,
+    pos TEXT,
+    cards TEXT,
+    vpip INTEGER,      -- voluntarily put money in preflop
+    pfr INTEGER,       -- raised/3bet preflop
+    saw_flop INTEGER,
+    showed INTEGER,    -- cards reached showdown / were shown
+    summary TEXT,
+    created_at TEXT NOT NULL
+);
+CREATE INDEX IF NOT EXISTS idx_pobs_player ON player_observations(player_id);
 """
 
+# Below this many observed hands, don't surface % stats (too small a sample).
+MIN_STATS_SAMPLE = 12
+
 _ensured_for = None
 
 
@@ -329,7 +350,8 @@ def record_hand(shorthand: str, session_id: int | None = None, stakes: str | Non
     if not parsed:
         return {"id": None, "parsed": None}
     hid = store_hand_history(parsed, session_id=session_id, tag=tag, lesson=lesson)
-    return {"id": hid, "parsed": parsed}
+    linked = link_hand_players(hid, parsed, session_id=session_id)  # enrich villain files
+    return {"id": hid, "parsed": parsed, "linked": linked}
 
 
 def get_hand(hand_id: int) -> dict | None:
@@ -493,6 +515,90 @@ def add_read(note: str, seat: str | None = None, name: str | None = None,
     return int(cur.lastrowid)
 
 
+def _player_flags(parsed: dict, pos: str | None) -> tuple[int, int, int]:
+    """(vpip, pfr, saw_flop) for the player at `pos` in a parsed hand."""
+    acts = parsed.get("actions") or []
+    pre = [a for a in acts if a.get("street") == "preflop" and a.get("pos") == pos]
+    post = [a for a in acts if a.get("pos") == pos and a.get("street") in ("flop", "turn", "river")]
+    vol = {"call", "bet", "raise", "allin"}
+    vpip = int(any(a.get("action") in vol for a in pre))
+    pfr = int(any(a.get("action") in {"raise", "allin"} for a in pre))
+    return vpip, pfr, int(bool(post))
+
+
+def link_hand_players(hand_id: int, parsed: dict, session_id: int | None = None) -> int:
+    """For each NAMED player in a parsed hand, upsert their file + log a structured
+    observation. Returns how many players were linked."""
+    sid = _resolve(session_id)
+    linked = 0
+    for pl in (parsed.get("players") or []):
+        name = (pl.get("name") or "").strip()
+        if not name:
+            continue
+        pid = upsert_player(name)
+        vpip, pfr, saw = _player_flags(parsed, pl.get("pos"))
+        cards = " ".join(pl.get("cards") or []) or None
+        acts = [a for a in (parsed.get("actions") or [])
+                if a.get("pos") == pl.get("pos") and a.get("action")]
+        astr = ", ".join(a["action"] + (f" {a['amount']}" if a.get("amount") is not None else "")
+                         for a in acts)
+        summary = (pl.get("pos") or "?") + (f" ({cards})" if cards else "") + (f": {astr}" if astr else "")
+        conn = _c()
+        with conn:
+            conn.execute(
+                "INSERT INTO player_observations (player_id, hand_id, session_id, pos, cards, "
+                "vpip, pfr, saw_flop, showed, summary, created_at) VALUES (?,?,?,?,?,?,?,?,?,?,?)",
+                (pid, hand_id, sid, pl.get("pos"), cards, vpip, pfr, saw, int(bool(cards)),
+                 summary, _now()),
+            )
+        linked += 1
+    return linked
+
+
+def player_profile(name: str) -> dict | None:
+    """Everything known about a player: dossier + observations, with inferred
+    stats once the sample is large enough."""
+    p = _c().execute(
+        "SELECT * FROM poker_players WHERE name LIKE ? COLLATE NOCASE ORDER BY updated_at DESC LIMIT 1",
+        (f"%{name}%",),
+    ).fetchone()
+    if not p:
+        return None
+    p = dict(p)
+    obs = [dict(r) for r in _c().execute(
+        "SELECT * FROM player_observations WHERE player_id = ? ORDER BY id DESC", (p["id"],)
+    ).fetchall()]
+    reads = [r["note"] for r in _c().execute(
+        "SELECT note FROM player_reads WHERE player_id = ? ORDER BY id DESC LIMIT 8", (p["id"],)
+    ).fetchall()]
+    n = len(obs)
+    prof: dict = {
+        "player": p, "observations": n,
+        "recent": [o["summary"] for o in obs[:8] if o["summary"]],
+        "showdowns": [o["cards"] for o in obs if o["cards"]][:10],
+        "reads": reads, "stats": None,
+    }
+    if n >= MIN_STATS_SAMPLE:
+        prof["stats"] = {
+            "hands": n,
+            "vpip_pct": round(100 * sum(o["vpip"] or 0 for o in obs) / n),
+            "pfr_pct": round(100 * sum(o["pfr"] or 0 for o in obs) / n),
+            "wtsd_pct": round(100 * sum(o["showed"] or 0 for o in obs) / n),
+        }
+    elif n:
+        prof["small_sample"] = f"only {n} hand(s) logged — too few for reliable stats"
+    return prof
+
+
+def list_players() -> list[dict]:
+    """The villain file with observation counts, for browsing."""
+    rows = _c().execute(
+        "SELECT p.*, (SELECT COUNT(*) FROM player_observations o WHERE o.player_id = p.id) AS obs "
+        "FROM poker_players p ORDER BY p.updated_at DESC"
+    ).fetchall()
+    return [dict(r) for r in rows]
+
+
 def get_villain_file(name: str | None = None, venue: str | None = None) -> list[dict]:
     """Pull villain dossiers, optionally filtered by name or venue."""
     sql = "SELECT * FROM poker_players"

lyra/tools.py

@@ -173,6 +173,37 @@ def _generate_recap(args: dict, ctx: dict) -> str:
             f"at /recap/{out['id']}")
 
 
+def _player_profile(args: dict, ctx: dict) -> str:
+    prof = poker.player_profile(args.get("name") or "")
+    if not prof:
+        return f"No file on {args.get('name')} yet."
+    p = prof["player"]
+    L = [p["name"] + (f" ({p['venue']})" if p.get("venue") else "")
+         + (f" [{p['category']}]" if p.get("category") else "")]
+    thin = not (p.get("tendencies") or p.get("adjustment")) and not prof.get("stats")
+    if thin:
+        L.append("⚠ THIN FILE — no standing read on record. Report only the observed "
+                 "hand(s) below and tell Brian you've barely seen him. Do NOT generalize a style.")
+    if p.get("description"):
+        L.append(p["description"])
+    if p.get("tendencies"):
+        L.append(f"Tendencies: {p['tendencies']}")
+    if p.get("adjustment"):
+        L.append(f"Exploit: {p['adjustment']}")
+    s = prof.get("stats")
+    if s:
+        L.append(f"Stats ({s['hands']} hands): VPIP {s['vpip_pct']}% · PFR {s['pfr_pct']}% · WTSD {s['wtsd_pct']}%")
+    elif prof.get("small_sample"):
+        L.append(prof["small_sample"])
+    if prof.get("showdowns"):
+        L.append("Shown down: " + ", ".join(prof["showdowns"][:6]))
+    if prof.get("reads"):
+        L.append("Notes: " + " | ".join(prof["reads"][:4]))
+    if prof.get("recent"):
+        L.append("Recent hands: " + " | ".join(prof["recent"][:4]))
+    return "\n".join(L)
+
+
 def _villain_file(args: dict, ctx: dict) -> str:
     vs = poker.get_villain_file(name=args.get("name"), venue=args.get("venue"))
     if not vs:
@@ -271,6 +302,13 @@ TOOLS.update({
         "data + this conversation. Use when he asks for the recap/writeup, usually "
         "after ending a session.",
         {}, [])},
+    "player_profile": {"handler": _player_profile, "spec": _f(
+        "player_profile",
+        "Look up everything known about one opponent — dossier, reads, hands "
+        "they've shown down, and (once enough hands are logged) inferred stats "
+        "like VPIP/PFR. Use when Brian asks what's known about a player.",
+        {"name": {**_S, "description": "Player name to look up"}},
+        ["name"])},
     "get_villain_file": {"handler": _villain_file, "spec": _f(
         "get_villain_file",
         "Pull saved opponent dossiers (the villain file). Filter by name or venue, e.g. before sitting down.",

tests/test_poker.py

@@ -116,6 +116,40 @@ def test_list_recent_hands(lyra):
     assert hh and hh[0]["hole_cards"] == "QQ" and hh[0]["stakes"] == "1/3"
 
 
+def test_player_observation_and_profile(lyra):
+    poker = lyra
+    sid = poker.start_session(stakes="1/3", buy_in=300)
+    parsed = {"hero_pos": "BB",
+              "players": [{"pos": "BTN", "name": "Round Mike"}, {"pos": "BB", "name": None}],
+              "actions": [{"street": "preflop", "pos": "BTN", "action": "raise", "amount": 12},
+                          {"street": "preflop", "pos": "BB", "action": "call"},
+                          {"street": "flop", "board": ["7d", "2c", "5h"]},
+                          {"street": "flop", "pos": "BTN", "action": "bet", "amount": 15}]}
+    hid = poker.store_hand_history(parsed, session_id=sid)
+    assert poker.link_hand_players(hid, parsed, session_id=sid) == 1  # only the named player
+    prof = poker.player_profile("mike")
+    assert prof["player"]["name"] == "Round Mike"
+    assert prof["observations"] == 1
+    assert prof["stats"] is None and "small_sample" in prof  # too few hands for stats
+
+
+def test_player_stats_emerge_with_sample(lyra):
+    poker = lyra
+    sid = poker.start_session(stakes="1/3", buy_in=300)
+    raised = {"players": [{"pos": "BTN", "name": "LAG"}],
+              "actions": [{"street": "preflop", "pos": "BTN", "action": "raise", "amount": 10}]}
+    folded = {"players": [{"pos": "UTG", "name": "LAG"}],
+              "actions": [{"street": "preflop", "pos": "UTG", "action": "fold"}]}
+    for i in range(poker.MIN_STATS_SAMPLE):
+        p = raised if i % 2 == 0 else folded
+        hid = poker.store_hand_history(p, session_id=sid)
+        poker.link_hand_players(hid, p, session_id=sid)
+    prof = poker.player_profile("LAG")
+    assert prof["stats"] is not None
+    assert prof["stats"]["hands"] >= poker.MIN_STATS_SAMPLE
+    assert 30 <= prof["stats"]["vpip_pct"] <= 70  # ~half were voluntary
+
+
 def test_poker_tools_dispatch(lyra):
     from lyra import tools
     assert "started" in tools.dispatch("start_session", {"stakes": "1/3", "buy_in": 300})