feat(observability): 抓取会话逐次尝试与升级路径记成 event

重试链路的关键信息是「升级路径」，而属性表达不了过程：同名属性后写覆盖先写，
三次尝试跑完只剩最后一次的状态码，前两次为什么失败、升到哪一级全被盖掉。

- site_session / rakuma_session：每次尝试各记一条 scrape.attempt event，带
  attempt / outcome / status_code / 截断后的错误串；outcome 区分 http_error、
  bad_status、challenge、validate_failed
- site_session 的每次升级各记一条 scrape.escalate：rewarm_on_home、浏览器兜底
  recovered / failed。兜底失败也要记——不然链路里只剩「最终失败」，看不出浏览器
  这一级试过没有，而「没装 playwright」和「装了也被挡」是两个查法（reason 取
  BrowserFallback.unavailable_reason，为 None 时由 add_event 跳过）
- 三处 span.record_exception 换成 record_error，失败的错误码与可重试位跟着落下来
- 失败页面快照带上 url 与 profile，省得回头对是哪条通道的哪个地址

测试：test_scrape_telemetry.py 补一条会话层用例，用 MockTransport 让所有请求都回
挑战页，断言三次尝试各留一条 event（而不是只剩最后一次）、升级路径依次是
rewarm_on_home → browser，以及浏览器那一级的 outcome=failed 与 reason。

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

app/scraping/services/rakuma_session.py

@@ -29,10 +29,14 @@ from app.shared.errors import (
     UpstreamBlockedError,
     UpstreamRequestError,
 )
-from app.shared.telemetry import snapshot
+from app.shared.telemetry import add_event, record_error, snapshot
 
 logger = logging.getLogger(__name__)
 
+# 逐次尝试 event 里错误串的截断长度：httpx 的异常消息可能很长（带完整 URL 与
+# 底层 socket 错误），而这里只是用来区分「这次是怎么失败的」，前半句就够
+_ERROR_MAX_CHARS = 200
+
 
 class RakumaSession:
     """ラクマ 站点抓取会话，管理并发限流与失败重试"""
@@ -108,7 +112,7 @@ class RakumaSession:
                 )
             except TimeoutError as exc:
                 err = ResourceBusyError()
-                span.record_exception(err)
+                record_error(span, err)
                 span.set_attribute("scrape.fail_reason", "ResourceBusyError")
                 raise err from exc
 
@@ -119,6 +123,13 @@ class RakumaSession:
                         response = await client.get(url)
                     except httpx.HTTPError as exc:
                         last_error = f"{type(exc).__name__}: {exc}"
+                        # 每次尝试各记一条 event：属性同名后写覆盖先写，三次尝试
+                        # 跑完只剩最后一次的状态，中间那两次为什么失败全被盖掉
+                        add_event(span, "scrape.attempt", {
+                            "attempt": attempt,
+                            "outcome": "http_error",
+                            "error": last_error[:_ERROR_MAX_CHARS],
+                        })
                         logger.warning(
                             "ラクマ 抓取请求异常：url=%s attempt=%s/%s err=%s",
                             url, attempt, max_attempts, last_error,
@@ -127,7 +138,7 @@ class RakumaSession:
 
                     if response.status_code == 404:
                         err = ItemNotFoundError(f"Page not found: {url}")
-                        span.record_exception(err)
+                        record_error(span, err)
                         span.set_attribute("scrape.fail_reason", "ItemNotFoundError")
                         raise err
 
@@ -145,6 +156,12 @@ class RakumaSession:
                     last_text = response.text
                     span.set_attribute("scrape.last_status_code", response.status_code)
                     span.set_attribute("scrape.html_bytes", len(response.text))
+                    add_event(span, "scrape.attempt", {
+                        "attempt": attempt,
+                        "outcome": "bad_status",
+                        "status_code": response.status_code,
+                        "error": last_error[:_ERROR_MAX_CHARS],
+                    })
                     logger.warning(
                         "ラクマ 抓取结果异常：url=%s attempt=%s/%s %s",
                         url, attempt, max_attempts, last_error,
@@ -154,9 +171,13 @@ class RakumaSession:
                     err = UpstreamRequestError(f"Upstream request failed: {last_error}")
                 else:
                     err = UpstreamBlockedError(f"Failed to fetch {url}: {last_error}")
-                span.record_exception(err)
+                record_error(span, err)
                 span.set_attribute("scrape.fail_reason", type(err).__name__)
-                snapshot(span, "scrape.failed_html", last_text, self._settings.otel_snapshot_max_bytes)
+                snapshot(
+                    span, "scrape.failed_html", last_text,
+                    self._settings.otel_snapshot_max_bytes,
+                    extra={"scrape.url": url, "scrape.profile": "rakuma"},
+                )
                 raise err
             finally:
                 self._semaphore.release()