feat: session modes (Talk/Cash) + live session HUD

Lyra now switches register based on what she's doing at the table instead of
being a wishy-washy companion mid-session.

Modes (lyra/modes.py):
- Talk (default companion) + Cash (live cash copilot); a mode = prompt card +
  tool allow-list. Tool gating via tools.specs(allow=).
- Two-register Cash voice: act-first one-line logging when fed facts; full warm
  companion voice for strategy / tilt / mental game.
- mode persisted per chat session (new sessions.mode column); auto-switch into
  Cash when start_session fires; UI forces cloud backend in Cash (tools only
  fire there).

Stack tracking + HUD:
- log_stack tool + poker_stack_log table; live net while sitting (stack - buy-in).
- poker.hud() bundle; /session HUD page (stack sparkline, hands, villains, notes,
  stats) polling /session/data every 5s; Talk/Cash switcher + Session nav.

Endpoints: /session, /session/data, GET/POST /sessions/{id}/mode, /modes.
tests/test_modes.py (gating, mode roundtrip, stack/HUD); 36 tests green. v0.3.0.

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

lyra/chat.py

@@ -10,7 +10,7 @@ After replying, the session is compacted if enough new turns have accumulated.
 """
 from __future__ import annotations
 
-from lyra import clock, config, llm, logbus, memory, persona, self_state, summary
+from lyra import clock, config, llm, logbus, memory, modes, persona, self_state, summary
 from lyra import tools as toolkit
 from lyra.llm import Backend, Message
 
@@ -24,6 +24,15 @@ MAX_TOOL_ROUNDS = 5  # cap tool-call iterations per turn
 TOOL_BACKENDS = {"cloud"}
 
 
+def _maybe_switch_mode(session_id: str, tool_name: str) -> None:
+    """Keep the chat framing aligned with the live data: opening a poker session
+    auto-flips this chat into Cash mode (so the next turn gets the cash card + the
+    full live toolset). Manual UI switching still overrides anytime."""
+    if tool_name == "start_session":
+        memory.set_session_mode(session_id, modes.CASH.key)
+        logbus.log("info", "mode auto-switch", session=session_id, mode=modes.CASH.key)
+
+
 def _summary_note(summaries: list[memory.Summary]) -> Message:
     lines = [f"- ({(s.session_started_at or s.created_at)[:10]}) {s.content}" for s in summaries]
     body = "Gist of earlier sessions (compacted — ask if you need specifics):\n" + "\n".join(lines)
@@ -56,7 +65,8 @@ def _render(messages: list[Message]) -> str:
     return "\n\n".join(f"[{m['role']}]\n{m['content']}" for m in messages)
 
 
-def build_messages(session_id: str, user_msg: str) -> list[Message]:
+def build_messages(session_id: str, user_msg: str,
+                   mode: modes.Mode | None = None) -> list[Message]:
     """Assemble the full, tiered message list for one turn."""
     messages: list[Message] = [{"role": "system", "content": persona.system_prompt()}]
 
@@ -64,6 +74,12 @@ def build_messages(session_id: str, user_msg: str) -> list[Message]:
     # right after the persona — her sense of self before her model of the world.
     messages.append({"role": "system", "content": self_state.render_for_context(self_state.load())})
 
+    # Mode card: how to behave *right now* (e.g. live-cash copilot). High priority —
+    # it sits just after her sense of self, before her model of the world. Talk mode
+    # has no card (the persona's default voice is the Talk register).
+    if mode and mode.card:
+        messages.append({"role": "system", "content": mode.card})
+
     # When she is: current time + the gap since Brian last spoke (she has no clock).
     messages.append(_now_note())
 
@@ -133,11 +149,12 @@ def respond(session_id: str, user_msg: str, backend: Backend = "cloud",
         model=model, embed=cfg.embed_backend,
     )
 
-    messages = build_messages(session_id, user_msg)
+    mode = modes.get(memory.get_session_mode(session_id))
+    messages = build_messages(session_id, user_msg, mode=mode)
 
-    # Tool loop: offer Lyra her tools; if she calls one, run it and feed the
-    # result back so she can continue, until she returns a normal text reply.
-    tool_specs = toolkit.specs() if backend in TOOL_BACKENDS else None
+    # Tool loop: offer Lyra her tools (scoped to the mode); if she calls one, run it
+    # and feed the result back so she can continue, until she returns a text reply.
+    tool_specs = toolkit.specs(mode.tools) if backend in TOOL_BACKENDS else None
     ctx = {"session_id": session_id, "backend": backend}
     reply = ""
     for _ in range(MAX_TOOL_ROUNDS):
@@ -152,6 +169,7 @@ def respond(session_id: str, user_msg: str, backend: Backend = "cloud",
             result = toolkit.dispatch(tc["name"], tc["arguments"], ctx)
             logbus.log("info", "tool call", session=session_id, tool=tc["name"], result=result[:80])
             messages.append({"role": "tool", "tool_call_id": tc["id"], "content": result})
+            _maybe_switch_mode(session_id, tc["name"])
     if not reply:
         reply = "(I got tangled using my tools there — say that again?)"
     logbus.log("info", "reply", session=session_id, chars=len(reply))
@@ -183,8 +201,9 @@ def respond_stream(session_id: str, user_msg: str, backend: Backend = "cloud",
         model=model, embed=cfg.embed_backend,
     )
 
-    messages = build_messages(session_id, user_msg)
-    tool_specs = toolkit.specs() if backend in TOOL_BACKENDS else None
+    mode = modes.get(memory.get_session_mode(session_id))
+    messages = build_messages(session_id, user_msg, mode=mode)
+    tool_specs = toolkit.specs(mode.tools) if backend in TOOL_BACKENDS else None
     ctx = {"session_id": session_id, "backend": backend}
     parts: list[str] = []
     for _ in range(MAX_TOOL_ROUNDS):
@@ -207,6 +226,7 @@ def respond_stream(session_id: str, user_msg: str, backend: Backend = "cloud",
             result = toolkit.dispatch(tc["name"], tc["arguments"], ctx)
             logbus.log("info", "tool call", session=session_id, tool=tc["name"], result=result[:80])
             messages.append({"role": "tool", "tool_call_id": tc["id"], "content": result})
+            _maybe_switch_mode(session_id, tc["name"])
             yield ("tool", tc["name"])
 
     reply = "".join(parts)