serversdown
96a44365d9
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>
98 lines
4.4 KiB
Python
98 lines
4.4 KiB
Python
"""Reliable hand logging: hero-hand guard, tool-visible history (B), forced log (A).
|
|
|
|
Root cause these guard: mid-session, memory.history() rebuilt past turns as
|
|
'hand -> narration' with tool calls stripped, few-shot-conditioning the model to
|
|
stop logging (clean history logged 4/4, the stripped history 0/4)."""
|
|
from __future__ import annotations
|
|
|
|
from types import SimpleNamespace
|
|
|
|
from lyra import poker_prompts as pp
|
|
|
|
|
|
# --- the hero-hand guard (who gets force-logged) --------------------------
|
|
|
|
def test_looks_like_hero_hand_true_for_brians_own_hand():
|
|
assert pp.looks_like_hero_hand("im utg with 2d2s. i raise to $15, btn calls")
|
|
assert pp.looks_like_hero_hand("300eff. i call btn w AsQs, flop Qh7c2s, i bet 20 he calls")
|
|
|
|
|
|
def test_looks_like_hero_hand_false_for_observed_and_chatter():
|
|
# A villain the actor (no I/me/my) must never be force-logged as Brian's hand.
|
|
assert not pp.looks_like_hero_hand("TAG limped A4o in the SB")
|
|
assert not pp.looks_like_hero_hand("how's the table looking tonight?")
|
|
assert not pp.looks_like_hero_hand("")
|
|
|
|
|
|
# --- Fix B: tool calls made visible in reconstructed history --------------
|
|
|
|
def _ex(role, content, at):
|
|
return SimpleNamespace(role=role, content=content, created_at=at, id=hash(at))
|
|
|
|
|
|
def test_history_marks_the_assistant_turn_that_logged(monkeypatch):
|
|
from lyra import mind, memory
|
|
recent = [
|
|
_ex("user", "i have 2d2s utg, flop 2c2hKs, quads", "2026-07-10T18:00:00.000000+00:00"),
|
|
_ex("assistant", "Sick cooler.", "2026-07-10T18:00:05.000000+00:00"),
|
|
_ex("user", "how am i doing", "2026-07-10T18:01:00.000000+00:00"),
|
|
_ex("assistant", "Up a grand.", "2026-07-10T18:01:03.000000+00:00"),
|
|
]
|
|
monkeypatch.setattr(memory, "tool_events", lambda sid: [
|
|
{"tool": "record_hand", "result": "Hand #62 logged — UTG 2d2s.",
|
|
"created_at": "2026-07-10T18:00:03.000000+00:00"},
|
|
{"tool": "session_state", "result": "net +1000",
|
|
"created_at": "2026-07-10T18:01:02.000000+00:00"},
|
|
])
|
|
msgs = mind._history_with_tools("s1", recent)
|
|
# each event is attributed to the assistant turn whose window it falls in
|
|
assert "record_hand → Hand #62 logged" in msgs[1]["content"]
|
|
assert msgs[1]["content"].endswith("Sick cooler.")
|
|
assert "session_state" in msgs[3]["content"]
|
|
# user turns are untouched
|
|
assert msgs[0]["content"] == recent[0].content
|
|
|
|
|
|
def test_history_no_marker_when_no_tools(monkeypatch):
|
|
from lyra import mind, memory
|
|
monkeypatch.setattr(memory, "tool_events", lambda sid: [])
|
|
recent = [_ex("assistant", "just talking", "2026-07-10T18:00:05.000000+00:00")]
|
|
assert mind._history_with_tools("s1", recent)[0]["content"] == "just talking"
|
|
|
|
|
|
# --- Fix A: force the log when the model skipped a hero hand ---------------
|
|
|
|
def _force_setup(monkeypatch, tool_calls):
|
|
from lyra import chat
|
|
monkeypatch.setattr(chat.llm, "chat_call",
|
|
lambda *a, **k: ({"role": "assistant"}, tool_calls))
|
|
dispatched = []
|
|
monkeypatch.setattr(chat.toolkit, "dispatch",
|
|
lambda name, args, ctx=None: dispatched.append(name) or "Hand #71 logged.")
|
|
monkeypatch.setattr(chat.memory, "add_tool_event", lambda *a, **k: 1)
|
|
return chat, dispatched
|
|
|
|
|
|
def test_forces_log_on_unlogged_hero_hand(monkeypatch):
|
|
chat, dispatched = _force_setup(monkeypatch, [{"id": "1", "name": "record_hand",
|
|
"arguments": '{"shorthand":"AsQs..."}'}])
|
|
forced = chat._ensure_hand_logged([], "300eff i call btn w AsQs, i bet 20", "HAND", [],
|
|
"cloud", None, {}, "s1")
|
|
assert forced == ["record_hand"] and dispatched == ["record_hand"]
|
|
|
|
|
|
def test_does_not_force_when_already_logged(monkeypatch):
|
|
chat, dispatched = _force_setup(monkeypatch, [])
|
|
forced = chat._ensure_hand_logged([], "i have AsQs, i bet", "HAND", ["record_hand"],
|
|
"cloud", None, {}, "s1")
|
|
assert forced == [] and dispatched == []
|
|
|
|
|
|
def test_does_not_force_non_hand_or_observed(monkeypatch):
|
|
chat, dispatched = _force_setup(monkeypatch, [])
|
|
# not a HAND turn
|
|
assert chat._ensure_hand_logged([], "down to 220", "LOG", [], "cloud", None, {}, "s1") == []
|
|
# HAND-classified but observed (no first person) → never force-logged as his
|
|
assert chat._ensure_hand_logged([], "TAG shoved AKo", "HAND", [], "cloud", None, {}, "s1") == []
|
|
assert dispatched == []
|