feat(agent): align with workflow@20261022 - turn_context messages and prompt tails

- merge main (b0ff2e0..c7ca781): workflow/20261022 moves dynamic context
  out of fixed prompts - collection/extraction prompts carry no inline vars;
  reference time and current form travel in the user message <turn_context>
  block; photo/confirm data kept at prompt tails
- prompts: all 8 files regenerated from 20261022 (byte-identity tests
  point at the new export)
- collect: user message = <turn_context>(本轮参考时间) + <user_input>;
  extraction message adds 当前表单; single trusted clock per turn threads
  through reply/extraction/repair
- photo: raw input only (20261022 photo nodes use system_text, no wrapper)
- workflow fake llm: unwraps <user_input> before event parsing
- fields: accident_time normalized to extraction format (YYYY年M月D日H点m分,
  strip zero padding) - fixes form assertion mismatch with padded output
- evals/run.py: trust_env=False - bypass Windows system proxy (registry
  proxy at 192.168.0.4:7897 was intercepting localhost and returning 503)
- verified: 172 unit tests; ALL golden suites pass on real model
  (46/46): collection_skip 12/12, photo_skip 4/4, no_false 2/2,
  button_guidance 12/12, non_motor_vehicle 14/14, time_confirmation 2/2

src/agent/collect.py

@@ -130,9 +130,22 @@ def context_prompt(state: AgentState, *, time_context: dict | None = None) -> st
     }, ensure_ascii=False)
 
 
-def _build_user_message(state: AgentState) -> str:
-    """对齐工作流 Text Editor#2：只传用户本轮原始文本。"""
-    return state.get("input_text", "")
+def _format_turn_context(moment: datetime, extra: dict | None = None) -> str:
+    """workflow@20261022 的 <turn_context> 块：动态上下文经 user 消息传递。"""
+    lines = [f"本轮参考时间：{moment.strftime('%Y-%m-%d %H:%M:%S %z')}"]
+    for key, value in (extra or {}).items():
+        lines.append(f"{key}：{value}")
+    return "<turn_context>\n" + "\n".join(lines) + "\n</turn_context>"
+
+
+def _build_user_message(state: AgentState, *, now: datetime) -> str:
+    """对齐 workflow@20261022 采集节点 userChatInput：
+    <turn_context>（本轮参考时间）+ <user_input>（原始输入）。
+    """
+    return (
+        f"{_format_turn_context(now)}\n\n"
+        f"<user_input>\n{state.get('input_text', '')}\n</user_input>"
+    )
 
 
 
@@ -148,9 +161,9 @@ async def _extract_turn_fields(
 ) -> dict:
     """独立提取调用（计划作业 4-4：调用计数可审计——每轮在对话调用之外多一次）。
 
-    提示词为工作流「文本内容提取事故信息」原文（含当前时间与当前表单
-    注入），模型只输出 JSON；校验见 fields.validate_form_update。
-    提取失败不阻塞对话（返回 {}）。
+    提示词为工作流「文本内容提取事故信息」原文（20261022 起时间/表单
+    经 content 的 <turn_context> 传递）；模型只输出 JSON；
+    校验见 fields.validate_form_update。提取失败不阻塞对话（返回 {}）。
     """
     system = (
         _EXTRACTION_MARKER
@@ -158,10 +171,14 @@ async def _extract_turn_fields(
         + render_prompt(EXTRACTION, state, now=now)
         + context_prompt(state, time_context=time_context)
     )
+    message = (
+        f"{_format_turn_context(now, {'当前表单': json.dumps(state.get('accident_fields') or {}, ensure_ascii=False)})}\n\n"
+        f"<user_input>\n{state.get('input_text', '')}\n</user_input>"
+    )
     try:
         raw = await llm.complete(
             system,
-            state.get("input_text", ""),
+            message,
             history=conversation_history(state),
         )
         data = json.loads(raw.strip())
@@ -245,7 +262,7 @@ async def run_collect(state: AgentState, llm: LLMService, *, now: datetime | Non
     moment = observation_time(now)
     evidence = time_evidence(state, moment)
     system_prompt = render_prompt(COLLECTION, state, now=moment) + context_prompt(state, time_context=evidence)
-    user_message = _build_user_message(state)
+    user_message = _build_user_message(state, now=moment)
     current = state.get("stage_code") or COLLECT_STAGE
     raw, stage = await validated_reply(
         llm, system_prompt, user_message, current, history=conversation_history(state),