feat(vendor-channels): 过渡管线诊断快照与 Anthropic 配对自检#255
Merged
Conversation
在 execute_message 和 execute_stream 的 semantic rejection 日志中 附加请求体参数快照（thinking/extended_thinking/reasoning_effort 顶层参数、 会话历史中 thinking blocks 数量、cache_control 存在情况、模型名、消息数）， 用于定位 zhipu glm-4.7 [1210] 参数校验拒绝的具体祸根参数。 🤖 Generated with [Claude Code](https://github.com/claude), [CodeX](https://openai.com), [Gemini](https://github.com/apps/gemini-code-assist) Co-Authored-By: Aurelius Huang<threefish.ai@gmail.com>
…t_types 等维度 PR #244 部署后的诊断日志反转了原推断：失败请求均不含 thinking/cache_control， 说明祸根在更细粒度的参数。扩展 _build_semantic_rejection_diagnostic 函数： 新增维度（仅存在时输出）： - system 形态（string/blocks + cache_control 计数） - tools 数量 + tool_choice 形态 - 采样参数（max_tokens/temperature/top_p/top_k/stop_sequences） - stream / metadata_keys - messages.content 类型分布（含 string content） - 请求体字节数估算（json.dumps） 新增 14 个单元测试（TestBuildSemanticRejectionDiagnostic）覆盖各字段组合 与真实失败请求形态。所有测试通过（1478 passed）。
- pyproject.toml: 版本号取上游 0.4.1a8 - tests/test_router_executor.py: 保留两侧新增的 import 与测试类（TestBuildSemanticRejectionDiagnostic + TestSanitizeUserText + TestExtractSessionTitle） - uv.lock: 同步版本号并重新生成 🤖 Generated with [Claude Code](https://github.com/claude), [CodeX](https://openai.com), [Gemini](https://github.com/apps/gemini-code-assist) Co-Authored-By: Aurelius Huang<threefish.ai@gmail.com>
…] 语义拒绝 基于 2026-05-26 16:30–16:31 日志证据（8 次连续拒绝均含 thinking.type=adaptive）， 在 ZhipuVendor._prepare_request 中实现兼容转换： - adaptive → enabled(budget=16000)：保留 thinking 能力，使用 GLM 原生确认支持的格式 - 新增 _build_zhipu_request_snapshot 诊断快照（成功/失败统一格式，可 diff 对比） - 扩展语义拒绝日志错误体截断（200→500 字符），保留完整字段级诊断 - metadata 暂不处理，待进一步诊断确认兼容性 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Step 1 v2 扩展版本与 Step 1 旧版本同名重复定义，Python 运行时后者覆盖前者 不报错但旧版成为死代码。删除旧版仅保留扩展版本。 🤖 Generated with [Claude Code](https://github.com/claude), [CodeX](https://openai.com), [Gemini](https://github.com/apps/gemini-code-assist) Co-Authored-By: Aurelius Huang<threefish.ai@gmail.com>
冲突文件：docs/agents/issue.md — 保留 HEAD 的 Step 2 根因定位和修复记录 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
在 prepare_zhipu_to_anthropic 管线中新增两个辅助函数： 1. _dump_message_digest: 输出各阶段消息结构摘要（DEBUG 级别）， 用于过渡管线变换前后的可观测性诊断 2. _validate_anthropic_pairing: 独立的 tool_use/tool_result 配对 自检（纯检测，不修改），定位 enforce/sanity 未覆盖的边界 case 🤖 Generated with [Claude Code](https://github.com/claude), [CodeX](https://openai.com), [Gemini](https://github.com/apps/gemini-code-assist) Co-Authored-By: Aurelius Huang<threefish.ai@gmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
摘要
在
prepare_zhipu_to_anthropic过渡管线中引入两个辅助函数，提升变换阶段的可观测性与协议兼容性自检能力，定位enforce_anthropic_tool_pairing与_enforce_pairing_sanity_pass之外的边界 case。变更内容
1.
_dump_message_digest— 过渡管线诊断快照role+content_type_counts），用于诊断变换前后的消息形态差异prepare_zhipu_to_anthropic的 4 个关键阶段插桩（before/after_rewrite/after_enforce/after_strip）2.
_validate_anthropic_pairing— 独立配对自检enforce_*形成职责正交assistant + tool_use，精确记录下一条user消息中匹配/缺失的tool_use_idassistant含tool_use但无后继user）tool_use后非user消息）tool_use_id在user.content.tool_result中未匹配）prepare_zhipu_to_anthropic末端执行，发现问题时追加anthropic_pairing_validation_issues适配标签设计取舍
enforce_anthropic_tool_pairing：保持原有自动修复链路的稳定性，新增自检作为独立保险层测试覆盖
新增
TestDumpMessageDigest与TestValidateAnthropicPairing测试类，覆盖：tool_result检测prepare_zhipu_to_anthropic的集成（正常路径不触发标签，构造场景下捕获缺陷）测试计划
uv run pytest tests/test_vendor_channels.py -k "TestDumpMessageDigest or TestValidateAnthropicPairing" -vuv run pytest tests/test_vendor_channels.py -v