A2A 任务幂等与恢复：重复消息、断流与停滞任务

流中断 / 响应超时
  ├─ 任务已到终态（COMPLETED / FAILED / CANCELED / REJECTED）？
  │    └─ 是：GetTask 取终态与产出物，结束
  ├─ 订阅通道可用（capabilities.streaming）？
  │    └─ 是：SubscribeToTask 重连，从事件流继续
  │         └─ 服务端不支持从任意点续传时，以收到的事件为准，
  │            重复事件按序号去重（见下）
  ├─ 只剩轮询？
  │    └─ GetTask 按退避轮询，直到终态或停滞判定
  └─ 停滞判定：超过业务上限仍停在 SUBMITTED / WORKING
       ├─ 客户端：CancelTask，或在新任务里重发请求（同 contextId）
       └─ 服务端：把任务转入 FAILED 并写明原因，不要永远 WORKING

启动 → 加载持久化的任务记录
  ├─ 幂等键登记过的任务 → 重放登记结果，不重跑副作用
  ├─ 已在执行的任务 → 恢复执行，或转 FAILED（原因写"服务重启"）
  └─ 无法恢复的 → FAILED + 可读原因；绝不停回 WORKING 等一个不会来的执行器

#!/usr/bin/env bash
set -euo pipefail

: "${A2A_BASE_URL:?Set A2A_BASE_URL}"
: "${A2A_VALID_TOKEN:?Set A2A_VALID_TOKEN}"

send() { # body -> response
  curl --silent -H "Authorization: Bearer $A2A_VALID_TOKEN" \
    -H 'Content-Type: application/json' -d "$1" "$A2A_BASE_URL"
}

# Probe 1 — duplicate message is idempotent:
#   send the same message twice with one messageId; the observable task
#   artifacts must not double. Pick a task whose artifact count is stable.
MSG_ID="probe-$$-$(date +%s)"
BODY="{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"message/send\",\"params\":{\"message\":{\"role\":\"role_user\",\"parts\":[{\"kind\":\"text\",\"text\":\"count words in: one two three\"}],\"messageId\":\"$MSG_ID\",\"contextId\":\"probe-ctx-$MSG_ID\"}}}"

first="$(send "$BODY")"
second="$(send "$BODY")"

task_id="$(printf '%s' "$first" | jq -r '.result.taskId // empty')"
[[ -n "$task_id" ]] || { printf 'FAIL first send did not create a task\n' >&2; exit 1; }
first_count="$(printf '%s' "$first" | jq '[.result.artifacts[]?] | length')"
second_count="$(printf '%s' "$second" | jq '[.result.artifacts[]?] | length')"
[[ "$first_count" == "$second_count" ]] \
  || { printf 'FAIL duplicate message produced extra artifacts (%s vs %s)\n' "$first_count" "$second_count" >&2; exit 1; }
printf 'OK   duplicate message is idempotent (taskId=%s, artifacts=%s)\n' "$task_id" "$first_count"

# Probe 2 — terminal state survives a dropped stream:
#   1. start a streaming task, read the first event, then kill the connection
#   2. SubscribeToTask (or GetTask when streaming is unavailable)
#   3. assert the task reaches a terminal state with the same taskId