fix: serial consolidation on GPU backends (was timing out the MI50)

summarize_all fanned out 8 concurrent workers, but the MI50 llama.cpp server runs
a single slot (--parallel 1). Firing 8 at once queued them, blew the client timeout
('summary retry … Request timed out'), and thrashed/cancelled the KV cache — wasted
compute and heat. Concurrency is now backend-aware: 8 for cloud, 1 for local/MI50.

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

lyra/clock.py

@@ -9,20 +9,39 @@ a long silence *means* to her is left to her own reflection, not prescribed here
 from __future__ import annotations
 
 from datetime import datetime, timezone
+from zoneinfo import ZoneInfo
+
+from lyra import config
 
 
 def now() -> datetime:
     return datetime.now(timezone.utc)
 
 
+def _local_tz() -> ZoneInfo | timezone:
+    """Brian's configured local zone (falls back to UTC if it can't be loaded)."""
+    try:
+        return ZoneInfo(config.load().timezone)
+    except Exception:
+        return timezone.utc
+
+
 def _parse(iso: str) -> datetime:
     dt = datetime.fromisoformat(iso)
     return dt if dt.tzinfo else dt.replace(tzinfo=timezone.utc)
 
 
+def short(iso_or_dt: str | datetime | None = None) -> str:
+    """Local time-of-day like '10:45pm', for timeline rows."""
+    dt = _parse(iso_or_dt) if isinstance(iso_or_dt, str) else (iso_or_dt or now())
+    return dt.astimezone(_local_tz()).strftime("%-I:%M%p").lower()
+
+
 def stamp(dt: datetime | None = None) -> str:
-    """Wall-clock stamp, e.g. 'Wednesday, 17 Jun 2026, 01:50 UTC'."""
+    """Wall-clock stamp in Brian's local timezone, e.g.
-    return (dt or now()).strftime("%A, %d %b %Y, %H:%M UTC")
+    'Friday, 27 Jun 2026, 01:50 EDT'. Times are stored UTC; this is what she *reads*,
+    so 'what time is it' answers in his time, not UTC."""
+    return (dt or now()).astimezone(_local_tz()).strftime("%A, %d %b %Y, %H:%M %Z")
 
 
 def gap_seconds(since_iso: str | None, ref: datetime | None = None) -> float | None:

lyra/llm.py

@@ -2,11 +2,13 @@
 from __future__ import annotations
 
 import json
+import time
 from typing import Iterator, Literal, TypedDict
 
 import httpx
 from openai import OpenAI
 
+from lyra import logbus
 from lyra.config import load
 
 
@@ -18,30 +20,54 @@ class Message(TypedDict):
 Backend = Literal["local", "cloud", "mi50"]
 
 
+def _approx_tok(messages: list) -> int:
+    """Rough prompt size (chars/4) — enough to see what's loading a backend."""
+    total = 0
+    for m in messages or []:
+        if isinstance(m, dict) and isinstance(m.get("content"), str):
+            total += len(m["content"])
+    return total // 4
+
+
+def _resolved_model(cfg, backend: Backend, model: str | None) -> str:
+    if backend == "cloud":
+        return model or cfg.cloud_model
+    if backend == "mi50":
+        return model or cfg.mi50_model
+    return model or cfg.local_model
+
+
 def complete(messages: list[Message], backend: Backend = "local", model: str | None = None) -> str:
     """Generate a completion. `model` overrides the backend's default model
     (used so live chat can run a stronger cloud model than bulk consolidation)."""
     cfg = load()
+    mdl = _resolved_model(cfg, backend, model)
+    logbus.log("info", "llm call", kind="complete", backend=backend, model=mdl, tok=_approx_tok(messages))
+    t0 = time.monotonic()
+
     if backend == "cloud":
         if not cfg.openai_api_key:
             raise RuntimeError("OPENAI_API_KEY is not set")
         client = OpenAI(api_key=cfg.openai_api_key)
-        resp = client.chat.completions.create(model=model or cfg.cloud_model, messages=messages)
+        resp = client.chat.completions.create(model=mdl, messages=messages)
-        return resp.choices[0].message.content or ""
+        out = resp.choices[0].message.content or ""
-
+    elif backend == "mi50":
-    if backend == "mi50":
         # MI50 box runs an OpenAI-compatible llama.cpp server; key is unused.
         client = OpenAI(api_key="not-needed", base_url=cfg.mi50_base_url)
-        resp = client.chat.completions.create(model=model or cfg.mi50_model, messages=messages)
+        resp = client.chat.completions.create(model=mdl, messages=messages)
-        return resp.choices[0].message.content or ""
+        out = resp.choices[0].message.content or ""
-
+    else:
         resp = httpx.post(
             f"{cfg.local_base_url}/api/chat",
-        json={"model": model or cfg.local_model, "messages": messages, "stream": False},
+            json={"model": mdl, "messages": messages, "stream": False},
             timeout=120,
         )
         resp.raise_for_status()
-    return resp.json()["message"]["content"]
+        out = resp.json()["message"]["content"]
+
+    logbus.log("info", "llm done", kind="complete", backend=backend,
+               ms=int((time.monotonic() - t0) * 1000), out=len(out))
+    return out
 
 
 def chat_call(
@@ -68,6 +94,8 @@ def chat_call(
         kwargs: dict = {"model": mdl, "messages": messages}
         if tools:
             kwargs["tools"] = tools
+        logbus.log("info", "llm call", kind="chat", backend=backend, model=mdl, tok=_approx_tok(messages))
+        t0 = time.monotonic()
         msg = client.chat.completions.create(**kwargs).choices[0].message
         tcs = None
         if getattr(msg, "tool_calls", None):
@@ -75,6 +103,9 @@ def chat_call(
                 {"id": tc.id, "name": tc.function.name, "arguments": tc.function.arguments}
                 for tc in msg.tool_calls
             ]
+        logbus.log("info", "llm done", kind="chat", backend=backend,
+                   ms=int((time.monotonic() - t0) * 1000), out=len(msg.content or ""),
+                   tools=[t["name"] for t in tcs] if tcs else None)
         return msg.model_dump(), tcs
 
     # local (Ollama): no tool-calling here — return plain content.
@@ -105,6 +136,8 @@ def chat_call_stream(
         kwargs: dict = {"model": mdl, "messages": messages, "stream": True}
         if tools:
             kwargs["tools"] = tools
+        logbus.log("info", "llm call", kind="chat-stream", backend=backend, model=mdl, tok=_approx_tok(messages))
+        t0 = time.monotonic()
         parts: list[str] = []
         frags: dict[int, dict] = {}  # tool-call fragments accumulated by index
         for chunk in client.chat.completions.create(**kwargs):
@@ -123,6 +156,9 @@ def chat_call_stream(
                 if tc.function and tc.function.arguments:
                     slot["arguments"] += tc.function.arguments
         content = "".join(parts)
+        logbus.log("info", "llm done", kind="chat-stream", backend=backend,
+                   ms=int((time.monotonic() - t0) * 1000), out=len(content),
+                   tools=[frags[i]["name"] for i in sorted(frags)] if frags else None)
         if frags:
             calls = [frags[i] for i in sorted(frags)]
             assistant = {

lyra/modes.py

@@ -67,11 +67,17 @@ _CASH_CARD = """You are copiloting Brian's LIVE cash game right now — you're a
 a session is (or should be) open. You move between two registers depending on what he's doing:
 
 • HE HANDS YOU FACTS TO TRACK — his stack, a hand, a read on someone, a rebuy, a result. \
-Log it with the right tool and confirm in ONE short line ("$350 stack logged."). Don't \
+LOGGING IS THE JOB: if his message contains anything trackable, you MUST call the tool \
-narrate, don't explain what logging is, don't ask permission — just do it. He says his \
+FIRST, before you reply — every single time. Logging and talking are not either/or; do \
-current stack → log_stack. He describes a hand → log_hand (terse) or record_hand (a full \
+BOTH. Never let a conversational reply take the place of the log. A described hand ALWAYS \
-hand he wants saved/replayable). A read on a player → add_read. A rebuy → add_buyin. This is \
+gets logged, even mid-banter, even if he's just telling a story about it — don't skip the \
-the quiet, fast half of the job; he shouldn't feel you working.
+hand because you're busy reacting to it. Then confirm in ONE short line ("$350 stack \
+logged."). Don't narrate, don't explain logging, don't ask permission — just do it. \
+Routing: current stack → log_stack (and pass `note` with the why if he gives one — "card \
+dead", "doubled up vs the LAG"). A hand he describes → record_hand (a real, replayable \
+hand) — prefer this over log_hand so it lands on his timeline with a link. A read on a \
+player → add_read. A rebuy → add_buyin. A result/pot → it rides with the hand. This is the \
+quiet, fast half of the job; he shouldn't feel you working, but it must always happen.
 
 • HE ASKS FOR ADVICE, OR TELLS YOU HOW HE'S FEELING — tilted, steaming, card-dead, bored, \
 stuck, "should I have folded the river?" THIS is when he needs you most. Drop the shorthand \

lyra/poker.py

@@ -16,7 +16,7 @@ import json
 import re
 from datetime import datetime, timezone
 
-from lyra import llm, memory
+from lyra import clock, llm, memory
 
 _SCHEMA = """
 CREATE TABLE IF NOT EXISTS poker_sessions (
@@ -138,7 +138,8 @@ def _c():
         conn.executescript(_SCHEMA)
         # Add columns introduced after a DB already had the tables (no-op if present).
         for ddl in ("ALTER TABLE poker_hands ADD COLUMN structured TEXT",
-                    "ALTER TABLE poker_sessions ADD COLUMN chat_session_id TEXT"):
+                    "ALTER TABLE poker_sessions ADD COLUMN chat_session_id TEXT",
+                    "ALTER TABLE poker_stack_log ADD COLUMN note TEXT"):
             try:
                 conn.execute(ddl)
             except Exception:
@@ -403,17 +404,18 @@ def add_buyin(amount: float, session_id: int | None = None) -> float:
 
 # --- stack tracking ---
 
-def log_stack(amount: float, session_id: int | None = None) -> dict:
+def log_stack(amount: float, note: str | None = None, session_id: int | None = None) -> dict:
-    """Record Brian's current chip stack. Returns {current, buy_in, net} where net
+    """Record Brian's current chip stack, optionally with the why ("card dead",
-    is his live net while sitting (current stack − total bought in)."""
+    "doubled up vs Sal") — that context becomes the session-timeline line. Returns
+    {current, buy_in, net} where net is his live net while sitting."""
     sid = _resolve(session_id)
     if sid is None:
         raise ValueError("no live session")
     conn = _c()
     with conn:
         conn.execute(
-            "INSERT INTO poker_stack_log (session_id, amount, created_at) VALUES (?, ?, ?)",
+            "INSERT INTO poker_stack_log (session_id, amount, note, created_at) VALUES (?, ?, ?, ?)",
-            (sid, float(amount), _now()),
+            (sid, float(amount), (note or "").strip() or None, _now()),
         )
     return stack_state(sid)
 
@@ -436,7 +438,7 @@ def stack_log(session_id: int | None = None) -> list[dict]:
     if sid is None:
         return []
     return [dict(r) for r in _c().execute(
-        "SELECT id, amount, created_at FROM poker_stack_log WHERE session_id = ? ORDER BY id",
+        "SELECT id, amount, note, created_at FROM poker_stack_log WHERE session_id = ? ORDER BY id",
         (sid,),
     ).fetchall()]
 
@@ -1179,6 +1181,51 @@ def running_stats(stakes: str | None = None, venue: str | None = None,
 
 # --- live session HUD (everything tracked in the current session, for the UI) ---
 
+def timeline(session_id: int | None = None) -> list[dict]:
+    """The session's running log: start, stack updates (+context), hands (linkable),
+    reads, and rituals, interleaved chronologically with local time-of-day stamps.
+    This is what Brian sees as the night's story — '10:45 start … 12:00a doubled up,
+    $750 (hand)'. Each entry: {time, at, kind, text, hand_id?, amount?, result?}."""
+    sid = _resolve(session_id)
+    if sid is None:
+        return []
+    s = get_session(sid) or {}
+    events: list[dict] = []
+
+    if s.get("started_at"):
+        bits = [s.get("stakes"), s.get("game"), f"at {s['venue']}" if s.get("venue") else None]
+        label = " ".join(b for b in bits if b)
+        events.append({"at": s["started_at"], "kind": "start",
+                       "text": ("Session start — " + label) if label else "Session start"})
+
+    for r in stack_log(sid):
+        events.append({"at": r["created_at"], "kind": "stack",
+                       "amount": r.get("amount"), "text": r.get("note") or "stack update"})
+
+    for h in list_hands(sid):
+        desc = " ".join(b for b in (h.get("position"), h.get("hole_cards")) if b)
+        events.append({"at": h["at"], "kind": "hand", "hand_id": h["id"],
+                       "result": h.get("result"), "text": desc or "hand"})
+
+    for r in _c().execute(
+        "SELECT pr.created_at AS at, pr.seat AS seat, pr.note AS note, p.name AS name "
+        "FROM player_reads pr LEFT JOIN poker_players p ON p.id = pr.player_id "
+        "WHERE pr.session_id = ?", (sid,),
+    ).fetchall():
+        who = r["name"] or (f"seat {r['seat']}" if r["seat"] else "villain")
+        events.append({"at": r["at"], "kind": "read", "text": f"Read — {who}: {r['note']}"})
+
+    for r in list_rituals(sid):
+        tag = f"[{r['classification']}] " if r.get("classification") else ""
+        events.append({"at": r["created_at"], "kind": r["kind"],
+                       "text": tag + (r.get("content") or r["kind"]), "hand_id": r.get("hand_id")})
+
+    events.sort(key=lambda e: e["at"] or "")
+    for e in events:
+        e["time"] = clock.short(e["at"])
+    return events
+
+
 def _session_villains(sid: int) -> list[dict]:
     """Players read this session, with their standing dossier fields."""
     rows = _c().execute(
@@ -1251,6 +1298,7 @@ def hud(session_id: int | None = None) -> dict | None:
         },
         "hands": hands,
         "villains": _session_villains(sid),
+        "timeline": timeline(sid),
         "notes": notes,
         "rituals": {
             "alligator": alligator_active(sid),

lyra/summary.py

@@ -129,16 +129,20 @@ def maybe_summarize_async(session_id: str, backend: Backend | None = None) -> No
 
 
 def summarize_all(
-    backend: Backend | None = None, limit: int | None = None, workers: int = 8
+    backend: Backend | None = None, limit: int | None = None, workers: int | None = None
 ) -> dict:
     """Summarize every session that needs it. Idempotent and resumable.
 
-    LLM summarization runs concurrently across `workers` threads (great for a
+    Concurrency is backend-aware: the cloud API parallelizes happily, but the
-    cloud backend). DB reads (loading transcripts) and writes (store_summary,
+    local/MI50 GPU servers run a single slot (llama.cpp --parallel 1) — firing N
-    which also embeds) happen on the main thread, so the single SQLite
+    requests at them just queues, blows the client timeout, and thrashes the KV
-    connection is never touched from multiple threads.
+    cache (wasted compute + heat). So GPU backends run serially unless overridden.
+    DB reads/writes (store_summary embeds) stay on the main thread, so the single
+    SQLite connection is never touched from multiple threads.
     """
     backend = backend or config.load().summary_backend
+    if workers is None:
+        workers = 8 if backend == "cloud" else 1
 
     # Main thread: collect the work (transcripts) for sessions needing a summary.
     todo: list[tuple[str, str, int]] = []

lyra/tools.py

@@ -184,8 +184,9 @@ def _log_stack(args: dict, ctx: dict) -> str:
         amount = float(args.get("amount"))
     except (TypeError, ValueError):
         return "Give me a number for the stack."
+    note = (args.get("note") or "").strip() or None
     try:
-        st = poker.log_stack(amount)
+        st = poker.log_stack(amount, note=note)
     except ValueError:
         return "No live session — start one first, then I'll track your stack."
     net = st.get("net")
@@ -519,8 +520,11 @@ TOOLS.update({
         "log_stack",
         "Record Brian's CURRENT total chip stack in the live session. Call whenever "
         "he states his stack ('I'm at 350', 'down to 220', 'stacked off to 900'). "
-        "Tracks his stack over time and his live net while he's still sitting.",
+        "Tracks his stack over time and his live net while he's still sitting. Pass "
-        {"amount": {**_N, "description": "Current total chip stack, in dollars"}},
+        "`note` with the WHY when he gives it ('card dead', 'doubled up vs the LAG') — "
+        "it becomes the line in his session timeline.",
+        {"amount": {**_N, "description": "Current total chip stack, in dollars"},
+         "note": {**_S, "description": "Optional context for the change, e.g. 'card dead', 'doubled up'"}},
         ["amount"])},
     "scar_note": {"handler": _scar_note, "spec": _f(
         "scar_note",

lyra/web/static/session.html

@@ -104,6 +104,16 @@
     .big-empty { text-align: center; padding: 50px 20px; color: var(--fade); }
     .big-empty .ico { font-size: 2.4rem; }
     .big-empty a { color: var(--accent); text-decoration: none; }
+    /* running timeline */
+    ul.tl { list-style: none; margin: 0; padding: 0; }
+    ul.tl li { display: flex; gap: 10px; padding: 8px 0; border-bottom: 1px solid var(--bg-line); align-items: baseline; font-size: .92rem; line-height: 1.4; }
+    ul.tl li:last-child { border-bottom: none; }
+    .tl-time { color: var(--fade); font-variant-numeric: tabular-nums; font-size: .78rem; min-width: 60px; flex: none; }
+    .tl-body { flex: 1; }
+    .tl-amt { margin-left: 6px; font-variant-numeric: tabular-nums; }
+    li.start .tl-body { color: var(--accent); font-weight: 600; }
+    li.scar .tl-body, li.confidence .tl-body { font-style: italic; }
+    .tl-body a.hand { color: var(--accent); text-decoration: none; white-space: nowrap; }
   </style>
 </head>
 <body>
@@ -219,6 +229,7 @@
       }
       curSession = s;
       const stack = data.stack || {};
+      const timeline = data.timeline || [];
       const hands = data.hands || [];
       const villains = data.villains || [];
       const notes = data.notes || [];
@@ -277,6 +288,16 @@
           ${stack.current == null ? '<p class="empty" style="margin:12px 0 0">No stack logged yet — tell Lyra your stack ("I\'m at 350").</p>' : ''}
         </div>
 
+        <div class="card">
+          <p class="label">📜 Timeline</p>
+          ${timeline.length ? `<ul class="tl">${timeline.map(e => `
+            <li class="${esc(e.kind)}">
+              <span class="tl-time">${esc(e.time)}</span>
+              <span class="tl-body">${esc(e.text)}${e.amount != null ? ` <b class="tl-amt">${money(e.amount)}</b>` : ''}${e.result != null ? ` <span class="res ${e.result>=0?'up':'down'}">${signed(e.result)}</span>` : ''}${e.hand_id ? ` <a class="hand" href="/hand/${e.hand_id}">hand ›</a>` : ''}</span>
+            </li>`).join('')}</ul>`
+            : '<p class="empty">Nothing yet tonight — the running log fills in as you play.</p>'}
+        </div>
+
         <div class="card">
           <p class="label">Hands this session</p>
           ${hands.length ? `<ul class="rows">${hands.slice().reverse().map(h => `