browser-replay

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Browser Replay

浏览器重放

Re-drive a recorded session trajectory. Used for regression testing, deterministic re-runs, and as the verification path that

browser-record

plus

browser-selectors

actually produces something replayable.

This skill is the load-bearing assumption of the v0.2.0 architecture. ADR-0001 Verification §4 requires ≥80% replay success across 10 distinct sites of varying drift profiles before the proposal moves from
Proposed
→
Accepted
. If you find replay unreliable, capture the failure modes in
findings.md
and report them up the ADR.

重新驱动已录制的会话轨迹。用于回归测试、确定性重跑，以及作为验证路径，确保

browser-record

搭配

browser-selectors

生成的内容可被重放。

该技能是v0.2.0架构的核心假设。 ADR-0001验证第4节要求，在10个具有不同漂移特征的站点上实现≥80%的重放成功率，提案才能从
Proposed
（提议）状态转为
Accepted
（已接受）状态。如果发现重放不可靠，请在
findings.md
中记录失败模式并上报至ADR。

When to use

使用场景

Regression-testing a UI flow after a deploy.
Reproducing a bug captured in a prior session.
Comparing two runs of the same flow for
```
browser-screenshot-diff
```
.
Forking a session (
```
/ruflo-browser fork
```
) and replaying the parent before mutating.

部署后对UI流程进行回归测试。
复现先前会话中捕获的Bug。
对比同一流程的两次运行结果，用于
```
browser-screenshot-diff
```
。
分叉会话（
```
/ruflo-browser fork
```
）并在修改前重放父会话。

Steps

操作步骤

Locate the source session:

bash

npx -y ruvector@0.2.25 rvf status <session-id>.rvf

Load the trajectory:

bash

Read .../trajectory.ndjson

Each line is

{ts, action, args, selector, result}

Open a fresh browser via
```
mcp__claude-flow__browser_open
```
(target URL = original or
```
--url
```
override).
For each trajectory step, dispatch the matching MCP tool (
```
browser_click
```
,
```
browser_fill
```
,
```
browser_eval
```
, etc.) with the recorded args.

On selector miss, do not fail immediately — query the

browser-selectors

namespace for an embedding-similar selector for the same

<host>:<intent>

and retry once:

bash

npx -y @claude-flow/cli@latest memory search --namespace browser-selectors \
  --query "<host> <intent>" --limit 5

Record a new trajectory for the replay run (allocate a fresh RVF container, lineage-tracked via
```
rvf derive
```
).
Verdict: tally matched-step / total-step ratio. Default tolerance threshold is 0.85 (configurable via
```
--tolerance
```
). Verdict goes into
```
findings.md
```
.

定位源会话:

bash

npx -y ruvector@0.2.25 rvf status <session-id>.rvf

加载轨迹:

bash

Read .../trajectory.ndjson

每一行格式为

{ts, action, args, selector, result}

。

通过
mcp__claude-flow__browser_open
打开新浏览器（目标URL为原始URL或通过
```
--url
```
覆盖）。
针对每个轨迹步骤，调度匹配的MCP工具（
```
browser_click
```
、
```
browser_fill
```
、
```
browser_eval
```
等）并传入录制的参数。

当选择器匹配失败时，不要立即终止——查询

browser-selectors

命名空间，获取具有相同

<host>:<intent>

的嵌入相似度匹配选择器，并重试一次:

bash

npx -y @claude-flow/cli@latest memory search --namespace browser-selectors \
  --query "<host> <intent>" --limit 5

为重放运行录制新轨迹（分配新的RVF容器，通过
```
rvf derive
```
进行 lineage 追踪）。
判定结果: 计算匹配步骤数/总步骤数的比率。默认容错阈值为0.85（可通过
```
--tolerance
```
配置）。判定结果需写入
```
findings.md
```
。

Caveats

注意事项

Browserbase explicitly does not offer replay (rrweb session replay was deprecated). We're betting on selector-embedding recovery; expect noise on heavily drifted sites.
Network nondeterminism (timing, content variation) can produce false-fail verdicts. Use
```
--mutate
```
to inject expected variation or pin to a fixture.
For visual diff, chain into
```
browser-screenshot-diff
```
against the parent session id.
If selector recovery requires more than one retry per step, log it. That's the signal that the site needs a re-record, not a replay.

Browserbase明确不提供重放功能（rrweb会话重放已被弃用）。我们寄希望于选择器嵌入恢复技术；在DOM漂移严重的站点上可能会出现异常。
网络不确定性（时序、内容变化）可能导致误判。使用
```
--mutate
```
注入预期变化或固定到测试夹具。
如需视觉对比，可将结果与父会话ID关联到
```
browser-screenshot-diff
```
工具中。
如果每个步骤的选择器恢复需要超过一次重试，请记录该情况。这表明该站点需要重新录制会话，而非进行重放。