feat(agent): trusted time evidence and collection prompt optimization

- time_context.py: server-side observation clocks for relative-time
  evidence (anti client-forgery); resolves X分钟前/小时前 against the
  observation timestamp of the turn that produced them, never re-basing
  history on the current clock; flags historical references without a
  reliable baseline
- state: dialogue_timestamps keyed by dialogue message index, persisted
  with checkpoint; welcome seeds index 0
- collect: single clock per turn shared by reply/extraction/repair;
  time_evidence injected into runtime context; reply_validator hook
  rejects time claims lacking evidence (one shared repair budget);
  model still interprets facts and chooses actions
- prompts: collection prompt restructured (shorter, state-bound-to-action
  table, gatekeeper principle, time source rules); extraction prompt
  aligned; workflow@20261021 json updated to match
- evals: prompt_probes / prompt_compare / time_boundary probe scripts
  (supplementary checks, original cases untouched)
- docs: collection-prompt-optimization.md (method + baselines),
  time-boundary-fix.md (problem, design, verification)
- gitignore: editor artifact dirs (.agents/.claude/.vscode, skills-lock)

Verified: 171 unit tests pass (16 new time-context tests)

src/agent/state.py

@@ -46,6 +46,9 @@ class AgentState(TypedDict):
     # 已交换的消息列表 [{"role": "user"/"assistant", "content": str}]，
     # 用于注入提示词，让模型跳过已知信息；可序列化，随 checkpoint 持久化。
     dialogue: list
+    # 服务器接收用户消息时的时钟，key为完整dialogue的消息索引；
+    # 独立于消息正文，避免客户端伪造历史基准，随checkpoint跨轮保存。
+    dialogue_timestamps: dict[str, str]
     client_mode: str     # direct / browser_addon（LangGraphBackend 注入）
 
     # ---- 信息核实（作业 5） ----