fix(poker): guarantee hand logging — history was conditioning it away

Logging a stated hand was unreliable and got worse mid-session: same model, same
hand, clean history logged 4/4 but the real session's history logged 0/4. Root
cause: memory.recent() rebuilt past turns as "hand -> narration" with the tool
calls stripped (they live in tool_events), so the model's own context became
few-shot examples training it, mid-conversation, to STOP calling tools. Even a
maximal "LOG FIRST, no exceptions" prompt scored 0/5 — it's structural, not wording.

Two-part fix (both, per the system-of-record frame):
- A (guarantee): chat._ensure_hand_logged — on a HAND turn that's Brian's OWN hand,
  if the model didn't log it, force record_hand (tool_choice). Guarded to hero hands
  (looks_like_hero_hand) so an observed hand is never force-logged as his. Adds
  tool_choice passthrough to llm.chat_call; surfaces msg_type on TurnContext.
- B (heal forward): mind._history_with_tools makes each assistant turn's tool calls
  visible in reconstructed history ("record_hand -> Hand #62"), so the demonstrated
  pattern stops being "hand -> narrate". Recovers natural logging as logs accumulate.

Verified: force guard returns record_hand on the polluted context; full respond_stream
logs Hand #63 end-to-end on a clean session. 7 guard tests; suite 219 green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-07-10 20:48:04 +00:00
parent 366e71a384
commit 96a44365d9
5 changed files with 197 additions and 6 deletions
+47 -2
View File
@@ -10,7 +10,7 @@ deliberate) and hands back a ready message list + the active mode. Then:
"""
from __future__ import annotations
from lyra import config, llm, logbus, memory, mind, modes, summary
from lyra import config, llm, logbus, memory, mind, modes, poker_prompts, summary
from lyra import tools as toolkit
from lyra.llm import Backend
@@ -78,6 +78,43 @@ def _mind_loop(messages, backend: Backend, model: str | None, tool_specs,
return reply, tools_run
_FORCE_LOG = (
"You have not logged Brian's hand yet — and a hand must ALWAYS be recorded, no exceptions. "
"Call record_hand now: pass his ENTIRE hand description as one `shorthand` string."
)
def _ensure_hand_logged(messages, user_msg: str, msg_type: str | None, tools_run: list,
backend: Backend, model: str | None, ctx: dict, session_id: str) -> list:
"""Guarantee the ledger. If this turn was Brian's OWN hand and the model didn't log it,
force the record_hand call — the log can't be left to the model's discretion, because
mid-session the history few-shot-conditions it to skip logging (see mind._history_with_tools;
even a maximal 'LOG FIRST' prompt scored 0/5 under a polluted history). Guarded to hero
hands so an observed hand is never force-logged as his. Returns forced tool names."""
if msg_type != "HAND" or backend not in config.load().tool_backends:
return []
if any(t in ("record_hand", "log_hand") for t in tools_run):
return []
if not poker_prompts.looks_like_hero_hand(user_msg):
return []
try:
_, tcs = llm.chat_call(
messages + [{"role": "system", "content": _FORCE_LOG}],
backend=backend, model=model, tools=toolkit.specs(["record_hand"]),
tool_choice={"type": "function", "function": {"name": "record_hand"}},
)
except Exception as exc:
logbus.log("error", "forced hand-log failed", session=session_id, error=str(exc)[:160])
return []
forced = []
for tc in (tcs or []):
result = toolkit.dispatch(tc["name"], tc["arguments"], ctx)
memory.add_tool_event(session_id, tc["name"], tc["arguments"], result)
logbus.log("info", "forced hand log", session=session_id, tool=tc["name"], result=result[:80])
forced.append(tc["name"])
return forced
def _voice_pass(messages, draft: str, backend: Backend, model: str | None) -> str:
"""Mouth: re-render the mind's draft in her voice. Falls back to the draft on failure."""
try:
@@ -104,7 +141,8 @@ def respond(session_id: str, user_msg: str, backend: Backend = "cloud",
# Persist the user turn before the tool loop so its timestamp precedes any
# tool events fired mid-turn (keeps the transcript export in true order).
memory.remember(session_id, "user", user_msg)
reply, _ = _mind_loop(messages, backend, model, tool_specs, ctx, session_id)
reply, tools_run = _mind_loop(messages, backend, model, tool_specs, ctx, session_id)
_ensure_hand_logged(messages, user_msg, turn.msg_type, tools_run, backend, model, ctx, session_id)
mouth = _mouth_target(cfg, backend, model)
if mouth and reply:
reply = _voice_pass(messages, reply, *mouth)
@@ -139,6 +177,7 @@ def respond_stream(session_id: str, user_msg: str, backend: Backend = "cloud",
if mouth is None:
# No separate voice: stream the mind directly (the original path, unchanged).
parts: list[str] = []
tools_run: list[str] = []
for _ in range(MAX_TOOL_ROUNDS):
assistant_msg = None
tool_calls = None
@@ -161,7 +200,11 @@ def respond_stream(session_id: str, user_msg: str, backend: Backend = "cloud",
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"])
tools_run.append(tc["name"])
yield ("tool", tc["name"])
for name in _ensure_hand_logged(messages, user_msg, turn.msg_type, tools_run,
backend, model, ctx, session_id):
yield ("tool", name)
reply = "".join(parts)
if not reply:
reply = _TANGLED
@@ -169,6 +212,8 @@ def respond_stream(session_id: str, user_msg: str, backend: Backend = "cloud",
else:
# Mind decides + runs tools (non-streamed); mouth re-voices, streamed.
draft, tools_run = _mind_loop(messages, backend, model, tool_specs, ctx, session_id)
tools_run += _ensure_hand_logged(messages, user_msg, turn.msg_type, tools_run,
backend, model, ctx, session_id)
for name in tools_run:
yield ("tool", name)
parts = []