harness2: upstream gap fill — trivial selection fix, session budget, run_tag validation, preflight check

- select_final trivial condition now k==1 and single-candidate pool,
  regardless of whether a selector is provided (previously gated on
  selector is None, so wired runs always paid for a useless selector
  task at k=1)
- Budget gains max_sessions gate (probe + stage-attempt sessions;
  fmt2 corrections and selector/reflector sessions exempt), the
  backstop for unpriced models where the USD gate never binds
- validate_run_tag (charset, no leading '-', no s<N> seed prefix)
  enforced at run_improvement_via_tasks and the CLI
- CLI --check preflight (base harness, source dir, prompt, tag,
  control-plane /health probe) without creating tasks
- ModeResult.to_dict now includes rollout summaries so a lost probe
  is visible in full_result instead of only on the server
- CLI plan counts the selector only when k>1

cloud/harness2.py

@@ -26,8 +26,9 @@ Claude CLI 通道都没有搬。
 
 选终版时只比“产物”：候选产物先匿名化（A/B/C……，按任务+k+模式
 定种子洗牌，可复现），选择器看不到哪个产物出自哪个 harness；选不
-出来时回落到已交付的终版，绝不抛异常把整轮炸掉。k=1 且没有选择
-器时直接走 trivial：唯一的终版就是答案，不必再选一次。
+出来时回落到已交付的终版，绝不抛异常把整轮炸掉。k=1 且终版池
+只有唯一候选时直接走 trivial：唯一的终版就是答案，不必再选
+一次（与选择器是否提供无关）。
 
 经验库（上游叫 harnessing-level recursion）：
   采纳后，反思器只写一条有证据的经验（cue / lesson / evidence 三项
@@ -740,16 +741,32 @@ def _mission_experience() -> str:
 
 @dataclass
 class Budget:
+    """美元门 + 会话数门（2026-10-29 对照补齐）。
+
+    上游用会话数记账并强校验期望计数（R=4k、P=3k）；本项目此前
+    只有美元门，在 unpriced 模型上成本恒为 0、门永远不触发。
+    sessions 计探针会话与阶段尝试会话；edit() 内部的 fmt2 纠正
+    与选择/反思会话不计入（前者在接线层、后者不走 budget），
+    上限语义因此是“受门控的会话数”，不是全轮任务总数。
+    """
+
     max_cost_usd: float | None = None
     spent_usd: float = 0.0
+    max_sessions: int | None = None
+    sessions: int = 0
 
     @property
     def exceeded(self) -> bool:
-        return self.max_cost_usd is not None and self.spent_usd > self.max_cost_usd
+        if self.max_cost_usd is not None and self.spent_usd > self.max_cost_usd:
+            return True
+        return self.max_sessions is not None and self.sessions >= self.max_sessions
 
     def add(self, cost: float) -> None:
         self.spent_usd += float(cost or 0.0)
 
+    def add_session(self) -> None:
+        self.sessions += 1
+
 
 # ---------------------------------------------------------------------------
 # 阶段：一次提议（含一次修正机会）+ 一次探针
@@ -816,6 +833,18 @@ class ModeResult:
             if any(s.dim == "AGG" for s in self.stages)
             else None,
             "errors": self.errors,
+            # 探针结果此前不在 full_result 里：real5 的终版探针没建
+            # 出来时，本地日志完全看不到原因，只能去服务端翻任务。
+            # 只放摘要（不放 trajectory），避免日志爆炸。
+            "rollouts": {
+                lbl: {
+                    "ok": r.ok,
+                    "delivered": r.delivered,
+                    "error": (r.error or "")[:400],
+                    "deliverable_text": (r.deliverable_text or "")[:500],
+                }
+                for lbl, r in self.rollouts.items()
+            },
         }
 
 
@@ -872,6 +901,11 @@ def _run_stage(
     err = ""
     spent = 0.0
     for attempt in range(1, STAGE_ATTEMPTS + 1):
+        if budget is not None:
+            if budget.exceeded:
+                err = "budget exceeded before this attempt"
+                break
+            budget.add_session()
         try:
             result = editor.edit(
                 full_mission + (
@@ -918,6 +952,8 @@ def _roll(
     if budget is not None and budget.exceeded:
         return Rollout(label=label, ok=False, delivered=False,
                        error="budget exceeded before this rollout")
+    if budget is not None:
+        budget.add_session()
     try:
         rv = adapter.execute(label, tree)
     except Exception as exc:
@@ -1164,8 +1200,11 @@ def select_final(
                   f"{text.count(chr(10)) + 1:,} lines. COMPLETE -- nothing trimmed. -->\n")
         (cand_dir / f"{anon}.md").write_text(header + text, encoding="utf-8")
     ids = ", ".join(sorted(sel.id_map))
-    if selector is None and k == 1:
-        # 唯一终版：不必再开一轮选择会话（上游的 trivial_selection）。
+    if k == 1 and len(pool) == 1:
+        # 唯一终版：不必再开一轮选择会话（上游的 trivial_selection，
+        # 条件是“终版池 + k=1”，与选择器是否提供无关；此前误写成
+        # selector is None 才 trivial，而接线永远传选择器，导致
+        # k=1 也白白跑一个选择任务——2026-10-29 对照发现）。
         label = next(iter(pool))
         sel.ok = True
         sel.trivial = True
@@ -1402,6 +1441,7 @@ def improve_task(
     library: Library | None = None,
     auto_apply: bool = False,
     budget_usd: float | None = None,
+    max_sessions: int | None = None,
 ) -> ImprovementResult:
     """跑一轮完整改进。base 探针先跑一次，作为全部候选共享的证据。
 
@@ -1413,7 +1453,7 @@ def improve_task(
     if not 1 <= int(k) <= MAX_K:
         raise ValueError(f"k must be 1..{MAX_K}, got {k!r}")
     work_dir = Path(work_dir)
-    budget = Budget(max_cost_usd=budget_usd)
+    budget = Budget(max_cost_usd=budget_usd, max_sessions=max_sessions)
     base_tree = adapter.base_harness()
     # 校验 base 本身：base 若已不合法，整轮的对比就没意义，直接报错
     # 而不是让候选在坏 base 上各跑各的。