refactor: remove block-sequential gate path and gate_block knob (algo #6)

config/train_videomme.yaml 同时收录待入库的实验配置变更(run_id v2 /
concurrency 32 / batch_size 40)。tests/integration/test_v3_contract_e2e.py
的 run_id 断言按 Task 5 显式契约同步修正(原断言依赖旧隐式实例注入)。

app/harness/checkpoint.py

@@ -58,7 +58,6 @@ _DECISION_KEYS = (
     "gate_delta_min",
     "gate_lambda_dir",
     "gate_e_rollback",
-    "gate_block",
     "gate_n_max",
     "gate_p_low",
     "gate_p_high",

app/harness/config.py

@@ -70,14 +70,13 @@ class RunConfig:
         gate_delta_min: 最小点估计效应量下限（承接旧 margin 语义）。
         gate_lambda_dir: Wald 方向拒绝的对数似然比阈值（必须为负）。
         gate_e_rollback: 试用期对称回滚门（回滚 e 值门槛）。
-        gate_block: 块序贯验证的块大小（=推理并发度，块内跑满）。
         gate_n_max: 单次 gate 消耗的题数上限。
         gate_p_low: 信息量阶梯 p-hat 保留区间下界（剔除必错零信息题）。
         gate_p_high: 信息量阶梯 p-hat 保留区间上界（剔除必对零信息题）。
         gate_probe_quota: 冷启动探针集比例（全错题中插尾的比例）。
         gate_gamma_decay: 逐题正确率估计 p-hat 的 EMA 衰减系数。
         gate_cooldown_steps: 回滚后该题型跳过进化的冷却 step 数。
-        gate_guard_err: gate 内跨块累计 INFRA 错误率护栏。
+        gate_guard_err: gate 内累计 INFRA 错误率护栏。
         skill_update_mode: skill 进化模式，"patch"（局部 edit）/ "rewrite"（整篇重写）。
         appendix_consolidate_threshold: appendix note 条数达此值触发 LLM consolidation。
         run_id: diagnose/evolve 模式要分析的运行 ID，默认空字符串。
@@ -125,7 +124,6 @@ class RunConfig:
     gate_delta_min: float
     gate_lambda_dir: float
     gate_e_rollback: float
-    gate_block: int
     gate_n_max: int
     gate_p_low: float
     gate_p_high: float
@@ -361,7 +359,7 @@ def _validate_gate_thresholds(config: RunConfig) -> None:
 
 
 def _validate_gate_ladder(config: RunConfig) -> None:
-    """校验 CE-Gate 信息量阶梯与块序贯参数。
+    """校验 CE-Gate 信息量阶梯参数。
 
     参数:
         config: 待校验的配置实例。
@@ -369,11 +367,8 @@ def _validate_gate_ladder(config: RunConfig) -> None:
     异常:
         ValueError: 任一阶梯参数不合法。
     """
-    if config.gate_block <= 0 or config.gate_n_max < config.gate_block:
+    if config.gate_n_max <= 0:
-        raise ValueError(
+        raise ValueError(f"需 gate_n_max > 0，实际: n_max={config.gate_n_max}")
-            f"需 0 < gate_block <= gate_n_max，"
-            f"实际: block={config.gate_block}, n_max={config.gate_n_max}"
-        )
     if not (0 <= config.gate_p_low < config.gate_p_high <= 1):
         raise ValueError(
             f"需 0 <= gate_p_low < gate_p_high <= 1，"

app/harness/validate.py

@@ -1,15 +1,15 @@
-"""async 块序贯验证编排 — CE-Gate 局部验证的唯一独立子编排器。
+"""async 连续并发 gate 验证编排 — CE-Gate 局部验证的唯一独立子编排器。
 
-从 TRM4 core/harness/validate.py (626 行) 迁移，重大重构：
+多题型全部 (单元, 臂) 任务共享题槽并发（validate_skills_concurrent），
-- 同步 → async（run_inference 注入为 async callable）
+统计推进不按到达序，而按预声明的阶梯序前缀消费（_advance_prefix）：
-- _classify_quadrants → core.evolution.classify_quadrants 纯函数
+base 臂缓存命中瞬间返回、cand 臂必新鲜跑，两臂延迟不对称，按到达序判定
-- 配对逻辑 → 复用 core.evolution.pair_block + 本地证据行组装
+会系统性偏向早到翻转；前缀消费把判定顺序钉回阶梯序，anytime-valid 无条件
-- _load_run_rows / _candidate_correctness_from_db → 共享 log.query()
+成立（核心算法保真 #6，语义修订：块序贯 → 阶梯序前缀逐对序贯）。
-- materialize_candidate_skill 保持同步（纯文件操作）
 
-基线与候选在同一阶梯前缀上逐块配对，只数翻转（基线错→候选对 = W，
+基线与候选在同一阶梯前缀上逐单元配对，只数翻转（基线错→候选对 = W，
-基线对→候选错 = L），每块结束调 gate_decision 做四出口判定。
+基线对→候选错 = L），每消费一个单元调一次 gate_decision 做四出口判定，
-基线侧逐题对错走 BaselineCache 内容寻址缓存，miss 才新鲜跑。
+过线即冻结、τ 之后的 in-flight 结果整体丢弃。基线侧单元级对错走
+BaselineCache 内容寻址缓存，miss 才新鲜跑；INFRA 单元不写缓存、从配对剔除。
 判定逻辑全部在 core/evolution/gate，本模块只负责推理编排与证据收集。
 """
 
@@ -26,7 +26,7 @@ from typing import TYPE_CHECKING, Any, Protocol, runtime_checkable
 from loguru import logger
 
 from app.harness.gate_ladder import BaselineCache, skill_hash
-from app.harness.question_units import build_units, flatten_units, unit_correctness_view
+from app.harness.question_units import build_units, unit_correctness_view
 from core.evolution import (
     INFRA_STOP_REASONS,
     GateParams,
@@ -68,7 +68,7 @@ class RunInferenceFn(Protocol):
 
     调用方（runner）负责绑定 llm、tool_dispatch_fn、prompt_builder、
     log、concurrency、max_steps、skill_mode 等共享依赖。
-    validate 侧只传 questions、run_id、skills_dir 三个逐块变化的参数。
+    validate 侧只传 questions、run_id、skills_dir 三个逐任务变化的参数。
     """
 
     async def __call__(
@@ -85,21 +85,6 @@ class RunInferenceFn(Protocol):
 # ---------------------------------------------------------------------------
 
 
-@dataclass(frozen=True)
-class InferenceRunConfig:
-    """一次推理运行的配置三元组，把"如何跑推理"内聚成一组。
-
-    字段:
-        concurrency: 推理并发度。
-        max_steps: 单题最大推理步数。
-        skill_mode: 推理 skill 模式（"auto" / "manual" / "none"）。
-    """
-
-    concurrency: int
-    max_steps: int
-    skill_mode: str
-
-
 @dataclass
 class ValidationOutcome:
     """CE-Gate 局部验证结果：三态动作 + e-process 证据（单元口径）+ 逐题溯源对错。
@@ -260,23 +245,6 @@ def _infra_question_ids_from_db(
     }
 
 
-def _count_infra_units(units: list[QuestionUnit], infra_qids: set[str]) -> int:
-    """统计含 INFRA record 的 unit 数（一个 unit 任一题 INFRA 即计 1）。
-
-    使护栏分子与分母（r.total，unit 粒度）同口径：AR pair 一 unit 含两 record，
-    逐 record 计数会放大分子致 gate_guard_err 误触发，破坏 unit 粒度一致性
-    （核心算法保真 #5/#6）。
-
-    参数:
-        units: 当前块的单元列表（single 或 AR pair）。
-        infra_qids: 本 run 中 stop_reason 属 INFRA 故障族的 question_id 集合。
-
-    返回:
-        含至少一题 INFRA 的 unit 数。
-    """
-    return sum(1 for u in units if any(q.question_id in infra_qids for q in u.questions))
-
-
 def _candidate_correctness_from_db(
     log: HarnessLog,
     run_id: str,
@@ -296,164 +264,13 @@ def _candidate_correctness_from_db(
     return {q.question_id: rows.get(q.question_id, {}).get("_correct", False) for q in chunk}
 
 
-# ---------------------------------------------------------------------------
-# 块级 async 函数
-# ---------------------------------------------------------------------------
-
-
-async def _resolve_baseline_block(
-    units: list[QuestionUnit],
-    task_type: str,
-    s_hash: str,
-    prompts_version: str,
-    baseline_cache: BaselineCache,
-    base_skills_dir: Path,
-    run_inference: RunInferenceFn,
-    log: HarnessLog,
-    run_id: str,
-) -> tuple[dict[str, bool], list[QuestionUnit], int, int]:
-    """基线侧处理一个块：缓存优先（unit 键），miss 的单元新鲜跑基线版本并回写缓存。
-
-    缓存以 unit_id 为键、存单元级对错（AR pair 双向 AND 折叠后一个布尔）。
-    miss 的单元展开为逐题送推理，读回逐题预测后经 unit_correctness_view 折叠成
-    单元级对错再写缓存（核心算法保真 #5）。逐题 predictions 仍逐题落库溯源。
-
-    INFRA 隔离（算法 #6）：miss 单元内**任一题** stop_reason ∈ {error, parse_error}
-    即判定该单元为 INFRA 故障——**不写 BaselineCache**（否则瞬时故障永久污染基线
-    快照）、**不入 b_units**、并从返回的有效单元集中剔除，避免污染 W/L 翻转与配对。
-    命中缓存的单元恒为有效（此前已成功验证过）。
-
-    参数:
-        units: 当前块的单元列表（single 或 AR pair）。
-        task_type: 当前验证题型（缓存键成分）。
-        s_hash: 基线侧生效 skill 的内容哈希（缓存键成分）。
-        prompts_version: 当前 prompts 版本（缓存键成分）。
-        baseline_cache: 基线侧单元级对错缓存（键含 unit_id）。
-        base_skills_dir: 基线 skills 版本目录。
-        run_inference: 注入的 async 推理函数。
-        log: HarnessLog 共享实例（推理后读预测）。
-        run_id: 本块基线 run_id。
-
-    返回:
-        (b_units, valid_units, errors_inc, denom_inc)：块内有效 unit_id -> 基线单元
-        对错、剔除 INFRA 后的有效单元列表、本块新增的 INFRA error 计数与推理题次
-        分母增量（全命中时为 0, 0）。
-    """
-    miss_units = [
-        u
-        for u in units
-        if baseline_cache.get(task_type, s_hash, prompts_version, u.unit_id) is None
-    ]
-    errors_inc = 0
-    denom_inc = 0
-    infra_qids: set[str] = set()
-    if miss_units:
-        miss_questions = flatten_units(miss_units)
-        r_b = await run_inference(miss_questions, run_id=run_id, skills_dir=base_skills_dir)
-        infra_qids = _infra_question_ids_from_db(log, r_b.run_id, miss_questions)
-        # 护栏分子与分母（r.total，unit 粒度）同口径：含 INFRA record 的 unit 计 1，
-        # 避免 AR pair（一 unit 两 record）逐 record 计数放大分子致误触发；仍涵盖
-        # error + parse_error（_infra_question_ids_from_db 口径），parse_error 风暴不被绕过。
-        errors_inc = _count_infra_units(miss_units, infra_qids)
-        denom_inc = r_b.total
-        fresh_per_q = _candidate_correctness_from_db(log, r_b.run_id, miss_questions)
-        fresh_units = unit_correctness_view(miss_units, fresh_per_q)
-        # 只回写非 INFRA 单元；INFRA 单元不入缓存（不永久污染基线快照）
-        for u in miss_units:
-            if any(q.question_id in infra_qids for q in u.questions):
-                continue
-            baseline_cache.put(task_type, s_hash, prompts_version, u.unit_id, fresh_units[u.unit_id])
-
-    valid_units = [
-        u for u in units if not any(q.question_id in infra_qids for q in u.questions)
-    ]
-
-    b_units: dict[str, bool] = {}
-    for u in valid_units:
-        val = baseline_cache.get(task_type, s_hash, prompts_version, u.unit_id)
-        assert val is not None, f"基线缓存补齐后仍有 miss: unit={u.unit_id} run_id={run_id}"
-        b_units[u.unit_id] = val
-    return b_units, valid_units, errors_inc, denom_inc
-
-
-async def _run_candidate_block(
-    units: list[QuestionUnit],
-    cand_dir: Path,
-    run_inference: RunInferenceFn,
-    log: HarnessLog,
-    run_id: str,
-) -> tuple[dict[str, bool], int, int]:
-    """候选侧处理一个块：单元展开为逐题全块新鲜跑候选版本并从 db 读逐题对错。
-
-    返回逐题对错映射（question_id -> bool），折叠为单元视图交由调用方完成，
-    逐题结果同时用于 candidate_correctness 溯源与二轨 correctness 合并。
-
-    参数:
-        units: 当前块的单元列表。
-        cand_dir: 已物化的候选 skills 目录。
-        run_inference: 注入的 async 推理函数。
-        log: HarnessLog 共享实例（推理后读预测）。
-        run_id: 本块候选 run_id。
-
-    返回:
-        (c_per_q, errors_inc, denom_inc)：块内 question_id -> 候选对错。
-    """
-    questions = flatten_units(units)
-    r_c = await run_inference(questions, run_id=run_id, skills_dir=cand_dir)
-    c_per_q = _candidate_correctness_from_db(log, r_c.run_id, questions)
-    infra_qids = _infra_question_ids_from_db(log, r_c.run_id, questions)
-    # 护栏分子与分母（r.total，unit 粒度）同口径：含 INFRA record 的 unit 计 1
-    # （见 _count_infra_units），涵盖 error + parse_error。
-    errors_inc = _count_infra_units(units, infra_qids)
-    return c_per_q, errors_inc, r_c.total
-
-
-def _build_evidence_rows(
-    units: list[QuestionUnit],
-    b_units: dict[str, bool],
-    c_units: dict[str, bool],
-    task_type: str,
-    block_idx: int,
-) -> list[dict]:
-    """组装一个块的 gate_evidence 单元级证据行。
-
-    证据行按 unit 口径（question_id 字段存 unit_id、correct 存单元级对错），
-    与 e-process 判定同粒度；逐题预测明细仍在 predictions 表逐题溯源。
-    e_value 留 None 待块判定后回填，stop_reason 留空串待终态回填。
-
-    参数:
-        units: 当前块的单元列表。
-        b_units: 块内 unit_id -> 基线单元对错。
-        c_units: 块内 unit_id -> 候选单元对错。
-        task_type: 当前验证题型。
-        block_idx: 当前块序号。
-
-    返回:
-        单元级证据行列表。
-    """
-    return [
-        {
-            "question_id": u.unit_id,
-            "task_type": task_type,
-            # 落库列已更名 ladder_rank(阶梯序号);旧块路径此处值仍为块号,
-            # 仅键名对齐 gate_evidence 表结构以保持落库兼容。
-            "ladder_rank": block_idx,
-            "baseline_correct": b_units[u.unit_id],
-            "candidate_correct": c_units[u.unit_id],
-            "e_value": None,
-            "stop_reason": "",
-        }
-        for u in units
-    ]
-
-
 # ---------------------------------------------------------------------------
 # INFRA 护栏
 # ---------------------------------------------------------------------------
 
 
 def _check_infra_guard(errors: int, infra_denom: int, gate_guard_err: float) -> None:
-    """跨块累计 INFRA 错误率护栏：分母 >=10 且超阈值时 raise。
+    """累计 INFRA 错误率护栏：分母 >=10 且超阈值时 raise。
 
     参数:
         errors: 两侧累计 error 计数。
@@ -484,13 +301,13 @@ def _finalize_outcome(
     evidence_rows: list[dict],
     task_type: str,
 ) -> ValidationOutcome:
-    """将块循环终态判定组装为 ValidationOutcome。
+    """将终态判定组装为 ValidationOutcome。
 
     四象限/准确率/W/L 均按单元口径（base_obs/cand_obs 为 unit_id -> bool），
     candidate_correctness 独立保留逐题溯源（供 runner 二轨合并进 state.correctness）。
 
     参数:
-        verdict: 最后一块的 gate 判定结果。
+        verdict: 终态 gate 判定结果。
         w: 累计 W（基线错→候选对单元翻转）。
         l: 累计 L（基线对→候选错单元翻转）。
         n_used: 已消费的阶梯单元数。
@@ -576,228 +393,6 @@ def _ladder_units(ladder_items: list[GeneratedQuestion]) -> list[QuestionUnit]:
     return units
 
 
-async def _run_local_validation(
-    workspace_dir: Path,
-    cand_dir: Path,
-    base_skills_version: str,
-    task_type: str,
-    base_skill_content: str,
-    units: list[QuestionUnit],
-    gate_params: GateParams,
-    gate_block: int,
-    gate_guard_err: float,
-    baseline_cache: BaselineCache,
-    prompts_version: str,
-    run_inference: RunInferenceFn,
-    log: HarnessLog,
-    gate_run_prefix: str,
-) -> ValidationOutcome:
-    """块序贯循环主体：逐块基线（缓存优先）/候选按单元配对推理，块间 e-process 判定。
-
-    按 gate_block 切**单元**前缀（AR pair 整锁在同一块，不跨块拆分），每块先补齐
-    基线侧缓存 miss（新鲜跑基线版本并按 unit_id 写 BaselineCache），再全块跑候选，
-    折叠成单元视图后配对累计 W/L 调 gate_decision；非 continue 即早停。单元尽时
-    最后一块的判定即终态（n_remaining=0 走 provisional/inertia 分支），无循环外补判。
-
-    参数:
-        workspace_dir: Workspace 根目录。
-        cand_dir: 已物化的候选 skills 目录。
-        base_skills_version: 基线 skills 版本名。
-        task_type: 当前验证题型。
-        base_skill_content: 基线侧生效 skill 全文（skill_hash 作缓存键成分）。
-        units: 已截断到 gate_n_max 的阶梯单元序（single 或 AR pair）。
-        gate_params: e-process 判据阈值组。
-        gate_block: 块大小（单位为**单元数**）。
-        gate_guard_err: 跨块累计 INFRA 错误率护栏（分母 >=10 才触发）。
-        baseline_cache: 基线侧单元级对错缓存（键含 unit_id）。
-        prompts_version: 当前 prompts 版本（缓存键成分）。
-        run_inference: 注入的 async 推理函数。
-        log: HarnessLog 共享实例。
-        gate_run_prefix: 块 run_id 前缀（含 "_gate_" 标记）。
-
-    返回:
-        ValidationOutcome。
-
-    关键实现:
-        INFRA 护栏跨块累计基线+候选两侧的 error 计数，分母（总推理题次，仍逐题计）
-        >=10 且错误率超 gate_guard_err 时直接 raise，避免坏批次污染判定。
-    """
-    w = 0
-    l = 0  # noqa: E741
-    n_used = 0
-    n_excluded = 0  # 累计被 INFRA 隔离剔除的单元数（从阶梯分母扣除）
-    errors = 0
-    infra_denom = 0
-    evidence_rows: list[dict] = []
-    base_obs: dict[str, bool] = {}
-    cand_obs: dict[str, bool] = {}
-    candidate_per_q: dict[str, bool] = {}
-    s_hash = skill_hash(base_skill_content)
-    base_skills_dir = workspace_dir / "skills" / base_skills_version
-    unit_chunks = [units[i : i + gate_block] for i in range(0, len(units), gate_block)]
-    n_plan = len(units)
-    verdict: GateVerdict | None = None
-
-    for block_idx, unit_chunk in enumerate(unit_chunks):
-        # Phase 1: 基线侧（缓存优先，miss 新鲜跑，INFRA 单元剔除）
-        b_units, valid_chunk, err_b, den_b = await _resolve_baseline_block(
-            units=unit_chunk,
-            task_type=task_type,
-            s_hash=s_hash,
-            prompts_version=prompts_version,
-            baseline_cache=baseline_cache,
-            base_skills_dir=base_skills_dir,
-            run_inference=run_inference,
-            log=log,
-            run_id=f"{gate_run_prefix}_b{block_idx}_base",
-        )
-        # 本块全 INFRA：无有效单元可配对——候选无需空跑，仅把基线侧错误计入护栏后
-        # 累计剔除数进入下一块（护栏仍能在整轮 INFRA 错误率超阈值时熔断）。
-        n_excluded += len(unit_chunk) - len(valid_chunk)
-        if not valid_chunk:
-            errors += err_b
-            infra_denom += den_b
-            _check_infra_guard(errors, infra_denom, gate_guard_err)
-            continue
-
-        # 候选侧只跑基线侧判定有效（非 INFRA）的单元，保证配对 unit_ids 两侧一致
-        c_per_q, err_c, den_c = await _run_candidate_block(
-            units=valid_chunk,
-            cand_dir=cand_dir,
-            run_inference=run_inference,
-            log=log,
-            run_id=f"{gate_run_prefix}_b{block_idx}_cand",
-        )
-
-        # Phase 2: INFRA 护栏（跨块累计，分母 >=10 才触发）——写缓存前置于此已由
-        # _resolve_baseline_block 保证 INFRA 单元不落缓存，此处仅做整轮错误率熔断。
-        errors += err_b + err_c
-        infra_denom += den_b + den_c
-        _check_infra_guard(errors, infra_denom, gate_guard_err)
-
-        # Phase 3: 折叠成单元视图 + 配对 + 证据行 + 块间判定（均用有效单元）
-        c_units = unit_correctness_view(valid_chunk, c_per_q)
-        candidate_per_q.update(c_per_q)
-        unit_ids = [u.unit_id for u in valid_chunk]
-        pair_result = pair_block(b_units, c_units, unit_ids)
-        for uid, (b, c) in pair_result.observed.items():
-            base_obs[uid] = b
-            cand_obs[uid] = c
-
-        block_rows = _build_evidence_rows(valid_chunk, b_units, c_units, task_type, block_idx)
-
-        w += pair_result.w
-        l += pair_result.l  # noqa: E741
-        n_used += len(valid_chunk)
-        # 阶梯剩余按扣除 INFRA 后的有效分母计：n_remaining = (n_plan - n_excluded) - n_used
-        verdict = gate_decision(w, l, n_used, (n_plan - n_excluded) - n_used, params=gate_params)
-
-        for row in block_rows:
-            row["e_value"] = verdict.e_value
-        evidence_rows.extend(block_rows)
-
-        if verdict.decision != "continue":
-            break
-
-    # verdict 仍为 None ⟺ 全部单元被 INFRA 排除（空 ladder 已在入口拒绝）。
-    # 明确失败，避免落到误导性的"空阶梯"断言而无法定位为 INFRA 原因。
-    if verdict is None:
-        raise RuntimeError("gate 阶梯所有 unit 被判为 INFRA 排除，无法验证（检查推理基础设施）")
-    # 最后一块判定即终态（n_remaining=0 → provisional/inertia）
-    return _finalize_outcome(
-        verdict=verdict,
-        w=w,
-        l=l,
-        n_used=n_used,
-        n_plan=n_plan,
-        base_obs=base_obs,
-        cand_obs=cand_obs,
-        candidate_per_q=candidate_per_q,
-        evidence_rows=evidence_rows,
-        task_type=task_type,
-    )
-
-
-async def validate_skill_local(
-    workspace_dir: Path,
-    base_skills_version: str,
-    task_type: str,
-    target_file: str,
-    candidate_content: str,
-    base_skill_content: str,
-    ladder_items: list[GeneratedQuestion],
-    gate_params: GateParams,
-    gate_block: int,
-    gate_n_max: int,
-    gate_guard_err: float,
-    baseline_cache: BaselineCache,
-    prompts_version: str,
-    run_inference: RunInferenceFn,
-    log: HarnessLog,
-    gate_run_prefix: str,
-) -> ValidationOutcome:
-    """块序贯配对验证：阶梯出题，基线/候选逐块配对，e-process 四出口早停。
-
-    参数:
-        workspace_dir: workspace 根目录。
-        base_skills_version: 基线 skills 版本名（候选物化复制源）。
-        task_type: 待验证题型。
-        target_file: fallback 解析后该题型的真实生效 skill 文件名
-            （record.target_file，可能是共享 default-strategy.md）；
-            候选物化写此文件，与 accept 路径同源。
-        candidate_content: 候选 skill 全文。
-        base_skill_content: 基线侧该题型解析后生效 skill 文件全文
-            （skill_hash(base_skill_content) 作 BaselineCache 键成分）。
-        ladder_items: 阶梯序题目列表（已排除本 step 案例包题）。
-        gate_params: e-process 判据阈值组。
-        gate_block: 块大小（单位为**单元数**，AR pair 整锁不跨块拆）。
-        gate_n_max: 单 gate 单元数上限（阶梯截断到此数量个单元）。
-        gate_guard_err: 跨块累计 INFRA 错误率护栏（分母 >=10 才触发）。
-        baseline_cache: 基线侧单元级对错缓存（键含 unit_id）。
-        prompts_version: 当前 prompts 版本（缓存键成分）。
-        run_inference: 注入的 async 推理函数（RunInferenceFn 协议）。
-        log: HarnessLog 共享实例（供 DB 回读逐题对错）。
-        gate_run_prefix: gate 内推理 run_id 前缀，必须含 "_gate_"
-            （防泄露过滤靠它识别）。块 run_id = f"{prefix}_b{block_idx}_{arm}"。
-
-    返回:
-        ValidationOutcome。单元级证据记入 outcome.evidence_rows 随结果返回，
-        gate_evidence 落库由调用方（runner）负责。
-    """
-    if "_gate_" not in gate_run_prefix:
-        raise ValueError(f"gate_run_prefix 必须含 '_gate_'（防泄露过滤依赖）: {gate_run_prefix!r}")
-    if not ladder_items:
-        raise ValueError(f"task_type={task_type} 阶梯为空，无法验证")
-
-    # 阶梯题序聚合为单元并按信息阶梯序截断到 gate_n_max 个单元（AR pair 整锁不拆）
-    units = _ladder_units(ladder_items)[:gate_n_max]
-    cand_dir = materialize_candidate_skill(
-        workspace_dir, base_skills_version, target_file, candidate_content
-    )
-    try:
-        return await _run_local_validation(
-            workspace_dir=workspace_dir,
-            cand_dir=cand_dir,
-            base_skills_version=base_skills_version,
-            task_type=task_type,
-            base_skill_content=base_skill_content,
-            units=units,
-            gate_params=gate_params,
-            gate_block=gate_block,
-            gate_guard_err=gate_guard_err,
-            baseline_cache=baseline_cache,
-            prompts_version=prompts_version,
-            run_inference=run_inference,
-            log=log,
-            gate_run_prefix=gate_run_prefix,
-        )
-    finally:
-        try:
-            shutil.rmtree(cand_dir)
-        except OSError as e:
-            logger.warning("候选临时目录清理失败 {}: {}", cand_dir, e)
-
-
 # ---------------------------------------------------------------------------
 # 连续并发 gate:数据结构 + 前缀消费(algo #6 语义修订:块序贯 → 阶梯序前缀逐对序贯)
 # ---------------------------------------------------------------------------

config/default.yaml

@@ -42,7 +42,6 @@ harness:
   gate_delta_min: 0.02
   gate_lambda_dir: -0.642
   gate_e_rollback: 10.0
-  gate_block: 8
   gate_n_max: 40
   gate_p_low: 0.05
   gate_p_high: 0.95

config/question_gen_180_补.yaml

@@ -39,7 +39,6 @@ harness:
   gate_delta_min: 0.02
   gate_lambda_dir: -0.642
   gate_e_rollback: 10.0
-  gate_block: 8
   gate_n_max: 40
   gate_p_low: 0.05
   gate_p_high: 0.95

config/question_gen_360.yaml

@@ -42,7 +42,6 @@ harness:
   gate_delta_min: 0.02
   gate_lambda_dir: -0.642
   gate_e_rollback: 10.0
-  gate_block: 8
   gate_n_max: 40
   gate_p_low: 0.05
   gate_p_high: 0.95

config/train_action_recognition.yaml

@@ -22,7 +22,6 @@ harness:
   gate_delta_min: 0.02
   gate_lambda_dir: -0.642
   gate_e_rollback: 10.0
-  gate_block: 8
   gate_n_max: 40
   gate_p_low: 0.05
   gate_p_high: 0.95

config/train_ar30.yaml

@@ -23,7 +23,6 @@ harness:
   gate_delta_min: 0.02
   gate_lambda_dir: -0.642
   gate_e_rollback: 10.0
-  gate_block: 8
   gate_n_max: 40
   gate_p_low: 0.05
   gate_p_high: 0.95

config/train_videomme.yaml

@@ -10,8 +10,8 @@ harness:
   workspace_dir: "workspaces/train-videomme"
   store_dir: store
   mode: train
-  run_id: train_videomme_v1
+  run_id: train_videomme_v2
-  concurrency: 24
+  concurrency: 32
   max_steps: 40
   skill_mode: auto
   n_samples: 0
@@ -26,7 +26,6 @@ harness:
   gate_delta_min: 0.02
   gate_lambda_dir: -0.642
   gate_e_rollback: 10.0
-  gate_block: 8
   gate_n_max: 40
   gate_p_low: 0.05
   gate_p_high: 0.95
@@ -51,8 +50,10 @@ harness:
   # 可训练性预检（WP3）：val 单元 < eval_min_per_class 或 非test单元 < trainable_min_units 的题型剔除
   eval_min_per_class: 2
   trainable_min_units: 8
-  # mini-batch
+  # mini-batch —— 对齐 TRM4 正式实验 batch=40（sh --batch-size 40 覆盖 yaml 15 的最终生效值）：
-  batch_size: 10
+  # 8 可训题型 × 每型约 5 题/step，保住题型级诊断信号；同时 steps/epoch 180/40≈5，
+  # 进化/gate 验证轮数比 batch=10 少 4 倍。
+  batch_size: 40
   min_class_per_batch: 2
   batch_correct_ratio: 0.5
   momentum_samples: 20

tests/integration/test_checkpoint_pair.py

@@ -125,7 +125,6 @@ class _FakeConfig:
     gate_delta_min: float = 0.02
     gate_lambda_dir: float = -3.0
     gate_e_rollback: float = 10.0
-    gate_block: int = 4
     gate_n_max: int = 40
     gate_p_low: float = 0.1
     gate_p_high: float = 0.9

tests/integration/test_v3_contract_e2e.py

@@ -338,7 +338,7 @@ class TestInferenceUnitAggregationEndToEnd:
 
     def _assert_all_persisted(self, log: HarnessLog, questions: list[GeneratedQuestion]) -> None:
         """逐题溯源保留：含被剔除的孤儿题在内，每题仍逐题落 predictions。"""
-        rows = log.query("SELECT * FROM predictions WHERE run_id = ?", ("test-run",))
+        rows = log.query("SELECT * FROM predictions WHERE run_id = ?", ("run-v3-contract",))
         persisted = {r["question_id"] for r in rows}
         assert "orphan_o" in persisted, "孤儿题未逐题落库（逐题溯源被破坏）"
         assert persisted == {q.question_id for q in questions}, "逐题落库题数与输入不符"

tests/unit/test_gate_unit_scope.py

@@ -1,8 +1,9 @@
-"""tests/unit/test_gate_block_unit.py — gate 块实际执行路径按 unit 跑。
+"""tests/unit/test_gate_unit_scope.py — gate 真实执行路径按 unit 口径跑。
 
-针对 app/harness/validate.py::validate_skill_local（真实 gate 执行路径），
+迁移自块序贯版 test_gate_block_unit.py（载体 validate_skill_local，Task 6 删除）：
-断言混格阶梯下 gate 块按 unit 口径运行：baseline_cache 键含 unit_id、
+针对 app/harness/validate.py::validate_skills_concurrent（连续并发 gate 真实路径），
-n_used 按 unit 累加、pair_block 折叠 AR pair、逐题 predictions 仍溯源。
+断言混格阶梯下 gate 按 unit 口径运行：baseline_cache 键含 unit_id、n_used 按
+unit 累加、pair_block 折叠 AR pair、逐题 predictions 仍溯源。
 核心算法保真 #5（信息阶梯 e-process 口径从 question_id 迁至 unit_id）。
 """
 
@@ -15,7 +16,7 @@ import pytest
 from app.harness.gate_ladder import BaselineCache, skill_hash
 from app.harness.inference import PREDICTIONS_SCHEMA, InferenceResult
 from app.harness.log import HarnessLog
-from app.harness.validate import _ladder_units, validate_skill_local
+from app.harness.validate import GateSpec, _ladder_units, validate_skills_concurrent
 from core.evolution import GateParams
 from core.types import GeneratedQuestion
 
@@ -136,6 +137,35 @@ def _make_mock_run_inference(
     return mock_fn, call_log
 
 
+def _mk_spec(ladder: list[GeneratedQuestion]) -> GateSpec:
+    """由混格阶梯题序构造单题型 GateSpec（units 经 _ladder_units 聚合）。"""
+    return GateSpec(
+        task_type="temporal",
+        target_file="temporal.md",
+        candidate_content="improved skill",
+        base_skill_content="baseline skill content",
+        units=tuple(_ladder_units(ladder)),
+        gate_run_prefix="step1_gate_test",
+    )
+
+
+async def _run_gate(workspace: Path, spec: GateSpec, mock_fn, log: HarnessLog, cache, params):
+    """跑单 spec 的 validate_skills_concurrent 并返回该题型的 outcome。"""
+    outcomes = await validate_skills_concurrent(
+        workspace_dir=workspace,
+        base_skills_version="v1",
+        specs=[spec],
+        gate_params=params,
+        gate_guard_err=0.5,
+        baseline_cache=cache,
+        prompts_version="p1",
+        run_inference=mock_fn,
+        log=log,
+        concurrency=8,
+    )
+    return outcomes[spec.task_type]
+
+
 class TestLadderUnits:
     """_ladder_units：阶梯题序聚合为单元并保持信息阶梯序。"""
 
@@ -177,7 +207,7 @@ class TestLadderUnits:
 
 @pytest.mark.asyncio
 async def test_gate_n_used_counts_units_not_questions(tmp_path: Path) -> None:
-    """混格阶梯（1 pair + 2 single）→ n_used=3 单元，非 4 题。"""
+    """混格阶梯（1 pair + 2 single）→ n_used=3 单元，非 4 题（迁移自块序贯版）。"""
     workspace = _setup_workspace(tmp_path)
     log = _make_log(workspace)
     cache = BaselineCache(workspace / "baseline_cache.json")
@@ -186,7 +216,7 @@ async def test_gate_n_used_counts_units_not_questions(tmp_path: Path) -> None:
     # 基线全错、候选全对 → 3 单元齐翻 W=3
     baseline = {"p1_o": False, "p1_m": False, "s0": False, "s1": False}
     candidate = {"p1_o": True, "p1_m": True, "s0": True, "s1": True}
-    mock_fn, call_log = _make_mock_run_inference(log, baseline, candidate)
+    mock_fn, _ = _make_mock_run_inference(log, baseline, candidate)
 
     accept_params = GateParams(
         e_confirm=15.0,
@@ -197,30 +227,14 @@ async def test_gate_n_used_counts_units_not_questions(tmp_path: Path) -> None:
         e_rollback=10.0,
     )
     try:
-        outcome = await validate_skill_local(
+        outcome = await _run_gate(workspace, _mk_spec(ladder), mock_fn, log, cache, accept_params)
-            workspace_dir=workspace,
-            base_skills_version="v1",
-            task_type="temporal",
-            target_file="temporal.md",
-            candidate_content="improved skill",
-            base_skill_content="baseline skill content",
-            ladder_items=ladder,
-            gate_params=accept_params,
-            gate_block=10,
-            gate_n_max=20,
-            gate_guard_err=0.5,
-            baseline_cache=cache,
-            prompts_version="p1",
-            run_inference=mock_fn,
-            log=log,
-            gate_run_prefix="step1_gate_test",
-        )
         # n_used 按 unit 计（3），W 按 unit 计（3）
         assert outcome.n_used == 3
         assert outcome.w == 3
         assert outcome.l == 0
-        # 证据行按 unit 口径（3 行）
+        # 证据行按 unit 口径（3 行），ladder_rank 沿阶梯序连续
         assert len(outcome.evidence_rows) == 3
+        assert [r["ladder_rank"] for r in outcome.evidence_rows] == [0, 1, 2]
         # baseline_cache 键含 unit_id：pair 用 pair_id、single 用 question_id
         s_hash = skill_hash("baseline skill content")
         assert cache.get("temporal", s_hash, "p1", "p1") is False
@@ -235,84 +249,62 @@ async def test_gate_n_used_counts_units_not_questions(tmp_path: Path) -> None:
 
 @pytest.mark.asyncio
 async def test_gate_pair_partial_flip_not_counted(tmp_path: Path) -> None:
-    """AR pair 候选仅单向翻(T,F)→单元仍错，W 不被单题污染。"""
+    """AR pair 候选仅单向翻(T,F)→单元仍错，W 不被单题污染（迁移自块序贯版）。
+
+    前缀逐单元判定下 2 单元小阶梯会在首单元 futility 早停，观测不到 pair 语义；
+    补 2 个 single 拉长阶梯：4 单元中 3 个 single 翻转 → W=3（pair 不计入），
+    candidate_acc = 3/4。
+    """
     workspace = _setup_workspace(tmp_path)
     log = _make_log(workspace)
     cache = BaselineCache(workspace / "baseline_cache.json")
-    ladder = [*_pair("p1"), _single("s0")]
+    ladder = [*_pair("p1"), _single("s0"), _single("s1"), _single("s2")]
 
-    baseline = {"p1_o": False, "p1_m": False, "s0": False}
+    baseline = {"p1_o": False, "p1_m": False, "s0": False, "s1": False, "s2": False}
-    # pair 只翻一半（p1_o 对、p1_m 错）→ 单元 AND 仍错；s0 翻对
+    # pair 只翻一半（p1_o 对、p1_m 错）→ 单元 AND 仍错；singles 全翻对
-    candidate = {"p1_o": True, "p1_m": False, "s0": True}
+    candidate = {"p1_o": True, "p1_m": False, "s0": True, "s1": True, "s2": True}
     mock_fn, _ = _make_mock_run_inference(log, baseline, candidate)
 
     try:
-        outcome = await validate_skill_local(
+        outcome = await _run_gate(
-            workspace_dir=workspace,
+            workspace, _mk_spec(ladder), mock_fn, log, cache, _DEFAULT_GATE_PARAMS
-            base_skills_version="v1",
-            task_type="temporal",
-            target_file="temporal.md",
-            candidate_content="improved skill",
-            base_skill_content="baseline skill content",
-            ladder_items=ladder,
-            gate_params=_DEFAULT_GATE_PARAMS,
-            gate_block=10,
-            gate_n_max=20,
-            gate_guard_err=0.5,
-            baseline_cache=cache,
-            prompts_version="p1",
-            run_inference=mock_fn,
-            log=log,
-            gate_run_prefix="step1_gate_test",
         )
-        # 只有 s0 单元翻转，pair 单元不计 W（保真 #5：不被 P/Q 单题污染）
+        # 只有 single 单元翻转，pair 单元不计 W（保真 #5：不被 P/Q 单题污染）
-        assert outcome.w == 1
+        assert outcome.w == 3
         assert outcome.l == 0
-        assert outcome.n_used == 2
+        assert outcome.n_used == 4
-        # candidate_acc 分母按 unit（2 单元，1 对）→ 0.5
+        # candidate_acc 分母按 unit（4 单元，1 对）→ 3/4
-        assert outcome.candidate_acc == 0.5
+        assert outcome.candidate_acc == 0.75
     finally:
         log.close()
 
 
 @pytest.mark.asyncio
 async def test_gate_baseline_cache_hit_by_unit(tmp_path: Path) -> None:
-    """基线缓存按 unit_id 预填充 → 基线侧全命中不发起推理。"""
+    """基线缓存按 unit_id 预填充 → 基线侧全命中不发起推理（迁移自块序贯版）。
+
+    阶梯补长到 4 单元避免首单元 futility 早停，覆盖 pair 与 single 两种 unit 键。
+    """
     workspace = _setup_workspace(tmp_path)
     log = _make_log(workspace)
     cache = BaselineCache(workspace / "baseline_cache.json")
-    ladder = [*_pair("p1"), _single("s0")]
+    ladder = [*_pair("p1"), _single("s0"), _single("s1"), _single("s2")]
 
     s_hash = skill_hash("baseline skill content")
     # 按 unit_id 预填充（pair→pair_id，single→question_id），全错
-    cache.put("temporal", s_hash, "p1", "p1", False)
+    for unit_id in ("p1", "s0", "s1", "s2"):
-    cache.put("temporal", s_hash, "p1", "s0", False)
+        cache.put("temporal", s_hash, "p1", unit_id, False)
 
-    baseline = {"p1_o": False, "p1_m": False, "s0": False}
+    baseline = {"p1_o": False, "p1_m": False, "s0": False, "s1": False, "s2": False}
-    candidate = {"p1_o": True, "p1_m": True, "s0": True}
+    candidate = {"p1_o": True, "p1_m": True, "s0": True, "s1": True, "s2": True}
     mock_fn, call_log = _make_mock_run_inference(log, baseline, candidate)
 
     try:
-        outcome = await validate_skill_local(
+        outcome = await _run_gate(
-            workspace_dir=workspace,
+            workspace, _mk_spec(ladder), mock_fn, log, cache, _DEFAULT_GATE_PARAMS
-            base_skills_version="v1",
-            task_type="temporal",
-            target_file="temporal.md",
-            candidate_content="improved skill",
-            base_skill_content="baseline skill content",
-            ladder_items=ladder,
-            gate_params=_DEFAULT_GATE_PARAMS,
-            gate_block=10,
-            gate_n_max=20,
-            gate_guard_err=0.5,
-            baseline_cache=cache,
-            prompts_version="p1",
-            run_inference=mock_fn,
-            log=log,
-            gate_run_prefix="step1_gate_test",
         )
         base_calls = [c for c in call_log if c["run_id"].endswith("_base")]
         assert base_calls == [], "unit 键全命中不应发起基线推理"
-        assert outcome.n_used == 2
+        assert outcome.n_used == 4
     finally:
         log.close()

tests/unit/test_harness_checkpoint.py

@@ -171,7 +171,6 @@ class _FakeConfig:
     gate_delta_min: float = 0.02
     gate_lambda_dir: float = -3.0
     gate_e_rollback: float = 10.0
-    gate_block: int = 4
     gate_n_max: int = 40
     gate_p_low: float = 0.1
     gate_p_high: float = 0.9
@@ -306,7 +305,6 @@ class TestFingerprintStructuralVsDecision:
             "gate_delta_min",
             "gate_lambda_dir",
             "gate_e_rollback",
-            "gate_block",
             "gate_n_max",
             "gate_p_low",
             "gate_p_high",

tests/unit/test_harness_config.py

@@ -50,7 +50,6 @@ def _valid_kwargs() -> dict:
         "gate_delta_min": 0.02,
         "gate_lambda_dir": -0.642,
         "gate_e_rollback": 10.0,
-        "gate_block": 8,
         "gate_n_max": 40,
         "gate_p_low": 0.05,
         "gate_p_high": 0.95,
@@ -378,16 +377,16 @@ class TestGateValidation:
         with pytest.raises(ValueError, match="gate_lambda_dir"):
             _validate(cfg)
 
-    def test_block_exceeds_n_max_rejected(self) -> None:
+    def test_n_max_zero_rejected(self) -> None:
-        """gate_block > gate_n_max 应抛出 ValueError。"""
+        """gate_n_max <= 0 应抛出 ValueError（迁移自块序贯版 gate_block 校验）。"""
-        cfg = _make_config(gate_block=50, gate_n_max=40)
+        cfg = _make_config(gate_n_max=0)
-        with pytest.raises(ValueError, match="gate_block"):
+        with pytest.raises(ValueError, match="gate_n_max"):
             _validate(cfg)
 
-    def test_block_zero_rejected(self) -> None:
+    def test_n_max_negative_rejected(self) -> None:
-        """gate_block <= 0 应抛出 ValueError。"""
+        """gate_n_max 为负也应报错。"""
-        cfg = _make_config(gate_block=0)
+        cfg = _make_config(gate_n_max=-1)
-        with pytest.raises(ValueError, match="gate_block"):
+        with pytest.raises(ValueError, match="gate_n_max"):
             _validate(cfg)
 
     def test_p_low_exceeds_p_high_rejected(self) -> None:

tests/unit/test_harness_pools.py

@@ -327,7 +327,6 @@ class TestBuildOrLoadPoolsFrozen:
             gate_delta_min=0.02,
             gate_lambda_dir=-0.642,
             gate_e_rollback=10.0,
-            gate_block=8,
             gate_n_max=40,
             gate_p_low=0.05,
             gate_p_high=0.95,
@@ -881,7 +880,6 @@ class TestRunHoldoutEvalConfig:
             gate_delta_min=0.02,
             gate_lambda_dir=-0.642,
             gate_e_rollback=10.0,
-            gate_block=8,
             gate_n_max=40,
             gate_p_low=0.05,
             gate_p_high=0.95,
@@ -932,7 +930,6 @@ class TestRunHoldoutEvalConfig:
             gate_delta_min=0.02,
             gate_lambda_dir=-0.642,
             gate_e_rollback=10.0,
-            gate_block=8,
             gate_n_max=40,
             gate_p_low=0.05,
             gate_p_high=0.95,

tests/unit/test_harness_runner.py

@@ -840,7 +840,6 @@ class TestRunnerFactoryInjection:
             "gate_delta_min": 0.02,
             "gate_lambda_dir": -0.642,
             "gate_e_rollback": 10.0,
-            "gate_block": 8,
             "gate_n_max": 40,
             "gate_p_low": 0.05,
             "gate_p_high": 0.95,

tests/unit/test_harness_validate.py

@@ -1,7 +1,9 @@
 """tests/unit/test_harness_validate.py — app/harness/validate.py 的单元测试。
 
-覆盖：数据类型字段、materialize 物化与清理、async validate_skill_local
+覆盖：数据类型字段、materialize 物化与清理、async validate_skills_concurrent
-（accept/reject/prefix 校验/INFRA 护栏/缓存命中/最后一块终态）。
+（accept/reject/prefix 校验/INFRA 护栏/缓存命中/题尽终态）。async 用例迁移自
+块序贯版（validate_skill_local，Task 6 删除）：载体换连续并发 gate，语义断言
+保留；前缀逐单元判定使早停点比旧块判定更早（见各用例 docstring 的数值推导）。
 """
 
 from __future__ import annotations
@@ -14,10 +16,12 @@ from app.harness.gate_ladder import BaselineCache, skill_hash
 from app.harness.inference import PREDICTIONS_SCHEMA, InferenceResult
 from app.harness.log import HarnessLog
 from app.harness.validate import (
+    GateSpec,
     Probation,
     ValidationOutcome,
+    _ladder_units,
     materialize_candidate_skill,
-    validate_skill_local,
+    validate_skills_concurrent,
 )
 from core.evolution import GateParams, RejectedEdit
 from core.types import GeneratedQuestion
@@ -150,7 +154,7 @@ def _make_mock_run_inference(
 
 
 def _make_all_infra_mock(log: HarnessLog, stop_reason: str):
-    """构建基线全 INFRA 的 mock：每 record 写指定 INFRA stop_reason（error/parse_error）。
+    """构建全 INFRA 的 mock：每 record 写指定 INFRA stop_reason（error/parse_error）。
 
     与真实推理一致——per-record DB stop_reason 与汇总 stop_reason_counts 同源；护栏
     分子按 unit 从 DB 读（_infra_question_ids_from_db），故须真实落 DB。total 返回
@@ -199,6 +203,48 @@ def _make_all_infra_mock(log: HarnessLog, stop_reason: str):
     return mock_fn, call_log
 
 
+def _mk_spec(
+    questions: list[GeneratedQuestion],
+    *,
+    candidate_content: str = "candidate skill",
+    gate_run_prefix: str = "step1_gate_test",
+) -> GateSpec:
+    """由阶梯题序构造单题型 GateSpec（units 经 _ladder_units 聚合为阶梯序单元）。"""
+    return GateSpec(
+        task_type="temporal",
+        target_file="temporal.md",
+        candidate_content=candidate_content,
+        base_skill_content="baseline skill content",
+        units=tuple(_ladder_units(questions)),
+        gate_run_prefix=gate_run_prefix,
+    )
+
+
+async def _run_single_spec(
+    workspace: Path,
+    spec: GateSpec,
+    mock_fn,
+    log: HarnessLog,
+    cache: BaselineCache,
+    params: GateParams,
+    gate_guard_err: float = 0.5,
+) -> ValidationOutcome:
+    """跑单 spec 的 validate_skills_concurrent 并返回该题型的 outcome。"""
+    outcomes = await validate_skills_concurrent(
+        workspace_dir=workspace,
+        base_skills_version="v1",
+        specs=[spec],
+        gate_params=params,
+        gate_guard_err=gate_guard_err,
+        baseline_cache=cache,
+        prompts_version="p1",
+        run_inference=mock_fn,
+        log=log,
+        concurrency=8,
+    )
+    return outcomes[spec.task_type]
+
+
 def test_infra_stop_reasons_single_source() -> None:
     """app 侧 INFRA_STOP_REASONS 复用 core 常量（同一对象），杜绝未来漂移（M-2）。"""
     from app.harness import validate
@@ -331,13 +377,17 @@ class TestMaterializeCandidateSkill:
 
 
 # ===========================================================================
-# async 验证测试
+# async 验证测试（迁移自块序贯版 validate_skill_local）
 # ===========================================================================
 
 
 @pytest.mark.asyncio
-async def test_validate_skill_local_accept(tmp_path: Path) -> None:
+async def test_validate_concurrent_accept(tmp_path: Path) -> None:
-    """候选全对、基线全错 → 高 e 值 → accept_confirmed。"""
+    """候选全对、基线全错 → 高 e 值 → accept_confirmed（迁移自块序贯版）。
+
+    6 单元连胜：E=(2^(W+1)-1)/(W+1)，前 5 单元 E<15 且不触方向/futility，
+    第 6 单元 E=18.14 ≥ e_confirm=15 → 与旧块判定同点收敛（W=6, n_used=6）。
+    """
     workspace = _setup_workspace(tmp_path)
     log = _make_log(workspace)
     questions = _make_questions(6)
@@ -359,23 +409,13 @@ async def test_validate_skill_local_accept(tmp_path: Path) -> None:
     )
 
     try:
-        outcome = await validate_skill_local(
+        outcome = await _run_single_spec(
-            workspace_dir=workspace,
+            workspace,
-            base_skills_version="v1",
+            _mk_spec(questions, candidate_content="improved skill"),
-            task_type="temporal",
+            mock_fn,
-            target_file="temporal.md",
+            log,
-            candidate_content="improved skill",
+            cache,
-            base_skill_content="baseline skill content",
+            accept_params,
-            ladder_items=questions,
-            gate_params=accept_params,
-            gate_block=6,
-            gate_n_max=20,
-            gate_guard_err=0.5,
-            baseline_cache=cache,
-            prompts_version="p1",
-            run_inference=mock_fn,
-            log=log,
-            gate_run_prefix="step1_gate_test",
         )
 
         assert outcome.accepted is True
@@ -387,6 +427,8 @@ async def test_validate_skill_local_accept(tmp_path: Path) -> None:
         assert outcome.candidate_acc == 1.0
         assert outcome.baseline_acc == 0.0
         assert len(outcome.evidence_rows) == 6
+        # 阶梯序前缀消费：ladder_rank 连续（替代旧块边界断言）
+        assert [r["ladder_rank"] for r in outcome.evidence_rows] == list(range(6))
         # 终态证据行携带 stop_reason
         assert outcome.evidence_rows[-1]["stop_reason"] == "confirmed"
         # 候选临时目录应被清理
@@ -398,50 +440,45 @@ async def test_validate_skill_local_accept(tmp_path: Path) -> None:
 
 
 @pytest.mark.asyncio
-async def test_validate_skill_local_reject(tmp_path: Path) -> None:
+async def test_validate_concurrent_reject_directional(tmp_path: Path) -> None:
-    """候选全错、基线全对 → L 高 → 方向拒绝。"""
+    """候选全错、基线全对 → L 高 → 方向拒绝（迁移自块序贯版）。
+
+    前缀逐单元判定下早停点前移：15 单元阶梯保证 L=1..3 时 futility 不先触发
+    （E(w+n_rem, l) ≥ 3），L=4 时 Wald=4·ln0.6=-2.04 ≤ lambda_dir=-2.0 →
+    directional 早停于第 4 单元（旧块版一次性判整块故 L=6）。
+    """
     workspace = _setup_workspace(tmp_path)
     log = _make_log(workspace)
-    questions = _make_questions(6)
+    questions = _make_questions(15)
     cache = BaselineCache(workspace / "baseline_cache.json")
 
-    # 基线全对，候选全错 → W=0, L=6 → 方向拒绝
+    baseline_correct = {f"q{i}": True for i in range(15)}
-    baseline_correct = {f"q{i}": True for i in range(6)}
+    candidate_correct = {f"q{i}": False for i in range(15)}
-    candidate_correct = {f"q{i}": False for i in range(6)}
     mock_fn, _ = _make_mock_run_inference(log, baseline_correct, candidate_correct)
 
     try:
-        outcome = await validate_skill_local(
+        outcome = await _run_single_spec(
-            workspace_dir=workspace,
+            workspace,
-            base_skills_version="v1",
+            _mk_spec(questions, candidate_content="bad skill"),
-            task_type="temporal",
+            mock_fn,
-            target_file="temporal.md",
+            log,
-            candidate_content="bad skill",
+            cache,
-            base_skill_content="baseline skill content",
+            _DEFAULT_GATE_PARAMS,
-            ladder_items=questions,
-            gate_params=_DEFAULT_GATE_PARAMS,
-            gate_block=6,
-            gate_n_max=20,
-            gate_guard_err=0.5,
-            baseline_cache=cache,
-            prompts_version="p1",
-            run_inference=mock_fn,
-            log=log,
-            gate_run_prefix="step1_gate_test",
         )
 
         assert outcome.accepted is False
         assert outcome.action == "reject"
         assert outcome.stop_reason == "directional"
         assert outcome.w == 0
-        assert outcome.l == 6
+        assert outcome.l == 4
+        assert outcome.n_used == 4
     finally:
         log.close()
 
 
 @pytest.mark.asyncio
 async def test_gate_prefix_must_contain_gate(tmp_path: Path) -> None:
-    """gate_run_prefix 不含 '_gate_' 时抛 ValueError。"""
+    """gate_run_prefix 不含 '_gate_' 时抛 ValueError（迁移自块序贯版）。"""
     workspace = _setup_workspace(tmp_path)
     log = _make_log(workspace)
     questions = _make_questions(4)
@@ -452,23 +489,13 @@ async def test_gate_prefix_must_contain_gate(tmp_path: Path) -> None:
 
     try:
         with pytest.raises(ValueError, match="_gate_"):
-            await validate_skill_local(
+            await _run_single_spec(
-                workspace_dir=workspace,
+                workspace,
-                base_skills_version="v1",
+                _mk_spec(questions, gate_run_prefix="step1_no_marker"),
-                task_type="temporal",
+                noop_fn,
-                target_file="temporal.md",
+                log,
-                candidate_content="content",
+                cache,
-                base_skill_content="baseline",
+                _DEFAULT_GATE_PARAMS,
-                ladder_items=questions,
-                gate_params=_DEFAULT_GATE_PARAMS,
-                gate_block=4,
-                gate_n_max=20,
-                gate_guard_err=0.5,
-                baseline_cache=cache,
-                prompts_version="p1",
-                run_inference=noop_fn,
-                log=log,
-                gate_run_prefix="step1_no_marker",
             )
     finally:
         log.close()
@@ -476,34 +503,26 @@ async def test_gate_prefix_must_contain_gate(tmp_path: Path) -> None:
 
 @pytest.mark.asyncio
 async def test_infra_guard_threshold(tmp_path: Path) -> None:
-    """推理错误率超阈值时抛 RuntimeError（护栏分子/分母 unit 同粒度）。"""
+    """推理错误率超阈值时抛 RuntimeError（迁移自块序贯版，分子/分母 unit 同粒度）。
+
+    12 个 single 双臂全 INFRA error：errors 按单元去重逐单元 +1，分母逐臂 +1，
+    分母 ≥10 后错误率 >0.5 → 护栏熔断。
+    """
     workspace = _setup_workspace(tmp_path)
     log = _make_log(workspace)
-    # 需要 >=10 unit 分母才触发护栏：12 个 single，基线全 INFRA error。
-    # 首块全 INFRA → valid_chunk 空 → errors=12/denom=12=1.0>0.5 触发护栏。
     questions = _make_questions(12)
     cache = BaselineCache(workspace / "baseline_cache.json")
     mock_fn, _ = _make_all_infra_mock(log, "error")
 
     try:
         with pytest.raises(RuntimeError, match="错误率过高"):
-            await validate_skill_local(
+            await _run_single_spec(
-                workspace_dir=workspace,
+                workspace,
-                base_skills_version="v1",
+                _mk_spec(questions),
-                task_type="temporal",
+                mock_fn,
-                target_file="temporal.md",
+                log,
-                candidate_content="content",
+                cache,
-                base_skill_content="baseline skill content",
+                _DEFAULT_GATE_PARAMS,
-                ladder_items=questions,
-                gate_params=_DEFAULT_GATE_PARAMS,
-                gate_block=12,
-                gate_n_max=20,
-                gate_guard_err=0.5,
-                baseline_cache=cache,
-                prompts_version="p1",
-                run_inference=mock_fn,
-                log=log,
-                gate_run_prefix="step1_gate_test",
             )
     finally:
         log.close()
@@ -511,7 +530,10 @@ async def test_infra_guard_threshold(tmp_path: Path) -> None:
 
 @pytest.mark.asyncio
 async def test_baseline_cache_hit(tmp_path: Path) -> None:
-    """基线缓存全命中时不发起基线侧推理。"""
+    """基线缓存全命中时不发起基线侧推理（迁移自块序贯版）。
+
+    连续并发 gate 下候选侧逐单元发臂：4 单元 → 4 次 cand 调用（旧块版整块 1 次）。
+    """
     workspace = _setup_workspace(tmp_path)
     log = _make_log(workspace)
     questions = _make_questions(4)
@@ -528,30 +550,20 @@ async def test_baseline_cache_hit(tmp_path: Path) -> None:
     mock_fn, call_log = _make_mock_run_inference(log, baseline_correct, candidate_correct)
 
     try:
-        outcome = await validate_skill_local(
+        outcome = await _run_single_spec(
-            workspace_dir=workspace,
+            workspace,
-            base_skills_version="v1",
+            _mk_spec(questions, candidate_content="improved skill"),
-            task_type="temporal",
+            mock_fn,
-            target_file="temporal.md",
+            log,
-            candidate_content="improved skill",
+            cache,
-            base_skill_content="baseline skill content",
+            _DEFAULT_GATE_PARAMS,
-            ladder_items=questions,
-            gate_params=_DEFAULT_GATE_PARAMS,
-            gate_block=4,
-            gate_n_max=20,
-            gate_guard_err=0.5,
-            baseline_cache=cache,
-            prompts_version="p1",
-            run_inference=mock_fn,
-            log=log,
-            gate_run_prefix="step1_gate_test",
         )
 
         # 只有候选侧调用了 run_inference（_cand），基线侧全命中不调用
         base_calls = [c for c in call_log if c["run_id"].endswith("_base")]
         cand_calls = [c for c in call_log if c["run_id"].endswith("_cand")]
         assert len(base_calls) == 0, "基线缓存全命中不应发起推理"
-        assert len(cand_calls) == 1
+        assert len(cand_calls) == 4
         assert outcome.accepted is True
     finally:
         log.close()
@@ -559,21 +571,21 @@ async def test_baseline_cache_hit(tmp_path: Path) -> None:
 
 @pytest.mark.asyncio
 async def test_baseline_infra_error_not_cached(tmp_path: Path) -> None:
-    """基线臂 INFRA error 的 unit 不写入 BaselineCache（不永久污染），且从有效单元排除。"""
+    """基线臂 INFRA error 的 unit 不写入 BaselineCache（不永久污染），且从配对剔除。
-    from app.harness.gate_ladder import skill_hash
-    from app.harness.question_units import build_units
-    from app.harness.validate import _resolve_baseline_block
 
+    迁移自块序贯版 _resolve_baseline_block 直测：改经 validate_skills_concurrent
+    端到端验证同一契约——INFRA 单元不落缓存、不入配对；干净单元正常缓存并消费。
+    """
     workspace = _setup_workspace(tmp_path)
     log = _make_log(workspace)
-    questions = _make_questions(2)  # q0 干净, q1 INFRA error
+    questions = _make_questions(2)  # q0 基线 INFRA error, q1 干净
-    units = build_units(questions)
     cache = BaselineCache(workspace / "baseline_cache.json")
     s_hash = skill_hash("baseline skill content")
 
     async def mock_fn(qs, *, run_id, skills_dir):
+        is_base = run_id.endswith("_base")
         for q in qs:
-            is_err = q.question_id == "q1"
+            is_err = is_base and q.question_id == "q0"
             log.insert(
                 "predictions",
                 {
@@ -594,54 +606,49 @@ async def test_baseline_infra_error_not_cached(tmp_path: Path) -> None:
             )
         return InferenceResult(
             run_id=run_id,
-            accuracy=0.5,
+            accuracy=0.0,
-            total=2,
+            total=len(qs),
-            correct=1,
+            correct=0,
             per_task_type={},
             steps_mean=1.0,
             token_usage={"prompt_tokens": 10, "completion_tokens": 10},
-            stop_reason_counts={"completed": 1, "error": 1},
+            stop_reason_counts={},
         )
 
     try:
-        b_units, valid_units, _errors_inc, _denom_inc = await _resolve_baseline_block(
+        outcome = await _run_single_spec(
-            units=units,
+            workspace,
-            task_type="temporal",
+            _mk_spec(questions),
-            s_hash=s_hash,
+            mock_fn,
-            prompts_version="p1",
+            log,
-            baseline_cache=cache,
+            cache,
-            base_skills_dir=workspace / "skills" / "v1",
+            _DEFAULT_GATE_PARAMS,
-            run_inference=mock_fn,
+            gate_guard_err=0.9,  # 分母 <10 不触发错误率护栏
-            log=log,
-            run_id="step1_gate_b0_base",
         )
-        # q1 是 INFRA：不写缓存、不入 b_units、不在有效单元里
+        # q0 是 INFRA：不写缓存、不入配对观测
-        assert cache.get("temporal", s_hash, "p1", "q1") is None
+        assert cache.get("temporal", s_hash, "p1", "q0") is None
-        assert "q1" not in b_units
+        assert "q0" not in outcome.improvements + outcome.regressions
-        assert all(u.unit_id != "q1" for u in valid_units)
+        # q1 干净：正常缓存并被消费（唯一有效单元）
-        # q0 干净：正常缓存并入 b_units/valid_units
+        assert cache.get("temporal", s_hash, "p1", "q1") is True
-        assert cache.get("temporal", s_hash, "p1", "q0") is True
+        assert outcome.n_used == 1
-        assert b_units["q0"] is True
-        assert any(u.unit_id == "q0" for u in valid_units)
     finally:
         log.close()
 
 
 @pytest.mark.asyncio
-async def test_infra_guard_counts_units_not_records(tmp_path: Path) -> None:
+async def test_infra_errors_counted_per_unit_not_per_record(tmp_path: Path) -> None:
-    """护栏分子按 unit 计：AR pair 两 record 全 INFRA 只计 1 个 INFRA unit（而非 2）。
+    """护栏分子按 unit 去重：AR pair 两 record、双臂全 INFRA 只计 1 个 error。
 
-    回归 I-3：分子此前用 stop_reason_counts 逐 record 计数，分母 denom_inc=r.total
+    迁移自块序贯版 _resolve_baseline_block 直测（回归 I-3）：分子若逐 record /
-    是 unit 粒度；AR pair（一 unit 两 record）致分子被放大、误触发 gate_guard_err。
+    逐臂计数会被放大（一 unit 两 record × 两臂 = 4），与 unit 粒度分母失配致
-    分子改为"含 INFRA record 的 unit 数"后与分母同粒度（核心算法保真 #5/#6）。
+    gate_guard_err 误触发。新载体 _run_unit_arm + _register_arm_arrival 按
+    slot.excluded() 去重（核心算法保真 #5/#6）。
     """
-    from app.harness.gate_ladder import skill_hash
     from app.harness.question_units import build_units
-    from app.harness.validate import _resolve_baseline_block
+    from app.harness.validate import _GateRun, _QuestionSlots, _run_unit_arm
 
     workspace = _setup_workspace(tmp_path)
     log = _make_log(workspace)
-    # 一个 AR pair（两成员共享 pair_id）→ build_units 折叠为 1 个 pair unit
     common = {
         "video_id": "vp",
         "task_type": "temporal",
@@ -660,7 +667,17 @@ async def test_infra_guard_counts_units_not_records(tmp_path: Path) -> None:
     units = build_units(pair)
     assert len(units) == 1  # 前置：pair 折叠为 1 个 unit
     cache = BaselineCache(workspace / "baseline_cache.json")
-    s_hash = skill_hash("baseline skill content")
+    run = _GateRun.from_spec(
+        GateSpec(
+            task_type="temporal",
+            target_file="temporal.md",
+            candidate_content="cand",
+            base_skill_content="baseline skill content",
+            units=tuple(units),
+            gate_run_prefix="step1_gate_test",
+        )
+    )
+    s_hash = run.s_hash
 
     async def mock_fn(qs, *, run_id, skills_dir):
         # 两 record 皆 INFRA error
@@ -683,7 +700,7 @@ async def test_infra_guard_counts_units_not_records(tmp_path: Path) -> None:
                     "steps_json": "[]",
                 },
             )
-        # total 为 unit 粒度（1 个 pair unit）；stop_reason_counts 为 record 粒度（2）
+        # total 为 unit 粒度（1 个 pair unit）；record 粒度为 2
         return InferenceResult(
             run_id=run_id,
             accuracy=0.0,
@@ -695,94 +712,57 @@ async def test_infra_guard_counts_units_not_records(tmp_path: Path) -> None:
             stop_reason_counts={"error": 2},
         )
 
+    slots = _QuestionSlots(4)
     try:
-        _b_units, valid_units, errors_inc, denom_inc = await _resolve_baseline_block(
+        for arm in ("base", "cand"):
-            units=units,
+            await _run_unit_arm(
-            task_type="temporal",
+                run,
-            s_hash=s_hash,
+                0,
-            prompts_version="p1",
+                arm,
-            baseline_cache=cache,
+                slots,
-            base_skills_dir=workspace / "skills" / "v1",
+                mock_fn,
-            run_inference=mock_fn,
+                log,
-            log=log,
+                cache,
-            run_id="step1_gate_b0_base",
+                "p1",
+                workspace / "skills" / "v1",
+                workspace / "skills" / "v1",
+                _DEFAULT_GATE_PARAMS,
+                0.9,
             )
-        # 分子按 unit 计：1 个 INFRA unit（不是 2 条 record）；分母同粒度 = r.total = 1
+        # 分子按 unit 去重：双臂 × 两 record 只计 1 个 error；分母按臂 total 累计 = 2
-        assert errors_inc == 1
+        assert run.errors == 1
-        assert denom_inc == 1
+        assert run.infra_denom == 2
-        # 整对 INFRA → 从有效单元剔除
+        assert run.slots[0].base_infra and run.slots[0].cand_infra
-        assert valid_units == []
+        # INFRA 单元不写缓存
+        assert cache.get("temporal", s_hash, "p1", "p1") is None
     finally:
         log.close()
 
 
 @pytest.mark.asyncio
 async def test_all_infra_ladder_raises_clear_error(tmp_path: Path) -> None:
-    """整个阶梯所有 unit 都被判为 INFRA 排除 → 明确 RuntimeError（非误导性空阶梯断言）。"""
+    """整个阶梯所有 unit 都被判为 INFRA 排除 → 明确 RuntimeError（迁移自块序贯版）。
+
+    连续并发 gate 下双臂独立发射，候选臂不再依赖基线侧结果（旧版"全 INFRA 块
+    不空跑候选"的断言随块编排一并删除）。
+    """
     workspace = _setup_workspace(tmp_path)
     log = _make_log(workspace)
     questions = _make_questions(4)
     cache = BaselineCache(workspace / "baseline_cache.json")
-
+    mock_fn, _ = _make_all_infra_mock(log, "error")
-    candidate_calls: list[str] = []
-
-    async def mock_fn(qs, *, run_id, skills_dir):
-        if run_id.endswith("_cand"):
-            candidate_calls.append(run_id)
-        # 基线臂逐题全部 INFRA error（候选臂在修复后不应被空跑）
-        for q in qs:
-            log.insert(
-                "predictions",
-                {
-                    "run_id": run_id,
-                    "video_id": "v0",
-                    "question_id": q.question_id,
-                    "task_type": "temporal",
-                    "prediction": "",
-                    "answer": "A",
-                    "evidence": "",
-                    "reasoning": "",
-                    "steps_used": 1,
-                    "prompt_tokens": 10,
-                    "completion_tokens": 10,
-                    "stop_reason": "error",
-                    "steps_json": "[]",
-                },
-            )
-        total = len(qs)
-        return InferenceResult(
-            run_id=run_id,
-            accuracy=0.0,
-            total=total,
-            correct=0,
-            per_task_type={},
-            steps_mean=1.0,
-            token_usage={"prompt_tokens": 10, "completion_tokens": 10},
-            stop_reason_counts={"error": total},
-        )
 
     try:
         with pytest.raises(RuntimeError, match="INFRA"):
-            await validate_skill_local(
+            await _run_single_spec(
-                workspace_dir=workspace,
+                workspace,
-                base_skills_version="v1",
+                _mk_spec(questions),
-                task_type="temporal",
+                mock_fn,
-                target_file="temporal.md",
+                log,
-                candidate_content="content",
+                cache,
-                base_skill_content="baseline skill content",
+                _DEFAULT_GATE_PARAMS,
-                ladder_items=questions,
+                gate_guard_err=0.9,  # 4 单元分母 <10 不触发错误率护栏 → 逼出全排除分支
-                gate_params=_DEFAULT_GATE_PARAMS,
-                gate_block=4,
-                gate_n_max=20,
-                gate_guard_err=0.9,  # 高阈值：4 题 <10 分母不触发错误率护栏
-                baseline_cache=cache,
-                prompts_version="p1",
-                run_inference=mock_fn,
-                log=log,
-                gate_run_prefix="step1_gate_test",
             )
-        # 全 INFRA 块不应触发候选空跑
-        assert candidate_calls == []
     finally:
         log.close()
 
@@ -792,42 +772,33 @@ async def test_parse_error_counts_toward_guard(tmp_path: Path) -> None:
     """stop_reason=parse_error 也计入护栏错误率（与 INFRA 判定口径一致）→ 超阈值熔断。"""
     workspace = _setup_workspace(tmp_path)
     log = _make_log(workspace)
-    # 12 个 single，基线全 parse_error（per-record 落 DB，护栏按 unit 从 DB 读）。
-    # 首块全 INFRA → errors=12/denom=12=1.0>0.5 → parse_error 亦触发护栏。
     questions = _make_questions(12)
     cache = BaselineCache(workspace / "baseline_cache.json")
     mock_fn, _ = _make_all_infra_mock(log, "parse_error")
 
     try:
         with pytest.raises(RuntimeError, match="错误率过高"):
-            await validate_skill_local(
+            await _run_single_spec(
-                workspace_dir=workspace,
+                workspace,
-                base_skills_version="v1",
+                _mk_spec(questions),
-                task_type="temporal",
+                mock_fn,
-                target_file="temporal.md",
+                log,
-                candidate_content="content",
+                cache,
-                base_skill_content="baseline skill content",
+                _DEFAULT_GATE_PARAMS,
-                ladder_items=questions,
-                gate_params=_DEFAULT_GATE_PARAMS,
-                gate_block=12,
-                gate_n_max=20,
-                gate_guard_err=0.5,
-                baseline_cache=cache,
-                prompts_version="p1",
-                run_inference=mock_fn,
-                log=log,
-                gate_run_prefix="step1_gate_test",
             )
     finally:
         log.close()
 
 
 @pytest.mark.asyncio
-async def test_last_block_terminal(tmp_path: Path) -> None:
+async def test_ladder_exhaustion_terminal(tmp_path: Path) -> None:
-    """单块 + n_remaining=0 → 终态判定（provisional 或 inertia），非 continue。"""
+    """题尽（n_remaining=0）→ 终态判定（provisional 或 inertia），非 continue。
+
+    迁移自块序贯版"最后一块终态"：块边界不存在了，等价语义是阶梯耗尽时
+    第四出口兜底，终态行携带 stop_reason。
+    """
     workspace = _setup_workspace(tmp_path)
     log = _make_log(workspace)
-    # 4 题，gate_block=4 → 一块走完，n_remaining=0
     questions = _make_questions(4)
     cache = BaselineCache(workspace / "baseline_cache.json")
 
@@ -837,23 +808,13 @@ async def test_last_block_terminal(tmp_path: Path) -> None:
     mock_fn, _ = _make_mock_run_inference(log, baseline_correct, candidate_correct)
 
     try:
-        outcome = await validate_skill_local(
+        outcome = await _run_single_spec(
-            workspace_dir=workspace,
+            workspace,
-            base_skills_version="v1",
+            _mk_spec(questions),
-            task_type="temporal",
+            mock_fn,
-            target_file="temporal.md",
+            log,
-            candidate_content="candidate skill",
+            cache,
-            base_skill_content="baseline skill content",
+            _DEFAULT_GATE_PARAMS,
-            ladder_items=questions,
-            gate_params=_DEFAULT_GATE_PARAMS,
-            gate_block=4,
-            gate_n_max=4,
-            gate_guard_err=0.5,
-            baseline_cache=cache,
-            prompts_version="p1",
-            run_inference=mock_fn,
-            log=log,
-            gate_run_prefix="step1_gate_test",
         )
 
         # n_remaining=0 → 不可能是 continue
@@ -865,6 +826,8 @@ async def test_last_block_terminal(tmp_path: Path) -> None:
             "futility",
         )
         assert outcome.n_used == 4
+        # 阶梯序前缀消费：ladder_rank 连续
+        assert [r["ladder_rank"] for r in outcome.evidence_rows] == list(range(4))
         # 终态行标记 stop_reason
         assert outcome.evidence_rows[-1]["stop_reason"] != ""
     finally:

tests/unit/test_runner_diag_tree_inject.py

@@ -64,7 +64,6 @@ def _base_config(workspace_dir: Path, store_dir: Path) -> RunConfig:
         gate_delta_min=0.02,
         gate_lambda_dir=-0.642,
         gate_e_rollback=10.0,
-        gate_block=8,
         gate_n_max=40,
         gate_p_low=0.05,
         gate_p_high=0.95,