fix: improve handling of binary responses in GuzzleHttpClientAspect #1041
Conversation
- Check Content-Type header to determine if response is textual before reading - Return 'Binary Response' placeholder for non-textual content - Avoid unnecessary stream operations on binary responses - Maintain backward compatibility for textual responses This prevents attempting to read or process binary content as text, which could cause memory issues or corrupted logs when dealing with file downloads, images, or other binary API responses.
|
Warning Rate limit exceeded@huangdijia has exceeded the limit for the number of commits or files that can be reviewed per hour. Please wait 8 minutes and 59 seconds before requesting another review. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. 📒 Files selected for processing (2)
Note Other AI code review bot(s) detectedCodeRabbit has detected other AI code review bot(s) in this pull request and will avoid duplicating their findings in the review comments. This may lead to a less comprehensive review. Walkthrough在 Guzzle HTTP 客户端切面中将 Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes
Possibly related PRs
Suggested reviewers
诗一首
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (2)
src/telescope/src/Aspect/GuzzleHttpClientAspect.php (2)
99-102: 建议：考虑扩展文本内容类型检测范围当前的正则表达式较为保守，可能会遗漏一些常见的文本内容类型，例如：
application/javascript和application/ecmascriptapplication/*+json（如application/ld+json）application/*+xml（如application/soap+xml、application/atom+xml）如果项目需要处理这些内容类型，建议扩展正则表达式以包含它们。
如需支持更多文本类型，可应用此修改：
$isTextual = \preg_match( - '/^(text\/|application\/(json|xml|x-www-form-urlencoded|grpc))/i', + '/^(text\/|application\/(json|xml|javascript|ecmascript|x-www-form-urlencoded|grpc|\w+\+(json|xml)))/i', $response->getHeaderLine('Content-Type') ) === 1;
104-107: 可选优化：占位符消息可能产生误导当条件
! ($isTextual && $stream->isSeekable())为真时，既包括二进制响应，也包括文本但不可定位的流。对于后者，返回"Binary Response"可能会产生误导。虽然不处理不可定位的流在技术上是正确的（因为无法在读取后重置位置），但考虑使用更准确的消息，如
"Response Not Captured"或"Binary or Non-Seekable Response"。如需提高准确性，可应用此修改：
- if (! ($isTextual && $stream->isSeekable())) { - return 'Binary Response'; - } + if (! $isTextual) { + return 'Binary Response'; + } + + if (! $stream->isSeekable()) { + return 'Non-Seekable Stream'; + }
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
src/telescope/src/Aspect/GuzzleHttpClientAspect.php(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
src/*/src/**/*.php
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
All components use the namespace pattern:
FriendsOfHyperf\{ComponentName}
Files:
src/telescope/src/Aspect/GuzzleHttpClientAspect.php
**/*.php
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
**/*.php: Follow PSR-12 coding standards for all PHP code
Use PHP-CS-Fixer for code formatting as configured in.php-cs-fixer.php
Use PHPStan for static analysis as configured inphpstan.neon.dist
Files:
src/telescope/src/Aspect/GuzzleHttpClientAspect.php
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (20)
- GitHub Check: Test on PHP 8.2 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.1 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.3 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.2 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.1 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.1 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.3 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.3 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.2 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.2 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.1 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.3 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.1 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.2 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.1 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.3 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.2 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.3 with Swoole 5.1.8
- GitHub Check: Agent
- GitHub Check: Seer Code Review
🔇 Additional comments (1)
src/telescope/src/Aspect/GuzzleHttpClientAspect.php (1)
109-141: 代码结构改进得当新增的
try-finally块确保即使在处理过程中发生异常，可定位的流也会被正确重置。这种结构可以防止流状态问题，是一个良好的防御性编程实践。
There was a problem hiding this comment.
Pull request overview
This PR aims to improve binary response handling in the Telescope component's GuzzleHttpClientAspect by detecting Content-Type headers and avoiding unnecessary processing of binary data. However, the implementation introduces critical bugs that will break existing functionality.
Key Changes:
- Adds Content-Type header validation to distinguish textual from binary responses
- Returns 'Binary Response' placeholder for non-textual content
- Modifies stream handling logic to check seekability earlier
Comments suppressed due to low confidence (1)
src/telescope/src/Aspect/GuzzleHttpClientAspect.php:144
- The
getResponsePayloadmethod lacks test coverage. Given the complexity of this logic and the various edge cases (binary vs textual responses, seekable vs non-seekable streams, different content types, size limits), comprehensive tests should be added to verify correct behavior for all scenarios mentioned in the test plan.
public function getResponsePayload(ResponseInterface $response)
{
$stream = $response->getBody();
// Determine if the response is textual based on the Content-Type header.
$isTextual = \preg_match(
'/^(text\/|application\/(json|xml|x-www-form-urlencoded))/i',
$response->getHeaderLine('Content-Type')
) === 1;
// If the response is not textual or the stream is not seekable, we will return a placeholder.
if (! ($isTextual && $stream->isSeekable())) {
return 'Binary Response';
}
try {
$content = $stream->getContents();
if (is_string($content)) {
if (! $this->contentWithinLimits($content)) {
return 'Purged By Hyperf Telescope';
}
if (
is_array(json_decode($content, true))
&& json_last_error() === JSON_ERROR_NONE
) {
return $this->contentWithinLimits($content) /* @phpstan-ignore-line */
? $this->hideParameters(json_decode($content, true), Telescope::$hiddenResponseParameters)
: 'Purged By Hyperf Telescope';
}
if (Str::startsWith(strtolower($response->getHeaderLine('content-type') ?: ''), 'text/plain')) {
return $this->contentWithinLimits($content) ? $content : 'Purged By Hyperf Telescope'; /* @phpstan-ignore-line */
}
if (Str::contains($response->getHeaderLine('content-type'), 'application/grpc') !== false) {
return TelescopeContext::getGrpcResponsePayload() ?: 'Purged By Hyperf Telescope';
}
}
if (empty($content)) {
return 'Empty Response';
}
} catch (Throwable $e) {
return 'Purged By Hyperf Telescope: ' . $e->getMessage();
} finally {
if ($stream->isSeekable()) {
$stream->rewind();
}
}
return 'HTML Response';
}
![sentry[bot]](https://avatars.githubusercontent.com/in/12637?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
♻️ Duplicate comments (2)
src/telescope/src/Aspect/GuzzleHttpClientAspect.php (2)
102-111: gRPC 响应处理被破坏正则表达式
/^(text\/|application\/(json|xml|x-www-form-urlencoded))/i不匹配application/grpc，导致 gRPC 响应被错误地识别为二进制，在第 110 行提前返回"Binary Response"，永远无法到达第 131-133 行的 gRPC 专用处理逻辑。建议将 gRPC 添加到正则表达式中：
$isTextual = \preg_match( - '/^(text\/|application\/(json|xml|x-www-form-urlencoded))/i', + '/^(text\/|application\/(json|xml|x-www-form-urlencoded|grpc))/i', $response->getHeaderLine('Content-Type') ) === 1;
113-114: 读取流内容前需要先 rewind与 Sentry 版本存在相同问题：
$stream->getContents()从当前位置读取，但在on_stats回调时流指针可能已在末尾，导致返回空字符串。参考相同文件中其他位置（如
RequestHandledListener.php第 136-139 行）的实现，应在读取前先 rewind。try { + if ($stream->isSeekable()) { + $stream->rewind(); + } $content = $stream->getContents();
🧹 Nitpick comments (1)
src/telescope/src/Aspect/GuzzleHttpClientAspect.php (1)
94-98: 占位符字符串风格不一致Sentry 版本使用方括号格式（如
[Streamed Response]），而 Telescope 版本使用无括号格式（Streamed Response）。建议保持两个模块的一致性，便于用户识别这些是占位符而非实际响应内容。
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php(3 hunks)src/telescope/src/Aspect/GuzzleHttpClientAspect.php(4 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
src/*/src/**/*.php
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
All components use the namespace pattern:
FriendsOfHyperf\{ComponentName}
Files:
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.phpsrc/telescope/src/Aspect/GuzzleHttpClientAspect.php
**/*.php
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
**/*.php: Follow PSR-12 coding standards for all PHP code
Use PHP-CS-Fixer for code formatting as configured in.php-cs-fixer.php
Use PHPStan for static analysis as configured inphpstan.neon.dist
Files:
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.phpsrc/telescope/src/Aspect/GuzzleHttpClientAspect.php
🧬 Code graph analysis (2)
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php (3)
src/telescope/src/Aspect/GuzzleHttpClientAspect.php (1)
getResponsePayload(94-146)src/telescope/src/Middleware/TelescopeMiddleware.php (1)
getResponsePayload(106-138)src/telescope/src/Listener/RequestHandledListener.php (1)
getResponsePayload(133-170)
src/telescope/src/Aspect/GuzzleHttpClientAspect.php (1)
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php (1)
getResponsePayload(147-179)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (19)
- GitHub Check: Test on PHP 8.1 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.1 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.3 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.2 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.1 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.2 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.3 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.3 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.2 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.3 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.1 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.2 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.1 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.2 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.1 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.2 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.3 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.3 with Swoole 5.1.8
- GitHub Check: Seer Code Review
🔇 Additional comments (2)
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php (1)
119-123: LGTM!正确地将
$options传递给getResponsePayload方法，支持流式响应检测。src/telescope/src/Aspect/GuzzleHttpClientAspect.php (1)
63-78: LGTM!正确地将
$options捕获到闭包中并传递给getResponsePayload，支持流式响应检测功能。
Updated the regex in GuzzleHttpClientAspect to include 'application/grpc' as a textual Content-Type. This ensures that gRPC responses are correctly identified as textual for further processing.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
There was a problem hiding this comment.
Actionable comments posted: 2
♻️ Duplicate comments (3)
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php (1)
154-163: 非 seekable 流会被getContents()消耗且无法恢复，可能影响业务侧后续读取（且 on_stats 场景下也容易读到空）。这点在切面/监控里风险较高，建议对非 seekable 直接返回占位符而不是读取。$stream = $response->getBody(); try { - if ($stream->isSeekable()) { - $stream->rewind(); - } + if (! $stream->isSeekable()) { + return '[Non-Seekable Stream]'; + } + $stream->rewind(); $content = $stream->getContents();Also applies to: 165-183
src/telescope/src/Aspect/GuzzleHttpClientAspect.php (2)
100-117: gRPC 响应会被提前判定为二进制而直接返回，导致TelescopeContext::getGrpcResponsePayload()分支永远到不了（application/grpc不匹配当前正则）。- $isTextual = \preg_match( - '/^(text\/|application\/(json|xml|x-www-form-urlencoded))/i', - $contentType - ) === 1; + $isTextual = \preg_match( + '/^(text\/|application\/(json|xml|x-www-form-urlencoded|grpc))/i', + $contentType + ) === 1;Also applies to: 143-145
101-117:No Content-Type Header (treated as text)这条分支逻辑当前不可达（空 Content-Type 已强制$isTextual = true），建议删除该三元分支，避免误导维护者。if (! $isTextual) { - return $contentType === '' - ? 'No Content-Type Header (treated as text)' - : 'Binary Response'; + return 'Binary Response'; }
🧹 Nitpick comments (2)
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php (1)
154-158: 文本 MIME 识别建议补充+json/+xml等常见类型，避免误判成二进制（如application/problem+json、application/vnd.api+json）。src/telescope/src/Aspect/GuzzleHttpClientAspect.php (1)
106-110: 文本 MIME 识别建议覆盖.*\+json/.*\+xml等，避免把常见 API 响应误判为二进制。
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php(3 hunks)src/telescope/src/Aspect/GuzzleHttpClientAspect.php(4 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
src/*/src/**/*.php
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
All components use the namespace pattern:
FriendsOfHyperf\{ComponentName}
Files:
src/telescope/src/Aspect/GuzzleHttpClientAspect.phpsrc/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php
**/*.php
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
**/*.php: Follow PSR-12 coding standards for all PHP code
Use PHP-CS-Fixer for code formatting as configured in.php-cs-fixer.php
Use PHPStan for static analysis as configured inphpstan.neon.dist
Files:
src/telescope/src/Aspect/GuzzleHttpClientAspect.phpsrc/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php
🧬 Code graph analysis (2)
src/telescope/src/Aspect/GuzzleHttpClientAspect.php (1)
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php (1)
getResponsePayload(148-184)
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php (3)
src/telescope/src/Aspect/GuzzleHttpClientAspect.php (1)
getResponsePayload(94-158)src/telescope/src/Middleware/TelescopeMiddleware.php (1)
getResponsePayload(106-138)src/telescope/src/Listener/RequestHandledListener.php (1)
getResponsePayload(133-170)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
- GitHub Check: Seer Code Review
- GitHub Check: PHP CS Fixer on PHP 8.1
- GitHub Check: PHP CS Fixer on PHP 8.1
🔇 Additional comments (2)
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php (1)
120-124: 将响应体采集逻辑抽到getResponsePayload()的方向是对的：on_stats里只在 tag 开启时写入http.response.body.contents，避免无谓开销。src/telescope/src/Aspect/GuzzleHttpClientAspect.php (1)
63-79:on_stats把$options透传进getResponsePayload()是必要的（例如 stream 场景），这块改动合理。
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (2)
src/telescope/src/Aspect/GuzzleHttpClientAspect.php (2)
117-153: 非可寻址（non-seekable）响应体在on_stats阶段易落在 EOF：建议直接占位而不是读空
现在只在 seekable 时 rewind，但无论是否 seekable 都会getContents()；对于 non-seekable（且未显式stream=true）常见结果是读到空串并记录'Empty Response'，属于误报/丢信息。建议增加 non-seekable 的降级占位（避免“读空当空响应”）：
$stream = $response->getBody(); try { + if (! $stream->isSeekable()) { + return 'Streamed Response'; + } if ($stream->isSeekable()) { $stream->rewind(); } @@ } finally { $stream->isSeekable() && $stream->rewind(); }
100-115: gRPC 被误判为二进制，导致后续 gRPC 专用处理永远到不了（需修复）
application/grpc目前不匹配正则，直接返回'Binary Response'，从而绕过 Line 141-143 的 gRPC payload 逻辑。- $isTextual = \preg_match( - '/^(text\/|application\/(json|xml|x-www-form-urlencoded))/i', - $contentType - ) === 1; + $isTextual = \preg_match( + '/^(text\/|application\/(json|xml|x-www-form-urlencoded|grpc))/i', + $contentType + ) === 1;
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php(4 hunks)src/telescope/src/Aspect/GuzzleHttpClientAspect.php(4 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
src/*/src/**/*.php
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
All components use the namespace pattern:
FriendsOfHyperf\{ComponentName}
Files:
src/telescope/src/Aspect/GuzzleHttpClientAspect.phpsrc/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php
**/*.php
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
**/*.php: Follow PSR-12 coding standards for all PHP code
Use PHP-CS-Fixer for code formatting as configured in.php-cs-fixer.php
Use PHPStan for static analysis as configured inphpstan.neon.dist
Files:
src/telescope/src/Aspect/GuzzleHttpClientAspect.phpsrc/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php
🧬 Code graph analysis (1)
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php (3)
src/telescope/src/Aspect/GuzzleHttpClientAspect.php (1)
getResponsePayload(94-156)src/telescope/src/Listener/RequestHandledListener.php (1)
getResponsePayload(133-170)src/telescope/src/Middleware/TelescopeMiddleware.php (1)
getResponsePayload(106-138)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (19)
- GitHub Check: Test on PHP 8.3 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.1 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.1 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.2 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.2 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.3 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.2 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.1 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.3 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.1 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.3 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.2 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.2 with Swoole 5.1.8
- GitHub Check: Test on PHP 8.2 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.1 with Swoole 6.0.2
- GitHub Check: Test on PHP 8.3 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.1 with Swoole 6.1.3
- GitHub Check: Test on PHP 8.3 with Swoole 5.1.8
- GitHub Check: Seer Code Review
🔇 Additional comments (3)
src/sentry/src/Tracing/Aspect/GuzzleHttpClientAspect.php (2)
36-37: 新增响应体上限（8KB）方向正确，能避免 OOM/大包拖垮 worker
用MAX_RESPONSE_BODY_SIZE+Utils::copyToString(..., +1)做截断判断很实用。
122-126: 抽取getResponsePayload()并在 span 写入点复用：可维护性更好
http.response.body.contents采集逻辑下沉后，后续对“二进制/流式/截断”等策略调整更集中。src/telescope/src/Aspect/GuzzleHttpClientAspect.php (1)
63-79:on_stats透传$options给 payload 计算：行为更可控
能让stream等选项影响采集逻辑，符合本 PR 目标。
huangdijia
deleted the
feature/telescope-guzzle-aspect-binary-response-fix
branch
…1041) * fix: improve handling of binary responses in GuzzleHttpClientAspect - Check Content-Type header to determine if response is textual before reading - Return 'Binary Response' placeholder for non-textual content - Avoid unnecessary stream operations on binary responses - Maintain backward compatibility for textual responses This prevents attempting to read or process binary content as text, which could cause memory issues or corrupted logs when dealing with file downloads, images, or other binary API responses. * fix: 修复 GuzzleHttpClientAspect 中对响应有效负载的处理逻辑 * fix: 修复 GuzzleHttpClientAspect 中对流响应的处理逻辑 * fix: 修复 GuzzleHttpClientAspect 中对流响应的处理逻辑 * fix: 改进 GuzzleHttpClientAspect 中对二进制响应的处理逻辑 * fix: 简化 GuzzleHttpClientAspect 中对流响应的处理逻辑 * fix: 修复 GuzzleHttpClientAspect 中对二进制响应的处理逻辑 * fix: 修改 GuzzleHttpClientAspect 中对空字符串响应的处理逻辑 * fix: 修复 GuzzleHttpClientAspect 中对可回溯流的处理逻辑 * Add grpc to textual Content-Type detection Updated the regex in GuzzleHttpClientAspect to include 'application/grpc' as a textual Content-Type. This ensures that gRPC responses are correctly identified as textual for further processing. * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix: 修复 GuzzleHttpClientAspect 中对 Content-Type 头的处理逻辑 * fix: 处理 GuzzleHttpClientAspect 中的空响应情况 * fix: 优化 GuzzleHttpClientAspect 中的响应类型声明 * fix: 修复 GuzzleHttpClientAspect 中的响应处理逻辑，确保不再接受空响应 * fix: 修复 GuzzleHttpClientAspect 中的响应内容检查逻辑，确保正确处理空字符串响应 * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix: 优化 GuzzleHttpClientAspect 中的响应内容处理，增加响应内容截断逻辑 * fix: 优化 GuzzleHttpClientAspect 中的响应内容截断逻辑，改善代码可读性 * fix: 修正 GuzzleHttpClientAspect 中的常量注释格式，改善代码一致性 * fix: 优化 GuzzleHttpClientAspect 中的响应内容处理逻辑，确保在异常情况下不影响请求流程 * fix: 更新 GuzzleHttpClientAspect 中的内容类型匹配逻辑，支持 gRPC 响应类型 * fix: 简化 GuzzleHttpClientAspect 中的响应内容类型判断逻辑 * fix: 优化 GuzzleHttpClientAspect 中的响应内容处理逻辑，支持 gRPC 和纯文本响应 --------- Co-authored-by: Deeka Wong <8337659+huangdijia@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Summary
Changes
Test Plan
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.