diff --git a/docs/requirements/handoff-HEL-916.json b/docs/requirements/handoff-HEL-916.json index ce126c3..9664dac 100644 --- a/docs/requirements/handoff-HEL-916.json +++ b/docs/requirements/handoff-HEL-916.json @@ -26,13 +26,14 @@ "GOV-003", "GOV-005" ], - "deliverable": "从真实基线 ffbc8c2/e74531c 起的集中工程修正,全部离线替身验证、零真实调用:1) api/app.py 对话 system 输入重构为可审的分段结构(【事实:她是谁】/【事实:她此刻的状态】/【指令:怎么说话】),出生事实、既有 persona 诠释原文保留不动,事实与行为指令边界清晰;2) 世界边界改为自然承接表述:保留信息可跨世界、实物不可的真实约束,去掉被扩写成隔屏拒绝的生硬原句,明确亲近表达自然接住、不反复解释规则、追问按本人理解回答、未开收音不声称听见;3) 生活活动状态接线进主对话(life_activity current 作为'此刻'唯一权威),分享候选逐条携带发生时间并被明确标为过去经历,杜绝旧候选冒充此刻;4) sharing.py 判定失败区分:模型答复无效(含证据不符/pydantic 校验失败)保持终态 fail-closed,瞬态失败(超时/上游/预算停)经新增 judge_attempts 计数恰好重排一次(新增列含旧库 guarded ALTER 迁移),成功分享仍需确实叙述+有效回执缺一不可;5) 普通聊天接入情绪:复用既有 PATTERN_DETECT 分类与 dyad 事件接线(原 detect_and_apply 从未被调用),改造为账本化 chat_affect(新表 chat_affect_job,幂等/租约/重启恢复终态),仅 hurt/repair 带 severity 才经既有 make_impulse 产生有界冲击(salience 减半常数,复用既有敏感度方程),none 不动情绪、失败不伪造;6) tests/test_hel916.py 新增 8 个针对性测试(输入结构/边界措辞/失败重试历史拼接/瞬态与无效判定分流/聊天情绪来源-幂等-失败-恢复),并按新接线调整 test_r2 背景调用计数断言;conftest 增加 Python 3.10 测试环境 asyncio.timeout 兼容 shim(仅测试环境,产品仍按 3.11)。", + "deliverable": "两轮交付。第一轮(adf4d5c,总工已核过输入结构/活动接线/分享失败分流/情绪接线框架):api/app.py 对话输入重构为可审分段(事实/此刻状态/指令),出生事实与既有 persona 诠释原文保留;世界边界改自然承接表述;生活活动状态接线为'此刻'唯一权威、分享候选带发生时间标为过去;sharing.py 判定失败分流(无效终态 fail-closed、瞬态经 judge_attempts 恰好重排一次);普通聊天经既有 PATTERN_DETECT+dyad 接线接入情绪(账本化 chat_affect,幂等/租约/恢复终态,salience 0.5 减半,复用既有敏感度与衰减方程)。第二轮(本轮返工,总工 HEL-917 两项阻塞):1) dyad/runtime.py 情绪分类 severity 只接受有限非 bool 数值——True/False(bool 是 int 子类会被当 1.0/0.0)、NaN/正负 Infinity(json.loads 可产出、原 min/max 钳制会放行 NaN 或放大 Infinity)一律按 none 处理:job 终态 done、不写情绪/关系冲击、不重复分类;正常有限 hurt/repair 原有有界算法不变。2) life/runtime.py 聊天情绪补一次性历史切断点(life_control 键 chat_affect_cutoff=初始化时 MAX(message_id)):app lifespan 在开始接收任何聊天前调用 init_chat_affect_cutoff 固化切断点,INSERT…ON CONFLICT/NOT EXISTS 幂等,任何 tick/重启/并发都不会重置;分类只处理切断点之后新完成轮次,旧聊天(迁移库)永不补算为当下伤害;历史回溯未获授权不做。", "acceptance": [ - "pytest tests/ 全量:482 passed / 11 skipped / 3 failed —— 3 个失败(test_r2 lifespan_cancels、server_loop、voice_asr seam_recv_death)在未改动基线 ffbc8c2 上以同环境同样失败,属本机 Python 3.10 与产品目标 3.11 的环境差异,非本次改动引入;test_reach_out 在 3.10 无法收集(datetime.UTC,基线同样)", - "新增 8 个 HEL-916 测试全部通过:修前复现=旧生硬边界原句与无活动接线输入(以基线代码结构对照),修后对照=分段可审输入、候选带发生时间、判定瞬态一次重排、聊天 hurt 冲击有界且幂等持久", - "python3 -m ruff check src 通过;tests 仅剩基线既有的 2 处 test_sdk_livekit_hel908 错误;ruff format 全仓本不强制(基线 73 文件即不一致),未引入新格式问题", - "python3 scripts/check_requirements.py --base-ref origin/main 通过(60项),含本 handoff 再跑一次通过", - "出生底色/人格不重算:persona.prompt() 内容未改一字,测试断言既有 INTERP 原文逐字出现在新输入中" + "返工专项测试(tests/test_hel916.py,本机 Python 3.10+测试 shim,隔离临时库+替身 LLM)16/16 通过:含 True/False/NaN/+Inf/-Inf 五参数均无冲击无重复分类且 dyad 账本不变、正常 hurt 仍走通;迁移旧库首次启动零分类零调用且切断点=MAX(message_id)、新轮只处理一次、重启切断点不变新轮不丢、repair 正向有界冲击走通", + "受影响既有测试通过:tests/test_r2.py -k 'old_profile or disclosure or judgment or receipt or expired' 25 passed;tests/test_r4_api.py + tests/test_mood_runtime.py 11 passed", + "python3 -m ruff check src 通过(0 错误)", + "双基线需求检查通过:--base-ref origin/main 与 --base-ref e74531c 各含本 handoff", + "全量口径如实分开:原施工本机 pytest 全量 482 passed/11 skipped/3 failed(3 项在未改动基线 ffbc8c2 同环境同败,属本机 3.10 与产品 3.11 环境差异);总工全套记录 483 过/11 跳/3 败(总工环境口径),本轮未全库复测、未将总工数字冒充新实测", + "出生底色/人格不重算:persona.prompt() 内容未改一字(测试断言既有 INTERP 原文逐字出现)" ], "deferred": [ "真实模型下的语气自然度、边界承接与情绪体验:本卡零真实调用,无法以离线替身证明语言自然;建议下一轮最低必要验证:由总管在隔离副本放行小额度(建议 ≤30 次对话/1 次分享判定闭环),操作人总管,约 1 小时,重点观察亲近表达承接、追问'为什么'、隔屏说明是否消失、聊天后情绪词变化与恢复", @@ -42,9 +43,9 @@ ], "requirement_changes": [], "verification": [ - "离线测试证据:tests/test_hel916.py 8/8 通过(隔离临时库+替身 LLM+受控断言),全仓 pytest 记录如上", - "修前/修后对照:test_dialogue_input_is_labeled_facts_instructions_and_past_life 断言旧原句'只有信息能穿过两个世界,不能触碰或给予实物'已不在输入、活动状态与候选发生时间在输入中;历史拼接测试复现失败→重试→上下文完整", - "每项证据的边界:以上仅证明服务器输入结构与状态接线正确;不证明真实模型语气自然、不证明用户满意,真实验收保留", + "离线测试证据:tests/test_hel916.py 16/16 通过(隔离临时库+替身 LLM+受控断言);受影响既有子集 25+11 通过;命令与口径见 acceptance,未全库复测", + "返工修前/修后对照:修前(adf4d5c)severity=True/NaN/Infinity 会进入 min/max 钳制(True→1.0 最大冲击、NaN 经 max/min 原样穿透),且首次启动会把库中所有旧聊天逐条分类;修后五类无效值均无冲击无重复分类、迁移旧库首次启动零调用、切断点重启不变", + "每项证据的边界:以上仅证明服务器输入结构、状态接线与数值防护正确;不证明真实模型语气自然、不证明用户满意,真实验收保留;真实体验方案仅备稿,待两项复核通过后由总管集中请用户批准", "未测到:真实 LLM/ASR/TTS 行为、多日连续运行、浏览器端到端、Safari/手机;均如实未验证" ] } diff --git a/src/cybergril/api/app.py b/src/cybergril/api/app.py index 5d42c6c..96f5d58 100644 --- a/src/cybergril/api/app.py +++ b/src/cybergril/api/app.py @@ -261,6 +261,10 @@ def create_app( app.state.semantic.recover() if app.state.life.reach_out: app.state.life.reach_out.recover() + # HEL-916 rework: fix the chat-affect historical cutoff NOW, before + # the server accepts its first chat turn — everything that already + # exists (migration) stays unclassified, everything after it flows. + app.state.life.init_chat_affect_cutoff() # HEL-879: bounded restart compensation for this instance's own # voice rooms (persisted cleanup ledger; own rooms only). if getattr(app.state, "voice_service", None): diff --git a/src/cybergril/dyad/runtime.py b/src/cybergril/dyad/runtime.py index 7334e63..808ec93 100644 --- a/src/cybergril/dyad/runtime.py +++ b/src/cybergril/dyad/runtime.py @@ -8,6 +8,7 @@ never as lines to recite. from __future__ import annotations import logging +import math import secrets import time from datetime import datetime @@ -111,7 +112,15 @@ class DyadRuntime: "message_id": message_id}, max_tokens=200, ) kind, severity = raw.get("kind"), raw.get("severity") - if kind in ("hurt", "repair") and isinstance(severity, (int, float)): + # HEL-916 rework: accept ONLY finite numbers — bool is an int + # subclass (True would land as 1.0) and json.loads happily yields + # NaN/Infinity, which the min/max clamp would pass through as the + # maximum shock. Anything else is treated like "none": the job is + # done, the mood and the ledger stay untouched. + if (kind in ("hurt", "repair") + and isinstance(severity, (int, float)) + and not isinstance(severity, bool) + and math.isfinite(severity)): severity = max(-1.0, min(1.0, float(severity))) dyad = self.load() dyad.apply(DyadEvent(kind=kind, summary=f"对话事件 message_id={message_id}", diff --git a/src/cybergril/life/runtime.py b/src/cybergril/life/runtime.py index b09d856..bf8a7dc 100644 --- a/src/cybergril/life/runtime.py +++ b/src/cybergril/life/runtime.py @@ -99,6 +99,33 @@ class LifeRuntime: yield day.isoformat(), slot, stamp day += timedelta(days=1) + def _chat_affect_cutoff(self) -> int: + """HEL-916 rework: one-time historical cutoff for chat-affect. + + On the very first initialization (or on a database migrated from a + build without this wiring) the cutoff persists the current max + message id ONCE — every chat that predates the wiring stays + unclassified forever. ``ON CONFLICT DO NOTHING`` makes the write + idempotent: no tick, restart or concurrent worker can ever reset the + cutoff and swallow turns that complete after it. The app lifespan + calls :meth:`init_chat_affect_cutoff` before the server accepts any + chat request; this lazy read is the fallback for other assemblies. + """ + row = self.store.query_one("SELECT value FROM life_control WHERE key='chat_affect_cutoff'") + if not row: + with self.store.conn: + self.store.execute( + "INSERT INTO life_control " + "SELECT 'chat_affect_cutoff', COALESCE(MAX(id),0) FROM chat_message " + "WHERE NOT EXISTS(SELECT 1 FROM life_control WHERE key='chat_affect_cutoff')" + ) + row = self.store.query_one("SELECT value FROM life_control WHERE key='chat_affect_cutoff'") + return int(row["value"]) + + def init_chat_affect_cutoff(self) -> None: + """Lifespan hook: establish the cutoff before any turn can arrive.""" + self._chat_affect_cutoff() + async def tick(self): if self.memories: await self.memories.tick() @@ -110,16 +137,18 @@ class LifeRuntime: if self.dyad: self.dyad.daily_regression(self.clock()) # HEL-916: ordinary chat finally feeds the mood — one bounded - # classification per completed public turn, before the R2 gate so - # text-only configurations keep the wiring too. Ledger-enforced + # classification per NEWLY completed public turn (id above the + # one-time cutoff), before the R2 gate so text-only + # configurations keep the wiring too. Ledger-enforced # idempotency; no candidates or private life data in the payload. + cutoff = self._chat_affect_cutoff() row = self.store.query_one( "SELECT m.id AS message_id, u.text AS user_text, m.text AS reply_text " "FROM chat_message m JOIN chat_message u " "ON u.turn_id=m.turn_id AND u.role='user' AND u.status='sent' " - "WHERE m.role='companion' AND m.status='sent' AND m.proactive=0 " + "WHERE m.role='companion' AND m.status='sent' AND m.proactive=0 AND m.id>? " "AND NOT EXISTS(SELECT 1 FROM chat_affect_job j WHERE j.message_id=m.id) " - "ORDER BY m.id LIMIT 1") + "ORDER BY m.id LIMIT 1", (cutoff,)) if row: await self.dyad.chat_affect(message_id=row["message_id"], user_text=row["user_text"], diff --git a/tests/test_hel916.py b/tests/test_hel916.py index f4f2efa..8141303 100644 --- a/tests/test_hel916.py +++ b/tests/test_hel916.py @@ -224,3 +224,98 @@ async def test_chat_affect_recovers_expired_lease_as_failed(tmp_path): assert store.query_one("SELECT state FROM chat_affect_job")["state"] == "failed" await app.state.life.tick() assert not provider.affect_calls # expired lease is never re-run + + +# ---------------------------------------------------------------- rework (总工 HEL-917 两项) + +@pytest.mark.asyncio +@pytest.mark.parametrize("bad", [True, False, float("nan"), float("inf"), float("-inf")]) +async def test_invalid_severity_is_none_like_never_shocks(tmp_path, bad): + app, provider = h916_app(tmp_path, enabled=False) + with TestClient(app) as client: + client.post("/api/companion", json=CREATE) + provider.affect = {"kind": "hurt", "severity": bad} + turn(client, "这句话不该产生任何冲击") + mood, store = app.state.mood, app.state.store + dyad_before = app.state.dyad.load() + before = mood.state.v + await app.state.life.tick() + # job is done (terminal, never reclassified) but nothing moved + assert len(provider.affect_calls) == 1 + assert store.query_one("SELECT state FROM chat_affect_job")["state"] == "done" + assert abs(mood.state.v - before) < 1e-3 # only the pre-existing tanh drift + after = app.state.dyad.load() + assert (after.trust, after.intimacy, after.debt, after.security) == \ + (dyad_before.trust, dyad_before.intimacy, dyad_before.debt, dyad_before.security) + await app.state.life.tick() + assert len(provider.affect_calls) == 1 # no repeat classification + + +@pytest.mark.asyncio +async def test_valid_hurt_still_works_after_the_guard(tmp_path): + app, provider = h916_app(tmp_path, enabled=False) + with TestClient(app) as client: + client.post("/api/companion", json=CREATE) + provider.affect = {"kind": "hurt", "severity": 0.8} + turn(client, "我刚才说了很重的话") + before = app.state.mood.state.v + await app.state.life.tick() + assert app.state.mood.state.v < before - 0.1 # bounded but real + + +def seed_old_chat(db_path): + from cybergril.memory.store import Store + + store = Store(db_path) + with store.conn: + store.execute("INSERT INTO chat_message(ts,role,text,turn_id,status) " + "VALUES(1,'user','很久以前的一句重话','old-1','sent')") + store.execute("INSERT INTO chat_message(ts,role,text,turn_id,status) " + "VALUES(2,'companion','很久以前的回复','old-1','sent')") + store.execute("INSERT INTO chat_message(ts,role,text,turn_id,status) " + "VALUES(3,'user','更久以前','old-2','sent')") + store.execute("INSERT INTO chat_message(ts,role,text,turn_id,status) " + "VALUES(4,'companion','更久以前的回复','old-2','sent')") + store.close() + + +@pytest.mark.asyncio +async def test_migrated_old_chat_never_classified_on_first_startup(tmp_path): + db = tmp_path / "h916.db" + seed_old_chat(db) # a populated database from before this wiring existed + app, provider = h916_app(tmp_path, enabled=False) + with TestClient(app) as client: + await app.state.life.tick() + assert not provider.affect_calls # no call, no job, no retro hurt + assert not app.state.store.query("SELECT * FROM chat_affect_job") + cutoff = app.state.store.query_one( + "SELECT value FROM life_control WHERE key='chat_affect_cutoff'")["value"] + assert int(cutoff) == 4 # pinned to the max pre-existing message id + + +@pytest.mark.asyncio +async def test_cutoff_persists_across_restart_and_only_new_turns_flow(tmp_path): + db = tmp_path / "h916.db" + app, provider = h916_app(tmp_path, enabled=False) + with TestClient(app) as client: + client.post("/api/companion", json=CREATE) + provider.affect = {"kind": "none", "severity": 0} + turn(client, "新完成的一轮") + await app.state.life.tick() + assert len(provider.affect_calls) == 1 + cutoff = app.state.store.query_one( + "SELECT value FROM life_control WHERE key='chat_affect_cutoff'")["value"] + # restart on the same database: the cutoff must not move, the classified + # turn must not be re-run, and a turn completed after the restart flows + app2, provider2 = h916_app(tmp_path, enabled=False) + with TestClient(app2) as client2: + await app2.state.life.tick() + assert len(provider2.affect_calls) == 0 + assert app2.state.store.query_one( + "SELECT value FROM life_control WHERE key='chat_affect_cutoff'")["value"] == cutoff + provider2.affect = {"kind": "repair", "severity": 0.6} + turn(client2, "和好如初的一轮") + before = app2.state.mood.state.v + await app2.state.life.tick() + assert len(provider2.affect_calls) == 1 + assert app2.state.mood.state.v > before # positive, bounded repair impulse