diff --git a/agents/openclaw-main/warp-acp-ops.md b/agents/openclaw-main/warp-acp-ops.md
index faf6217..c01501b 100644
--- a/agents/openclaw-main/warp-acp-ops.md
+++ b/agents/openclaw-main/warp-acp-ops.md
@@ -102,6 +102,25 @@ For `opencode-warp-infini-glm`:
 - fallback candidate: `infini / kimi-k2.5`
 - fallback candidate: `infini / minimax-m2.5`
 
+## Continuation Rule for Limited / Failed ACP Runs
+
+If an ACP `opencode` run is interrupted by provider-side request limits or similar provider failures, the replacement run should continue with context rather than restart from zero.
+
+Required operator behavior:
+
+1. classify the failure as provider-side (rate limit / quota / upstream unavailable) vs task-side
+2. summarize the interrupted task before switching agents
+3. start a new ACP run with the next fallback Warp agent
+4. provide the summary so the new run can continue remaining work
+
+Minimum summary fields:
+
+- original task objective
+- work completed so far
+- files touched
+- relevant error / provider limit signal
+- remaining work
+
 ## Testing Checklist (for later execution)
 
 1. Confirm `~/.openclaw/.env` exists on each machine
diff --git a/daily/2026-03-17.md b/daily/2026-03-17.md
index 4bda9a8..5188241 100644
--- a/daily/2026-03-17.md
+++ b/daily/2026-03-17.md
@@ -19,7 +19,8 @@
   - `opencode-warp-infini-minimax`
   - `opencode-warp-infini-glm`
 - 已确定 wrapper 方案为后续 ACP 稳定注入点：wrapper 显式读取 `~/.openclaw/.env`，不依赖 `~/.zshrc`
-- 已将 fallback 纳入规范设计：当 provider 配额耗尽、限流或模型不可用时，优先同模型跨 provider fallback，其次同 provider 跨相邻模型 fallback
+- 已将 fallback 纳入规范设计：当 provider 配额耗尽、限流或模型不可用时，优先同模型/同任务意图的跨 provider fallback，其次同 provider 跨相邻模型 fallback
+- 已补充 ACP 连续执行规则：若中途因 provider 请求限制、quota、rate limit 等失败，应先总结当前任务已完成内容、失败点与剩余工作，再切换到新的 Warp fallback agent 继续执行，而不是盲目从零重跑
 - 新增长期设计文档：`shared/long-term/projects/warp-acp-integration.md`
 - 新增 OpenClaw 私域操作文档：`agents/openclaw-main/warp-acp-ops.md`
 
diff --git a/shared/long-term/projects/warp-acp-integration.md b/shared/long-term/projects/warp-acp-integration.md
index ed29cd3..64f9877 100644
--- a/shared/long-term/projects/warp-acp-integration.md
+++ b/shared/long-term/projects/warp-acp-integration.md
@@ -186,12 +186,41 @@ This preserves behavior consistency as much as possible before changing model fa
 For `opencode-warp-infini-kimi`:
 
 1. primary: `infini / kimi-k2.5`
-2. fallback-1: another provider offering `kimi-k2.5` (for example `ckimi / kimi-k2.5`)
+2. fallback-1: `ckimi / kimi-for-coding`
+3. fallback-2: `infini / glm-5`
+4. fallback-3: `infini / minimax-m2.5`
+
+For `opencode-warp-ckimi-kimi-for-coding`:
+
+1. primary: `ckimi / kimi-for-coding`
+2. fallback-1: `infini / kimi-k2.5`
 3. fallback-2: `infini / glm-5`
 4. fallback-3: `infini / minimax-m2.5`
 
 Exact fallback order should be documented per agent as providers are added.
 
+### ACP continuation rule after provider limit / request failure
+
+When an ACP task fails mid-run because a provider is limited, rate-limited, quota-exhausted, or otherwise request-blocked, the system should not just restart blindly.
+
+Use this continuation rule:
+
+1. detect that the failure is provider/request related rather than task-logic related
+2. produce a concise task-state summary of what had already been completed, what failed, and what remains
+3. start a new `opencode` ACP run using the next Warp fallback agent
+4. pass the summary into the new run so the replacement agent can continue instead of redoing everything from scratch
+
+The summary should include, when available:
+
+- original task goal
+- completed steps
+- files changed or attempted
+- command outputs or relevant error lines
+- exact provider failure signal (for example rate limit / quota exhaustion)
+- remaining work
+
+This behavior is part of the Warp fallback design, especially for long-running coding tasks where provider limits may interrupt execution mid-stream.
+
 ## Operational Reminder
 
 If runtime errors show quota exhaustion or provider-specific capacity limits during an ACP task, the operator should treat that as a routing event, not just a task failure. The next step is to move to the documented fallback provider/model path.