Compare commits
11 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| ab00aa4457 | |||
| 433039be79 | |||
| b4812e12c8 | |||
| 067b15be48 | |||
| 7b2f6105f3 | |||
| 393f2bf617 | |||
| 87c261bf73 | |||
| 300ced5dbd | |||
| a81cc91124 | |||
| e71a623b04 | |||
| 0c1165965f |
@@ -113,6 +113,9 @@ PGW_TELEMETRY_BACKEND=none # sqlite | postgres | none(必填)
|
|||||||
# # 也要能拿原样的请求复现与重放;截断后这两件事都做不成,而既有下游正依赖这一行为。
|
# # 也要能拿原样的请求复现与重放;截断后这两件事都做不成,而既有下游正依赖这一行为。
|
||||||
# # 反面同样要看清: 不截断意味着客户合同、标书全文无限期留在 llm_calls 里,
|
# # 反面同样要看清: 不截断意味着客户合同、标书全文无限期留在 llm_calls 里,
|
||||||
# # 多租户下还混在同一张表。真在意留存面的部署应显式设一个上限,并配保留期与访问控制。
|
# # 多租户下还混在同一张表。真在意留存面的部署应显式设一个上限,并配保留期与访问控制。
|
||||||
|
# # 1.3.5 补充: error_body(网关响应正文摘要)沿用库内 summarize_body 上限,
|
||||||
|
# # 结构化耗尽终态行的 error 说明自带有界限长(不含模型原始正文);
|
||||||
|
# # **两者都不在本键的覆盖面内**,估算留存面时要单独计。
|
||||||
# PGW_PRICING_PATH=config/prices.json # 可选: {"<model>": {"input_per_1m": x, "output_per_1m": y}};缺省 cost 恒 None
|
# PGW_PRICING_PATH=config/prices.json # 可选: {"<model>": {"input_per_1m": x, "output_per_1m": y}};缺省 cost 恒 None
|
||||||
# # 可选第三档 "cached_input_per_1m": z —— 供应商 prompt cache 命中部分的单价;
|
# # 可选第三档 "cached_input_per_1m": z —— 供应商 prompt cache 命中部分的单价;
|
||||||
# # 不填即命中部分也按 input 全额计(库不猜折扣率),cost 会偏高
|
# # 不填即命中部分也按 input 全额计(库不猜折扣率),cost 会偏高
|
||||||
|
|||||||
@@ -1,5 +1,39 @@
|
|||||||
# Changelog
|
# Changelog
|
||||||
|
|
||||||
|
## 1.3.5(2026-09-09)
|
||||||
|
|
||||||
|
把治理单位从「一次尝试」补齐到「一次逻辑调用」(issue #19、#23)。此前重试、换源、结构化重问、embedding 分批都各自独立可见,而「这一次调用总共打了几次、总共花了多久、最后为什么失败」在库外拼不出来;结构化耗尽、embedding/OCR 的无源与准入拒绝更是**一条遥测行都没有**。
|
||||||
|
|
||||||
|
### 公共面四项变更
|
||||||
|
|
||||||
|
| # | 位置 | 变更 | 谁会当场断 |
|
||||||
|
| --- | --- | --- | --- |
|
||||||
|
| 1 | `polygateway.CallStats` | 新导出的 frozen dataclass(`logical_call_id` / `attempts` / `total_latency_ms`) | 无(纯新增) |
|
||||||
|
| 2 | `LLMResponse` / `EmbeddingResponse` / `OcrTextResult` / `OcrLayoutResult` | 各追加**末尾**字段 `call_stats: CallStats \| None = None` | 按位置解包这四个类型的代码 |
|
||||||
|
| 3 | `ports.TelemetryRecorder.record_llm_call()` | 新增 **10 个无默认值 keyword-only 参数**(26 → 36 参) | 任何自建 recorder——且**在装配期当场报错**,不再是运行期静默丢行 |
|
||||||
|
| 4 | 遥测表 `llm_calls` | 追加 10 列(INSERT 字段 26 → 36,物理列 27 → 37);新增 `event_kind='terminal_failure'` 行 | 按旧口径计失败调用数的 SQL |
|
||||||
|
|
||||||
|
第 3 条的装配期报错是有意的:`_record` 的 `except Exception` 会把旧签名 recorder 的 `TypeError` 吞成 warning,后果是下游升级后 **100% 丢遥测且调用照常成功**。降级方向的铁律管的是运行期写失败,不是装配错误。`**fields` 形态的 recorder 不受影响。
|
||||||
|
|
||||||
|
### 下游必须做的事
|
||||||
|
|
||||||
|
| 动作 | 说明 |
|
||||||
|
| --- | --- |
|
||||||
|
| **计失败调用改 `WHERE event_kind = 'terminal_failure'`** | 一次逻辑调用恰好一条终态行。`error IS NOT NULL` 跨尝试行与终态行,升级后计数会变大 |
|
||||||
|
| `AVG(latency_ms)` 按 `event_kind` 分组 | 终态行的 `latency_ms` 是整个逻辑调用的总耗时,与单次尝试不同量纲 |
|
||||||
|
| 自建 recorder 补齐 10 参 | 或改成 `**fields`;同时同步自己的 schema 与 INSERT 字段 |
|
||||||
|
| PG manual 档下游补列 | `telemetry_schema_sql("postgres")` 自取;不补则这 10 个维度按现有列裁剪后静默不落库(库发一条点名警告) |
|
||||||
|
| 注意失败行可能带 `http_status_code = 200` | MonkeyOCR 的 `success != true` 就是 200 下的失败,该列不可当成败判据 |
|
||||||
|
|
||||||
|
费用口径**不变**:终态行 `cost IS NULL`、`usage_source='unavailable'`、token 为 0,不参与 `SUM(cost)`。400 密集负载下错误行会翻倍(既有 attempt 错误行 + 新增终态行),这是已批准的下游可见变化。
|
||||||
|
|
||||||
|
### 其他
|
||||||
|
|
||||||
|
- 新列全部可空、无默认值、追加在现有末列之后;**旧行不回填**(NULL 表达「补列之前根本没记过这件事」),滚动升级期新旧进程可写同一张表。
|
||||||
|
- `error_body` 沿用 `summarize_body` 上限,结构化耗尽终态行的 `error` 带有界说明(不含模型原始正文);**两者都不在 `PGW_TELEMETRY_TEXT_CAP` 覆盖面内**。
|
||||||
|
- 修正历史误标:`embed()` 非 200 的失败现在报 `operation="embedding"`。遥测新列 `operation` 由调用点给定,与 `exc.operation` 是两个语义。
|
||||||
|
- 重试预算与退避、429 免预算与 stall 算法、取消结算、限流/熔断语义、缓存 key 公式一字未改。
|
||||||
|
|
||||||
## 1.3.4(2026-09-09)
|
## 1.3.4(2026-09-09)
|
||||||
|
|
||||||
> [!WARNING]
|
> [!WARNING]
|
||||||
|
|||||||
@@ -103,6 +103,8 @@ make ci # 只读验证(check + test)
|
|||||||
|
|
||||||
Gitea 包 registry 是 **owner 级**(`/iomgaa/-/packages/`)不是仓库级;PyPI 元数据不含仓库字段,故不会自动挂到 `PolyGateway/packages`,需在包页面手动 Link to a repository。
|
Gitea 包 registry 是 **owner 级**(`/iomgaa/-/packages/`)不是仓库级;PyPI 元数据不含仓库字段,故不会自动挂到 `PolyGateway/packages`,需在包页面手动 Link to a repository。
|
||||||
|
|
||||||
|
发布验证补充(2026-09-09 实测):私有索引不镜像 setuptools,下载 sdist 时 pip 即使带 `--no-deps` 仍可能尝试安装构建依赖;已具备构建工具的 conda 环境可加 `--no-build-isolation`,仍须核对下载来源与散列。包关联 POST 本次返回400,但匿名包页面和认证 GET 包 API 均证实已关联目标仓库;**400本身不算成功,也不能直接推断已关联**,必须读取实际 `repository.full_name` 与页面链接。包 API 可能要求认证(匿名401),页面仍应匿名亲查;不要为重试关联先解绑现有正确关系。
|
||||||
|
|
||||||
### 4.5 配置管理
|
### 4.5 配置管理
|
||||||
- 工程配置走 `pydantic-settings` + `.env`(模板 `.env.example`,敏感项不提交);严禁硬编码默认值;缺失关键配置直接报错。
|
- 工程配置走 `pydantic-settings` + `.env`(模板 `.env.example`,敏感项不提交);严禁硬编码默认值;缺失关键配置直接报错。
|
||||||
- 多源命名约定 `{SCOPE}__{PROVIDER}__{N}__{FIELD}`;韧性参数键名沿用三项目习惯(`LLM_TIMEOUT` 等),降低迁移成本。
|
- 多源命名约定 `{SCOPE}__{PROVIDER}__{N}__{FIELD}`;韧性参数键名沿用三项目习惯(`LLM_TIMEOUT` 等),降低迁移成本。
|
||||||
|
|||||||
@@ -20,7 +20,8 @@
|
|||||||
| 流式看门狗 | TTFT / inter-token / 总超时三层活性;thinking token 刷活性不计结果;截断流(缺 `[DONE]`)判瞬时不入缓存 |
|
| 流式看门狗 | TTFT / inter-token / 总超时三层活性;thinking token 刷活性不计结果;截断流(缺 `[DONE]`)判瞬时不入缓存 |
|
||||||
| 推理可观测性 | "这次到底推理没推理"由多信号裁定(推理正文压倒 usage 明细),三态落在 `LLMResponse.thinking_observation`:`observed` / `absent` / `unknown`——**`unknown` 是"本次判不出",不是"没推理"**;本次实发档位与实测观测矛盾时按 `(源, 模型, 生效档位)` 各告警一次(能力表过期、开启未生效、注入了却观测不到;同一模型的 low 与 max 是两个独立的矛盾,不共用节流键);裁定结果随遥测落库 |
|
| 推理可观测性 | "这次到底推理没推理"由多信号裁定(推理正文压倒 usage 明细),三态落在 `LLMResponse.thinking_observation`:`observed` / `absent` / `unknown`——**`unknown` 是"本次判不出",不是"没推理"**;本次实发档位与实测观测矛盾时按 `(源, 模型, 生效档位)` 各告警一次(能力表过期、开启未生效、注入了却观测不到;同一模型的 low 与 max 是两个独立的矛盾,不共用节流键);裁定结果随遥测落库 |
|
||||||
| 推理档位 | 推理是**八档**(`none`/`auto`/`minimal`/`low`/`medium`/`high`/`xhigh`/`max`)而非开关:源级 `REASONING_EFFORT` + 请求级 `chat(reasoning_effort=...)`,`ENABLE_THINKING` 保留为语法糖;库带 24 条能力表(逐条 evidence 自报实测/文档推定),档位打空**默认报错并给出该模型最省的可用档与该配的键**,要静默映射需显式配 `EFFORT_FALLBACK=nearest`;实发档随 `LLMResponse.applied_effort` 与遥测落库 |
|
| 推理档位 | 推理是**八档**(`none`/`auto`/`minimal`/`low`/`medium`/`high`/`xhigh`/`max`)而非开关:源级 `REASONING_EFFORT` + 请求级 `chat(reasoning_effort=...)`,`ENABLE_THINKING` 保留为语法糖;库带 24 条能力表(逐条 evidence 自报实测/文档推定),档位打空**默认报错并给出该模型最省的可用档与该配的键**,要静默映射需显式配 `EFFORT_FALLBACK=nearest`;实发档随 `LLMResponse.applied_effort` 与遥测落库 |
|
||||||
| 遥测与成本 | 每次调用(含缓存命中与失败)必录 26 字段;SQLite / Postgres 后端(表已存在时**不需要** schema 建表权限,最小权限账号可直接用);按价格表折算成本落库(注意 `LLMResponse.cost` 本身恒为 `None`,成本只进遥测);多模态内容摘要落库不存原图 |
|
| 遥测与成本 | 每次调用(含缓存命中与失败)必录 36 字段;三类行(`event_kind` = `attempt` / `cache_hit` / `terminal_failure`)加逐源诊断列(`http_status_code` / `error_type` / `cause_type` / `error_body`);SQLite / Postgres 后端(表已存在时**不需要** schema 建表权限,最小权限账号可直接用);按价格表折算成本落库(注意 `LLMResponse.cost` 本身恒为 `None`,成本只进遥测);多模态内容摘要落库不存原图 |
|
||||||
|
| 逻辑调用统计 | 治理单位是**一次逻辑调用**而非一次尝试:四种响应(chat / embedding / OCR 两种)带 `call_stats`(`logical_call_id` / `attempts` / `total_latency_ms`),重试、换源、结构化重问、embedding 分批共享同一逻辑 ID;每次**领域失败**另落一条 `terminal_failure` 行,失败调用数从此是一条 `WHERE event_kind = 'terminal_failure'`,详见[1.3.5 逻辑调用统计与失败诊断](#135-逻辑调用统计与失败诊断) |
|
||||||
| 遥测的资源与降级 | Postgres 池**闲时占 0 条连接**、忙时上限可配(`PGW_TELEMETRY_PG_POOL_MAX`,缺省 4),每次写入有硬预算(`PGW_TELEMETRY_PG_WRITE_TIMEOUT_S`,缺省 5s);后端不可用是**可恢复的降级**(冷却 60s 后自动重试,DBA 建完表/放开权限即自愈),永久失能只留给 DSN 本身写错;降级状态可编程查询——`client.telemetry_status` 给出 `degraded`/`fatal`/`reason`/`dropped_rows` 等只读快照,不必再靠人工对账。**对账要同时看 `degraded` 与 `dropped_rows`**: 池饱和超预算丢的行走行级丢弃,`degraded` 保持 `False`(后端没挂,是本进程并发超了),只按 `degraded` 告警会看不见这一类丢行——而它恰是 `pool_max` 配小了的唯一信号 |
|
| 遥测的资源与降级 | Postgres 池**闲时占 0 条连接**、忙时上限可配(`PGW_TELEMETRY_PG_POOL_MAX`,缺省 4),每次写入有硬预算(`PGW_TELEMETRY_PG_WRITE_TIMEOUT_S`,缺省 5s);后端不可用是**可恢复的降级**(冷却 60s 后自动重试,DBA 建完表/放开权限即自愈),永久失能只留给 DSN 本身写错;降级状态可编程查询——`client.telemetry_status` 给出 `degraded`/`fatal`/`reason`/`dropped_rows` 等只读快照,不必再靠人工对账。**对账要同时看 `degraded` 与 `dropped_rows`**: 池饱和超预算丢的行走行级丢弃,`degraded` 保持 `False`(后端没挂,是本进程并发超了),只按 `degraded` 告警会看不见这一类丢行——而它恰是 `pool_max` 配小了的唯一信号 |
|
||||||
| 调用方维度 | 每次调用可带 `tenant_id`(遥测表的真实列,可挂 RLS、可建复合索引)与 `meta`(≤16 个自定义 KV);四个公共方法全覆盖,校验超限即报错;**库只交付列,不启用 RLS、不建索引** |
|
| 调用方维度 | 每次调用可带 `tenant_id`(遥测表的真实列,可挂 RLS、可建复合索引)与 `meta`(≤16 个自定义 KV);四个公共方法全覆盖,校验超限即报错;**库只交付列,不启用 RLS、不建索引** |
|
||||||
| 遥测表治理 | `llm_calls` 是**下游的表**:PG 侧缺省**不再自动 `ALTER` 补列**(`PGW_TELEMETRY_SCHEMA_MODE` 三态,不设则 sqlite→auto、postgres→manual),manual 档点名缺列并按现有列裁剪写入;`telemetry_schema_sql(backend)` 自取可粘进迁移文件的建表/补列 SQL;`PGW_TELEMETRY_TEXT_CAP` 限正文长度(**不设 = 存全文**);保留期与访问控制走[生产部署 DDL 模板](#生产部署-ddl-模板postgresql)加 `tools/telemetry_retention.py` |
|
| 遥测表治理 | `llm_calls` 是**下游的表**:PG 侧缺省**不再自动 `ALTER` 补列**(`PGW_TELEMETRY_SCHEMA_MODE` 三态,不设则 sqlite→auto、postgres→manual),manual 档点名缺列并按现有列裁剪写入;`telemetry_schema_sql(backend)` 自取可粘进迁移文件的建表/补列 SQL;`PGW_TELEMETRY_TEXT_CAP` 限正文长度(**不设 = 存全文**);保留期与访问控制走[生产部署 DDL 模板](#生产部署-ddl-模板postgresql)加 `tools/telemetry_retention.py` |
|
||||||
@@ -71,13 +72,50 @@ M8 包括 reasoning_effort、enable_thinking、thinking、thinking_budget、reas
|
|||||||
|
|
||||||
**本版验收例外(2026-09-09 用户正式批准)**:不再补全模型矩阵;既有失败、UNKNOWN、不可达、缺轮及下游现行配置缺证据如实保留,不改成 PASS。M2 两型的定向成功不代表全模型通过;三项目实际配置迁移仍未核验,合成兼容测试不能代替,缓存迁移操作前置也未被豁免。逐项实测、网络诊断与证据索引见[1.3.4 验证记录](research-wiki/findings/2026-09-09-134-thinking-contracts-validation.md)。
|
**本版验收例外(2026-09-09 用户正式批准)**:不再补全模型矩阵;既有失败、UNKNOWN、不可达、缺轮及下游现行配置缺证据如实保留,不改成 PASS。M2 两型的定向成功不代表全模型通过;三项目实际配置迁移仍未核验,合成兼容测试不能代替,缓存迁移操作前置也未被豁免。逐项实测、网络诊断与证据索引见[1.3.4 验证记录](research-wiki/findings/2026-09-09-134-thinking-contracts-validation.md)。
|
||||||
|
|
||||||
|
## 1.3.5 逻辑调用统计与失败诊断
|
||||||
|
|
||||||
|
> [!WARNING]
|
||||||
|
> **升级后失败行会变多,旧的"失败调用数" SQL 会多数。** 每次领域失败除逐次尝试行外另写一条 `terminal_failure` 行;自建 recorder 若未跟进 10 个新参数,会在**装配期**就报错(不是运行期静默丢行)。
|
||||||
|
|
||||||
|
本版把治理单位从"一次尝试"补齐到"一次逻辑调用"。两件事: 四种响应带上 `call_stats`;遥测表补 10 列并新增一类行。
|
||||||
|
|
||||||
|
### 读 `call_stats`
|
||||||
|
|
||||||
|
```python
|
||||||
|
resp = await client.chat([{"role": "user", "content": "hi"}])
|
||||||
|
stats = resp.call_stats # EmbeddingResponse / OcrTextResult / OcrLayoutResult 同名字段
|
||||||
|
stats.logical_call_id # 一次逻辑调用一个 ID:重试/换源/重问/分批共享
|
||||||
|
stats.attempts # 真实打出去的尝试次数(免预算 429 也计;缓存命中为 0)
|
||||||
|
stats.total_latency_ms # 含缓存 IO、退避、准入等待、重问与内联遥测收尾的墙钟
|
||||||
|
```
|
||||||
|
|
||||||
|
`call_stats` 为 `None` 意为**未知**(如第三方合成的响应、或旧缓存条目回放),不得读成 0。失败时异常对象上**不挂任何统计字段**——要归因请查遥测表。
|
||||||
|
|
||||||
|
### 下游 SQL 迁移五项
|
||||||
|
|
||||||
|
| # | 改什么 | 理由 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| 1 | 计失败调用改成 `WHERE event_kind = 'terminal_failure'` | 一次逻辑调用恰好一条终态行 |
|
||||||
|
| 2 | `error IS NOT NULL` 不再是失败调用的判据 | 它同时命中尝试错误行与终态行,升级后计数变大 |
|
||||||
|
| 3 | `AVG(latency_ms)` 须按 `event_kind` 分组 | 终态行的 `latency_ms` 是**整个逻辑调用**的总耗时,与单次尝试不同量纲 |
|
||||||
|
| 4 | 费用口径**不变** | 终态行 `cost IS NULL`、`usage_source='unavailable'`、token 为 0,不参与 `SUM(cost)` |
|
||||||
|
| 5 | 失败行可能带 `http_status_code = 200` | MonkeyOCR 的 `success != true` 就是 200 下的失败,该列不可当成败判据 |
|
||||||
|
|
||||||
|
归因查询的典型形态: 一条 `WHERE logical_call_id = :lcid` 同时拿到整池终态原因(`terminal_failure` 行的 `error` / `error_type`)与逐源现场(`attempt` 行的 `source_name` / `http_status_code` / `cause_type` / `error_body`)。**终态行的 `http_status_code`/`cause_type`/`error_body` 恒为 NULL**: 拿最后一个源的现场冒充整池归因是错的。
|
||||||
|
|
||||||
|
### 存储侧升级
|
||||||
|
|
||||||
|
新增 10 列全部可空、无默认值、追加在现有末列之后(`scope`、`operation`、`logical_call_id`、`event_kind`、`http_status_code`、`error_type`、`cause_type`、`error_body`、`attempts`、`total_latency_ms`),INSERT 字段 26 → 36、物理列 27 → 37。auto 档自动追加;manual 档一条 DDL 不发、按现有列裁剪写入并点名缺列(补列 SQL 由 `telemetry_schema_sql("postgres")` 自取)。**旧行的新列一律 NULL 且不回填**——NULL 表达的是"补列之前根本没记过这件事";滚动升级期新旧进程可写同一张表。
|
||||||
|
|
||||||
|
自建 `TelemetryRecorder` 的下游请同步补齐这 10 个 keyword-only 无默认值参数(或改成 `**fields` 形态),并同步自己的 schema 与 INSERT 字段。装配期形状闸只能证明形状能被接受,证不了函数体真的落这些列。
|
||||||
|
|
||||||
## 安装
|
## 安装
|
||||||
|
|
||||||
发布在实验室 Gitea PyPI(公开包,匿名可装):
|
发布在实验室 Gitea PyPI(公开包,匿名可装):
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
pip install --extra-index-url https://gitea.iomgaa.online/api/packages/iomgaa/pypi/simple/ \
|
pip install --extra-index-url https://gitea.iomgaa.online/api/packages/iomgaa/pypi/simple/ \
|
||||||
"polygateway[redis,postgres,structured]>=1.3.4,<2"
|
"polygateway[redis,postgres,structured]>=1.3.5,<2"
|
||||||
```
|
```
|
||||||
|
|
||||||
核心仅依赖 `httpx` + `pydantic`;按需选 extras:
|
核心仅依赖 `httpx` + `pydantic`;按需选 extras:
|
||||||
@@ -398,6 +436,8 @@ PGW_TELEMETRY_TEXT_CAP=2000 # 落库正文的字符上限;不设 = 存全
|
|||||||
|
|
||||||
**`PGW_TELEMETRY_TEXT_CAP` 的覆盖面必须说清,否则合规判断会出错。** cap 落在四处:`messages` 里每条消息的字符串 `content`、多模态 content 数组中 `type == "text"` 的 part 的 `text`,以及 `response` 与 `thinking` 两列。消息侧的这个面与缓存摘要函数 `digest_messages` 一致——**只碰 `content`**,消息里别的字段一概不碰。所以调用方自己塞进 `tool_calls.function.arguments`、`name` 等字段的内容**不在覆盖范围内**:开了 cap 不等于表里没有全文残留。另需知道:缺省是**不截断**(存全文),而截断之后遥测不再是可复现重放的证据。
|
**`PGW_TELEMETRY_TEXT_CAP` 的覆盖面必须说清,否则合规判断会出错。** cap 落在四处:`messages` 里每条消息的字符串 `content`、多模态 content 数组中 `type == "text"` 的 part 的 `text`,以及 `response` 与 `thinking` 两列。消息侧的这个面与缓存摘要函数 `digest_messages` 一致——**只碰 `content`**,消息里别的字段一概不碰。所以调用方自己塞进 `tool_calls.function.arguments`、`name` 等字段的内容**不在覆盖范围内**:开了 cap 不等于表里没有全文残留。另需知道:缺省是**不截断**(存全文),而截断之后遥测不再是可复现重放的证据。
|
||||||
|
|
||||||
|
**1.3.5 新增的两处诊断文本同样不在 cap 覆盖内**:`error_body` 记网关响应正文,沿用库内既有的 `summarize_body` 上限(与 cap 无关,也不随它变化);`error` 在结构化耗尽的终态行上带一段有界说明(修复原因至多 200 字符 + 至多 3 条校验错误 × 200 字符,**不含模型原始正文**),自带独立限长。判断留存面时这两列按各自上限估算,不能算进 cap 的四处。
|
||||||
|
|
||||||
### 7. SQLite 侧的保留期
|
### 7. SQLite 侧的保留期
|
||||||
|
|
||||||
SQLite 侧**不建议**对着一个大库文件跑 `DELETE` + `VACUUM`,而应**按天/按实验轮转库文件**——`runs/<date>.db`、`runs/<experiment>.db` 这样,到期直接删文件。这是三个现有下游(Video-Tree-TRM5 / CHSAnalyzer / dissect)天然就有的形态,比删行省事也安全得多:删文件是 O(1) 且不可能删错行,而 `VACUUM` 会重写整库、期间需要一倍磁盘空间,还会把并发写入方挡在外面。
|
SQLite 侧**不建议**对着一个大库文件跑 `DELETE` + `VACUUM`,而应**按天/按实验轮转库文件**——`runs/<date>.db`、`runs/<experiment>.db` 这样,到期直接删文件。这是三个现有下游(Video-Tree-TRM5 / CHSAnalyzer / dissect)天然就有的形态,比删行省事也安全得多:删文件是 O(1) 且不可能删错行,而 `VACUUM` 会重写整库、期间需要一倍磁盘空间,还会把并发写入方挡在外面。
|
||||||
|
|||||||
+1
-1
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
|||||||
|
|
||||||
[project]
|
[project]
|
||||||
name = "polygateway"
|
name = "polygateway"
|
||||||
version = "1.3.4"
|
version = "1.3.5"
|
||||||
description = "PolyGateway:实验室统一的大语言模型(LLM/VLM/OCR)调度与中转库——多源、限流、重试、熔断、缓存、遥测"
|
description = "PolyGateway:实验室统一的大语言模型(LLM/VLM/OCR)调度与中转库——多源、限流、重试、熔断、缓存、遥测"
|
||||||
# registry 包页面的正文只认这一项:缺了页面就是一片空白(1.1.2 的教训,twine 会警告
|
# registry 包页面的正文只认这一项:缺了页面就是一片空白(1.1.2 的教训,twine 会警告
|
||||||
# long_description missing 但不阻塞上传)。README 在打包时被固化进产物,发布后再改无效。
|
# long_description missing 但不阻塞上传)。README 在打包时被固化进产物,发布后再改无效。
|
||||||
|
|||||||
@@ -562,9 +562,9 @@ flowchart TB
|
|||||||
|
|
||||||
### 7.8 遥测与成本
|
### 7.8 遥测与成本
|
||||||
|
|
||||||
**必录字段**(继承三项目 15 字段规范;当前 26 个 INSERT 字段,物理表列 27 = 26 + 数据库自填的 `created_at`,两套口径的区分见 `telemetry/schema.py` 模块 docstring): call_id、parent_call_id、session_id、model、provider、source_name、messages(JSON)、response、thinking、prompt_tokens、completion_tokens、usage_source、latency_ms、ttft_ms、max_inter_token_ms、cache_hit、error、**cost**、**cached_prompt_tokens**、**model_reported**、**sampling**、**reasoning_tokens**、**tenant_id**、**meta**、**thinking_observation**、**reasoning_effort**。
|
**必录字段**(继承三项目 15 字段规范;当前 36 个 INSERT 字段,物理表列 37 = 36 + 数据库自填的 `created_at`,两套口径的区分见 `telemetry/schema.py` 模块 docstring): call_id、parent_call_id、session_id、model、provider、source_name、messages(JSON)、response、thinking、prompt_tokens、completion_tokens、usage_source、latency_ms、ttft_ms、max_inter_token_ms、cache_hit、error、**cost**、**cached_prompt_tokens**、**model_reported**、**sampling**、**reasoning_tokens**、**tenant_id**、**meta**、**thinking_observation**、**reasoning_effort**、**scope**、**operation**、**logical_call_id**、**event_kind**、**http_status_code**、**error_type**、**cause_type**、**error_body**、**attempts**、**total_latency_ms**。
|
||||||
|
|
||||||
**`sampling` 列(2026-07-31,issue #4,端口 20 → 21)**: 列语义 = 「调用方采样意图 ⊎ 生效源 `extra_body`」的 canonical JSON,空则 NULL。**不含**结构化注入的 `response_format`——列名是采样参数,schema 不是,且数 KB schema 逐行落库会让审计表无谓膨胀。三个 emit 入口口径必须各自定死,否则同一列在不同行含义不同: `emit_attempt`(RetryMW 调用,**唯一**有生效源者)并上 `source.extra_body`;`emit_cache_hit` / `emit_terminal_failure`(TelemetryMW 最外层调用)无 source 可言,只记调用级——与 `model`/`source_name` 在终态行置空是同一先例,且缓存命中行无损(`sampling` 已进缓存 key,能命中即意味调用级参数与历史那次逐字相同)。三者统一读 `request.sampling` 而非 `request.overlay`(后者在 RetryMW 处已被结构化注入污染、在 TelemetryMW 处未被污染,直接用必然三行分叉)。OCR/embedding 路径因决策 G 剥离 `extra_body`,该列恒 NULL。
|
**`sampling` 列(2026-07-31,issue #4,端口 20 → 21)**: 列语义 = 「调用方采样意图 ⊎ 生效源 `extra_body`」的 canonical JSON,空则 NULL。**不含**结构化注入的 `response_format`——列名是采样参数,schema 不是,且数 KB schema 逐行落库会让审计表无谓膨胀。三个 emit 入口口径必须各自定死,否则同一列在不同行含义不同: `emit_attempt`(RetryMW 调用,**唯一**有生效源者)并上 `source.extra_body`;`emit_cache_hit` / `emit_terminal_failure`(前者由 TelemetryMW 最外层调用,后者自 1.3.5 起由三个 client 的公开边界经 `emit_terminal_once` 统一写出)无 source 可言,只记调用级——与 `model`/`source_name` 在终态行置空是同一先例,且缓存命中行无损(`sampling` 已进缓存 key,能命中即意味调用级参数与历史那次逐字相同)。三者统一读 `request.sampling` 而非 `request.overlay`(后者在 RetryMW 处已被结构化注入污染、在 TelemetryMW 处未被污染,直接用必然三行分叉)。OCR/embedding 路径因决策 G 剥离 `extra_body`,该列恒 NULL。
|
||||||
|
|
||||||
**`reasoning_tokens` 列(2026-08-11,issue #6,端口 21 → 22)**: 推理 token 已计入 `completion_tokens`,故成本总额一直是对的——这不是计费缺口而是**归因**缺口:缺了它,"这次调用花的钱里有多少花在推理上"无法区分,也就无从判断某个 scope 该不该关推理。供应商不报时记 NULL 而非 0(不可得 ≠ 为零,与 `usage_source='unavailable'` 同一纪律)。
|
**`reasoning_tokens` 列(2026-08-11,issue #6,端口 21 → 22)**: 推理 token 已计入 `completion_tokens`,故成本总额一直是对的——这不是计费缺口而是**归因**缺口:缺了它,"这次调用花的钱里有多少花在推理上"无法区分,也就无从判断某个 scope 该不该关推理。供应商不报时记 NULL 而非 0(不可得 ≠ 为零,与 `usage_source='unavailable'` 同一纪律)。
|
||||||
|
|
||||||
@@ -581,6 +581,20 @@ flowchart TB
|
|||||||
|
|
||||||
实际档分析须 `cache_hit=false AND error IS NULL`。embedding/OCR text/layout 的成功与失败尝试由 reasoning_applies=False 保证 NULL,真实 client→emitter→临时 SQLite 与 chat 阳性共同守卫,不能用空行集合证明。生产 emitter 单一出口、端口字段数和 DDL 不变。
|
实际档分析须 `cache_hit=false AND error IS NULL`。embedding/OCR text/layout 的成功与失败尝试由 reasoning_applies=False 保证 NULL,真实 client→emitter→临时 SQLite 与 chat 阳性共同守卫,不能用空行集合证明。生产 emitter 单一出口、端口字段数和 DDL 不变。
|
||||||
|
|
||||||
|
**逻辑调用十列(2026-09-09,issue #19/#23,端口 26 → 36)**: 本版把治理单位从"一次尝试"补齐到"一次逻辑调用"。十列按同一顺序追加在 `reasoning_effort` 之后,全部可空、无默认值、不回填旧行(NULL 表达的是"补列之前根本没记过这件事",与任何哨兵值不同;这一点与 `tenant_id` 故意相反——后者是 RLS 可见性需要哨兵,前者是归因需要区分真实缺口)。
|
||||||
|
|
||||||
|
| 列 | 语义 |
|
||||||
|
| --- | --- |
|
||||||
|
| `scope` | 池名,`TelemetryEmitter` 构造期注入(三个 client 各一行),三类行都带;**不拿 `source_name` 顶替**(终态失败可能根本没选出源) |
|
||||||
|
| `operation` | `chat` / `embed` / `recognize_text` / `parse_layout`,**由调用点给定**。它与 `PolyGatewayError.operation` 是两个语义: 后者是异常自报的出错环节(可为 `download_result` 这类子步骤),链路上任何位置不得读它来填本列 |
|
||||||
|
| `logical_call_id` | 一次逻辑调用一个 ID;上下文缺席(库内现场构造的请求)落 NULL,**不造 ID** |
|
||||||
|
| `event_kind` | 三态: `attempt` / `cache_hit` / `terminal_failure`,三类行的唯一机械判据 |
|
||||||
|
| `http_status_code` / `cause_type` / `error_body` | 只在失败的 `attempt` 行上非空(成功行不统一填 200: 那会让"有状态码"不再等价于"失败了");终态行三列恒 NULL(**C1 红线**) |
|
||||||
|
| `error_type` | 该行自身错误的类名;取消路径传字符串,故为 NULL |
|
||||||
|
| `attempts` / `total_latency_ms` | 只属终态行(同一份冻结快照,与该行 `latency_ms` 同值),其余两类行 NULL |
|
||||||
|
|
||||||
|
两条不变量: **I3** —— 每次领域失败至多一条终态行(`_CallContext.claim_terminal()` 去重;recorder 写失败仍只 warning,故 SQL 可见 ≤ 1);**I4** —— 非领域异常(编程错)**零条**终态行、原样传播、分类不被改写。终态行仍 `cost=NULL`、`usage_source='unavailable'`、token 0,费用聚合口径不变。诊断值的提取收敛在 Emitter 内一个纯 helper(`_error_fields`),只读领域异常的既有属性,**不遍历任意对象、不解析字符串猜诊断**。另立**装配期形状闸**: 旧签名 recorder 在构造 `TelemetryEmitter` 时当场 `ValueError`——降级方向的铁律管的是**运行期写失败**,装配错误放行的后果是下游 100% 丢遥测且调用照常成功。
|
||||||
|
|
||||||
**`thinking_observation` 列(2026-08-25,issue #16/#17,端口 24 → 25)**: 落 `LLMResponse.thinking_observation` 的裸取值(`observed` / `absent` / `unknown`,两端均为可空 `TEXT`),语义见 §5.1。它补的是 `reasoning_tokens` 补不上的那一格: 后者为 NULL 时「没推理」与「没上报」不可区分,而供应商停报 `completion_tokens_details` 是会真实发生的事(MiniMax 这一路 2026-08-25 实测已停报,qwen 与 deepseek 在同一网关同一 key 上照常返回),届时按 `reasoning_tokens IS NULL OR = 0` 统计「未推理」会把推理了的调用一并算进去。有了本列,口径改为按本列取值分组,`unknown` 独立成一档而不再被并进「未推理」。
|
**`thinking_observation` 列(2026-08-25,issue #16/#17,端口 24 → 25)**: 落 `LLMResponse.thinking_observation` 的裸取值(`observed` / `absent` / `unknown`,两端均为可空 `TEXT`),语义见 §5.1。它补的是 `reasoning_tokens` 补不上的那一格: 后者为 NULL 时「没推理」与「没上报」不可区分,而供应商停报 `completion_tokens_details` 是会真实发生的事(MiniMax 这一路 2026-08-25 实测已停报,qwen 与 deepseek 在同一网关同一 key 上照常返回),届时按 `reasoning_tokens IS NULL OR = 0` 统计「未推理」会把推理了的调用一并算进去。有了本列,口径改为按本列取值分组,`unknown` 独立成一档而不再被并进「未推理」。
|
||||||
|
|
||||||
**recorder 收到的必须是裸 `str` 而非枚举实例**: `TelemetryEmitter` 的 `_AttemptUsage` 内部持 `ThinkingObservation` 类型,`_record` 下沉时取 `.value`。`StrEnum` 虽是 `str` 子类,asyncpg 的参数编码对 `str` 子类不保证接受,而遥测写失败只降级为一条 warning——这类问题不会当场炸,只会让 Postgres 那一路悄悄少一列数据。归一化放在 emitter 侧,与 `tenant_id`/`meta`/`sampling` 由 emitter 定型后再交 recorder 是同一分工(recorder 只落库,不做语义判断)。列序纪律同上: 新列排在最末,两端 DDL 与两份 backfill 同步。
|
**recorder 收到的必须是裸 `str` 而非枚举实例**: `TelemetryEmitter` 的 `_AttemptUsage` 内部持 `ThinkingObservation` 类型,`_record` 下沉时取 `.value`。`StrEnum` 虽是 `str` 子类,asyncpg 的参数编码对 `str` 子类不保证接受,而遥测写失败只降级为一条 warning——这类问题不会当场炸,只会让 Postgres 那一路悄悄少一列数据。归一化放在 emitter 侧,与 `tenant_id`/`meta`/`sampling` 由 emitter 定型后再交 recorder 是同一分工(recorder 只落库,不做语义判断)。列序纪律同上: 新列排在最末,两端 DDL 与两份 backfill 同步。
|
||||||
@@ -589,7 +603,7 @@ flowchart TB
|
|||||||
|
|
||||||
**schema 单一事实源、档位与冲突目标(2026-08-19,issue #13,决策见 D15)**: 列序、两端 DDL、两端补列语句、`INSERT` 构造与缺列告警收敛进 `telemetry/schema.py`——此前在两个 recorder 各存一份,而公共函数 `telemetry_schema_sql` 打印给下游的 SQL 必须与库真正执行的 DDL **同源**,三份必然漂移,漂移的表现是"下游照打印的 SQL 建完表,库仍报缺列"。补列自此由 `PGW_TELEMETRY_SCHEMA_MODE` 控制(三态: 不设按后端派生 sqlite→auto / postgres→manual,显式设置两侧均可覆盖): manual 档一条 DDL 都不发,改为按探测到的现有列**裁剪 `INSERT`**(裁剪是关掉 ALTER 的前提,否则缺列旧表每行写入都被拒 = 遥测全失)并发**一条**点名缺列、附可执行 SQL 的 warning;auto 档行为不变,且补列失败时**不裁剪**(该档承诺"把列补上",补不上就让缺列以逐行 warning 暴露)。**库内执行的补列语句与打印给人的那份是两套文本**: 库内不用 `ADD COLUMN IF NOT EXISTS`(它即便列已存在也先取 ACCESS EXCLUSIVE 锁,故库侧一律先探测后 ALTER),打印的那份带,以保证下游可重复执行。同批把 PG 写入的 `ON CONFLICT (call_id) DO NOTHING` 改为**无冲突目标**的 `ON CONFLICT DO NOTHING`: 带目标的语句要求恰好匹配 `(call_id)` 的唯一约束,而 PG 要求分区表的唯一约束必须包含分区键——按 `created_at` 分区(issue #12)后主键变成 `(call_id, created_at)`,该语句被 PG 直接拒收,而写失败只逐行 warning,表现为分区部署下遥测全线静默丢数据;无目标版本在两种表形态上都合法,普通表上语义逐字等价(表上只有主键这一个唯一约束),SQLite 的 `INSERT OR IGNORE` 本就无目标。
|
**schema 单一事实源、档位与冲突目标(2026-08-19,issue #13,决策见 D15)**: 列序、两端 DDL、两端补列语句、`INSERT` 构造与缺列告警收敛进 `telemetry/schema.py`——此前在两个 recorder 各存一份,而公共函数 `telemetry_schema_sql` 打印给下游的 SQL 必须与库真正执行的 DDL **同源**,三份必然漂移,漂移的表现是"下游照打印的 SQL 建完表,库仍报缺列"。补列自此由 `PGW_TELEMETRY_SCHEMA_MODE` 控制(三态: 不设按后端派生 sqlite→auto / postgres→manual,显式设置两侧均可覆盖): manual 档一条 DDL 都不发,改为按探测到的现有列**裁剪 `INSERT`**(裁剪是关掉 ALTER 的前提,否则缺列旧表每行写入都被拒 = 遥测全失)并发**一条**点名缺列、附可执行 SQL 的 warning;auto 档行为不变,且补列失败时**不裁剪**(该档承诺"把列补上",补不上就让缺列以逐行 warning 暴露)。**库内执行的补列语句与打印给人的那份是两套文本**: 库内不用 `ADD COLUMN IF NOT EXISTS`(它即便列已存在也先取 ACCESS EXCLUSIVE 锁,故库侧一律先探测后 ALTER),打印的那份带,以保证下游可重复执行。同批把 PG 写入的 `ON CONFLICT (call_id) DO NOTHING` 改为**无冲突目标**的 `ON CONFLICT DO NOTHING`: 带目标的语句要求恰好匹配 `(call_id)` 的唯一约束,而 PG 要求分区表的唯一约束必须包含分区键——按 `created_at` 分区(issue #12)后主键变成 `(call_id, created_at)`,该语句被 PG 直接拒收,而写失败只逐行 warning,表现为分区部署下遥测全线静默丢数据;无目标版本在两种表形态上都合法,普通表上语义逐字等价(表上只有主键这一个唯一约束),SQLite 的 `INSERT OR IGNORE` 本就无目标。
|
||||||
|
|
||||||
**正文截断(2026-08-19,issue #12)**: `PGW_TELEMETRY_TEXT_CAP` 给落库正文一个可配置的字符上限,**缺省不设 = 不截断**(人类决策 E-a): 截断后的遥测不再是审计证据,也无法拿原样的请求复现与重放,而这正是既有下游在依赖的行为,默认改动即破坏;代价是 issue 那句"无限期保留全部租户全文不应是默认状态"只被解决一半——默认仍是全文,但下游第一次有了不写全文的手段。截断落在 `TelemetryEmitter._record`(全库唯一遥测出口,单一 helper 铁律)内,位于 `digest_messages` 之后、`json.dumps` 之前,作用面四处: 每条消息的字符串 `content`、多模态 part 中 `type == "text"` 的 `text`、`response`、`thinking`;超出部分头部硬切并附 `…(略 N 字)`。**按每条文本切而不是切整串 JSON**——后者会往不做任何校验的 TEXT 列里写进非法 JSON,让此后一切按 JSON 解析该列的分析全废。**且只产出新对象、绝不就地修改**: `digest_messages` 对非 list 的 `content` 原样透传同一个 dict 对象,就地截断会同时污染调用方持有的 messages、后续重试的请求体与缓存写入的 key 且全程无报错——红线由"cap 开与关两态下 `build_cache_key` 输出逐字节相同"的测试钉死。覆盖面须诚实声明: 只碰 `content`(与 `digest_messages` 处理面一致),调用方放进 `tool_calls.function.arguments` 等字段的内容不在其中。embedding 与 OCR 两条链路各自既有的 200 字符上限保留不动,与新 cap 是取更严者的关系。
|
**正文截断(2026-08-19,issue #12)**: `PGW_TELEMETRY_TEXT_CAP` 给落库正文一个可配置的字符上限,**缺省不设 = 不截断**(人类决策 E-a): 截断后的遥测不再是审计证据,也无法拿原样的请求复现与重放,而这正是既有下游在依赖的行为,默认改动即破坏;代价是 issue 那句"无限期保留全部租户全文不应是默认状态"只被解决一半——默认仍是全文,但下游第一次有了不写全文的手段。截断落在 `TelemetryEmitter._record`(全库唯一遥测出口,单一 helper 铁律)内,位于 `digest_messages` 之后、`json.dumps` 之前,作用面四处: 每条消息的字符串 `content`、多模态 part 中 `type == "text"` 的 `text`、`response`、`thinking`;超出部分头部硬切并附 `…(略 N 字)`。**按每条文本切而不是切整串 JSON**——后者会往不做任何校验的 TEXT 列里写进非法 JSON,让此后一切按 JSON 解析该列的分析全废。**且只产出新对象、绝不就地修改**: `digest_messages` 对非 list 的 `content` 原样透传同一个 dict 对象,就地截断会同时污染调用方持有的 messages、后续重试的请求体与缓存写入的 key 且全程无报错——红线由"cap 开与关两态下 `build_cache_key` 输出逐字节相同"的测试钉死。覆盖面须诚实声明: 只碰 `content`(与 `digest_messages` 处理面一致),调用方放进 `tool_calls.function.arguments` 等字段的内容不在其中。embedding 与 OCR 两条链路各自既有的 200 字符上限保留不动,与新 cap 是取更严者的关系。**1.3.5 新增的两处诊断文本同样不在 cap 覆盖内**: `error_body` 沿用 `summarize_body` 的既有上限,结构化耗尽终态行的 `error` 说明自带有界限长(`repair=` 至多 200 字符 + `validation=` 至多 3 条 × 200 字符,**不含 `raw_text`**——模型正文的预算已由 attempt 行的 `response` 列承担)。两段限长常量与 `StructuredMW` 重问反馈共用同一份(`format_bounded_errors`),数值只有一份定义。
|
||||||
|
|
||||||
- 后端: `SQLiteRecorder`(默认;WAL + busy_timeout、`INSERT OR IGNORE` 幂等、`asyncio.to_thread` 桥接、初始化/写入失败全降级不冒泡)与 `PostgresRecorder`。
|
- 后端: `SQLiteRecorder`(默认;WAL + busy_timeout、`INSERT OR IGNORE` 幂等、`asyncio.to_thread` 桥接、初始化/写入失败全降级不冒泡)与 `PostgresRecorder`。
|
||||||
- **单一 helper 铁律**: 遥测调用点收敛为一个内部函数/上下文管理器;Video-Tree 与 GovDoc 各有 4-5 处逐字复制的 `record_llm_call(15 个参数)` 是本条的直接教训。
|
- **单一 helper 铁律**: 遥测调用点收敛为一个内部函数/上下文管理器;Video-Tree 与 GovDoc 各有 4-5 处逐字复制的 `record_llm_call(15 个参数)` 是本条的直接教训。
|
||||||
|
|||||||
@@ -0,0 +1,202 @@
|
|||||||
|
# 1.3.5:逻辑调用统计与结构化失败诊断
|
||||||
|
|
||||||
|
> 状态:独立审查及定向复审通过,**人类已于 2026-09-09 正式批准**(§10 六项批准项全数获批,可据此实施公共 API)。实施计划见 `research-wiki/plans/2026-09-09-135-call-observability.md`。
|
||||||
|
> 日期:2026-09-09。范围:issue #19、#23。基线源码 HEAD e71a623。
|
||||||
|
> 复用现有 Emitter / schema / 三条治理循环,不引入追踪平台、不做 deadline / hedging、不在库内复制上下游关联状态。
|
||||||
|
|
||||||
|
## 1. 问题与边界
|
||||||
|
|
||||||
|
治理单位是一次逻辑调用,但当前 `latency_ms` / `call_id` 只描述**单次尝试**:重试几次、等了多久、缓存有没有参与,SQL 答不出来。诊断侧,transport 抛出的领域错误已带 `status_code` / `operation` / `body_text`(errors.py:52),进 emitter 前却被 `str()` 压平成一列自由文本。终态失败可能没有选中源,但 **scope 始终已知**。
|
||||||
|
|
||||||
|
中转把供应商 529 改写成 503 后,库只能如实记 503,不能猜回 529;未知成本、未知状态一律 NULL。本版不改重试预算、429 语义、stall、推理能力表与取消结算算法,不新增核心依赖。
|
||||||
|
|
||||||
|
## 2. 方案
|
||||||
|
|
||||||
|
| 方案 | 收益 | 代价 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| A:只在 RetryMW 加两个计数、错误列细分 | 补丁最小 | 漏缓存命中、结构化重问、embedding 分批与三类失败终态,回答不了"整次调用" |
|
||||||
|
| B:每调用局部统计 + 领域异常下沉到单一出口,复用现有遥测行 | 统一边界、字段保真、不默认加成功行、不双计费用 | 增加内部上下文、响应字段与 recorder 字段;须补齐缺失的失败终态行 |
|
||||||
|
| C:新增独立逻辑调用表 / 通用事件端口 | 完整追踪与任意事件分析 | 新存储与运维面,超出当前需求 |
|
||||||
|
|
||||||
|
推荐 **B**。显式传递局部对象,不用 client 共享可变计数、不用模块级 ContextVar;不统一三条治理循环,只统一计数与诊断出口。
|
||||||
|
|
||||||
|
## 3. 逻辑边界与公开统计
|
||||||
|
|
||||||
|
四种响应(`LLMResponse`、`EmbeddingResponse`、`OcrTextResult`、`OcrLayoutResult`)追加 `call_stats: CallStats | None = None`。新增 frozen `CallStats` 并由包根导出——四份平铺字段会立刻漂移。
|
||||||
|
|
||||||
|
| CallStats 字段 | 语义 |
|
||||||
|
| --- | --- |
|
||||||
|
| `logical_call_id: str` | 每次公开调用一个 UUID;重试、重问、分批共享;不占用既有 `parent_call_id` |
|
||||||
|
| `attempts: int` | 准入后实际调用 transport 端口的次数;含免预算 429 与端口本地拒绝;**不是 HTTP 请求条数** |
|
||||||
|
| `total_latency_ms: int` | 从输入校验通过到返回/异常传播前的单调时钟快照;含缓存、等待、重问、分批、内联记账与资源收尾 |
|
||||||
|
|
||||||
|
输入校验异常发生在统计边界之外,保持原行为。第三方合成响应的 `None` 表示未知,不得默认伪造 0。
|
||||||
|
|
||||||
|
- **缓存命中**:`attempts=0`、新 logical ID、本次缓存路径耗时;不回放历史统计。缓存持久化排除 `call_stats`(`_serialize` 显式剔除),`_rehydrate` 显式覆盖为 `None`——`_RESPONSE_FIELDS` 过滤会放行历史 dict,不覆盖就会有 dict 冒充 `CallStats`。缓存 key 白名单不变。
|
||||||
|
- **embed 空输入**(embedding.py:180-190):合法零尝试,返回真实统计(`attempts=0`),**不写任何遥测行**——与 cache_hit 不同,不要按"必录"推断它有台账行。
|
||||||
|
- **OCR layout** 的 POST + ZIP GET 在同一 transport 调用内(monkey_ocr.py:262-296),计 1 次尝试。
|
||||||
|
- **chat 重问 / embedding 多批**计入同一上下文,不重置计数(重问经 `call_next` 重入 RetryMW,已核对)。
|
||||||
|
|
||||||
|
`latency_ms` / `call_id` / `parent_call_id` 语义不变;"总耗时减最后一次尝试耗时"不等于纯等待(含其他本地工作)。不在响应里挂每次尝试的明细列表,避免公共响应无界增长。
|
||||||
|
|
||||||
|
### 3.1 失败与取消
|
||||||
|
|
||||||
|
本版**不向异常对象附加可变 `call_stats`**:第三方可能复用同一异常实例,first-write-wins 会把首次调用的统计误读成本次,覆盖写则串扰;复制任意异常又保证不了构造签名与自定义属性。异常类型与分类原样保留,失败侧的统计走 §6 的终态行。
|
||||||
|
|
||||||
|
- 取消:`CancelledError` 保持原类型与语义,不在其上加字段;取消路径只**尽力**写一条终态,不 shield、不开新后台任务。
|
||||||
|
- 任意内部非领域异常(编程错)原样传播,本版**不承诺**为其提供任何统计或终态行,也不偷偷改分类。
|
||||||
|
|
||||||
|
## 4. 最小内部接缝
|
||||||
|
|
||||||
|
`CallStats` 与私有可变 `_CallContext` 都落 `types.py`:`types.py` 不反向依赖实现层,不产生循环,也不动 import-linter 分层(`ports : types : errors` 并列最内层)。私有上下文只持计数、单调时钟与必要去重状态,不做 I/O。
|
||||||
|
|
||||||
|
`ChatRequest` 追加内部上下文字段(`default=None, compare=False, repr=False`);`StructuredMW` 的 `dataclasses.replace` 保留同一引用(structured.py:96-110,已核对)。响应统计只在公共出口经 `replace` 附加。`GatewayClient` 需自存注入的 `now`(client.py 现未保存),**冻结快照是同步动作,不 await**。
|
||||||
|
|
||||||
|
- 上下文创建/冻结:`GatewayClient` 在公开入口创建、`finally` 冻结;`RetryMW` 只在 transport 调用前登记一次尝试。
|
||||||
|
- **OCR 例外(M1)**:`image` 的类型/空校验在 `_call` 内(ocr.py:238-241)而非公开方法,故上下文在该校验**通过之后**创建,§3 的"校验在边界外"对 OCR 才成立。
|
||||||
|
- `EmbeddingClient` / `OcrClient` 显式把同一上下文传到每批/每次尝试;统计生效与否**不由 telemetry 是否启用决定**。
|
||||||
|
- 每次尝试 ID 仍在当前循环产生,与上下文的 logical ID 一起交给 Emitter。不持久化断点,不引入任务恢复。
|
||||||
|
|
||||||
|
## 5. 诊断字段与归因方式
|
||||||
|
|
||||||
|
保留现有 `error` 字符串供人阅读;Emitter 改为接受**领域异常对象**而非调用方先 `str()`,由单一 helper 提取有限诊断字段。普通超时/网络翻译在 transport 侧保留直接 `__cause__` 类型,空 `str()` 退回类名;**不遍历任意异常对象、不猜测正文**。
|
||||||
|
|
||||||
|
| 新增 INSERT 列 | 值域 / 来源 |
|
||||||
|
| --- | --- |
|
||||||
|
| `scope` | 配置池名,构造期注入 Emitter(见下);不拿 `source_name` 顶替 |
|
||||||
|
| `operation` | **公开方法固定四值**:`chat` / `embed` / `recognize_text` / `parse_layout`;由三个 client 在调用点给定 |
|
||||||
|
| `logical_call_id` | 当前调用上下文的 UUID;上下文缺席(库内现场构造的 `ChatRequest`)→ **NULL,不造 ID** |
|
||||||
|
| `event_kind` | `attempt` / `cache_hit` / `terminal_failure`;旧行 NULL,不回填 |
|
||||||
|
| `http_status_code` | **仅 attempt 行**:失败异常实收状态;无 HTTP 或未知 NULL;成功行不统一填 200 |
|
||||||
|
| `error_type` | 该行自身错误的领域类名;成功行 NULL |
|
||||||
|
| `cause_type` | **仅 attempt 行**:transport 直接捕获的底层异常类名,未知 NULL |
|
||||||
|
| `error_body` | **仅 attempt 行**:既有 `summarize_body` 有界摘要,未知 NULL;不存 `raw_text`、不存全量原文 |
|
||||||
|
| `attempts` / `total_latency_ms` | **仅 terminal_failure 行**填逻辑快照,其余行 NULL;快照在写入前冻结 |
|
||||||
|
|
||||||
|
全部可空,追加到物理列末尾(与旧表 ALTER 追加位置一致,`schema.py` 的 DDL / BACKFILL / COLUMNS 三处同改)。
|
||||||
|
|
||||||
|
**归因方式(C1,决定性)**:`GatewayUnavailableError` 家族从不携带 `status_code` / `body_text`(errors.py:118-166),终态行的 `http_status_code` / `cause_type` / `error_body` 因此**保持 NULL,这是它自身的真实状态**——不把最后一次 attempt 的状态码与正文搬上来伪装成整池诊断(那正是"不拿最后一个源冒充整池归因"的同一条红线)。终态行的 `error_type` 落它自己的类名(`AllSourcesExhausted` / `CircuitOpenError` / …),scope 级 reason 沿用**已有 error 文案**(`str(exc)` 已是 `"{scope} 网关暂时不可用: {reason}"`,不新增列)。逐源现场由同一 `logical_call_id` 的 attempt 行给出。
|
||||||
|
|
||||||
|
```sql
|
||||||
|
-- #19 验收:一次逻辑失败调用的完整现场(终态 + 各次尝试)
|
||||||
|
SELECT event_kind, source_name, http_status_code, error_type, cause_type, error_body, error
|
||||||
|
FROM llm_calls WHERE logical_call_id = :lcid ORDER BY created_at;
|
||||||
|
```
|
||||||
|
|
||||||
|
该查询必须同时给出"整池为何失败"(终态行 error 文案)与"每个源怎么死的"(attempt 行状态码/正文),测试按它断言。因此**本版不再为 `reason` / `per_source_reasons` 扩列**。
|
||||||
|
|
||||||
|
**结构化耗尽的可定位性(C2)**:`ResultInvalidError("结构化输出阶梯耗尽")` 的 message 不含 `validation_errors` / `repair_error`(structured.py:80-86),而该失败发生在 StructuredMW 之上——RetryMW 侧的 attempt 行全是成功行,终态行是唯一记录。做法:**不写 `error_body`**(该列只属 attempt),由 Emitter 的单一 helper 对 `ResultInvalidError` 生成**有界结构化说明**并入现有 `error` 字符串,复用 structured.py 已有的取材口径(至多 3 条、每条 200 字符,与 `_format_errors` 同参数,拼装函数收敛在 helper 一处)。`raw_text` **不重复落库**(它是模型正文,attempt 行的 `response` 列已按 `text_cap` 记过一份;再存一份等于绕过既有正文预算)。该说明可能包含模型输出片段,故遵循与 `error` 现有正文相同的隐私边界,不额外扩大保留范围。
|
||||||
|
|
||||||
|
**operation 的数据源(I1/I2)**:openai_compat.py:169 的 `_status_to_error` 硬编码 `operation="chat"`,而 `embed()` 的非 200 分支(:512)也走它 → 现存所有 embedding HTTP 失败的 `exc.operation` 都是错的。(行号勘误 2026-09-09:本句原写 "(:512、:527)",实测 `:527` 属 `_complete_stream`即流式 chat,`embed` 只有 `:512` 一处;归属以实施计划 §2 表为准,决策未变。)修正:`_status_to_error` 增 keyword `operation`,`embed` 传 **`"embedding"`**(沿用该异常侧既有词表,不改 `chat` / `ocr_text` / `parse` / `download_result` 四值)。新列 `operation` 与 `exc.operation` 是**两个语义**:前者是公开方法,后者是 HTTP 子操作;新列由调用点给定,**绝不读 `exc.operation`**,两者不做自动转换。OCR 两个公开方法各自在调用级给定自己的值。
|
||||||
|
|
||||||
|
**scope 注入(M6)**:`TelemetryEmitter` 现在不知道 scope,`CacheMW` / `TelemetryMW` 自己也拿不到。构造期注入(三个 client 各一行),使 attempt / cache_hit / terminal_failure 三类行都带 scope,避免改三条调用链。model / provider / source 未选出时仍留原空值。
|
||||||
|
|
||||||
|
**成功侧不加承诺**:成功行不承诺 HTTP 状态与错误体;**本版不宣称 SQL 可直接统计所有成功逻辑调用的总耗时**(成功不加终态行)。`error_body` 沿用 `summarize_body` 的既有上限,**不纳入 `PGW_TELEMETRY_TEXT_CAP` 覆盖面**(该键现覆盖四处,详见 §8)。
|
||||||
|
|
||||||
|
## 6. 行语义与终态:只补确实缺失的失败
|
||||||
|
|
||||||
|
保留每次 attempt 与 cache_hit 的既有行,**不为成功新增终态行**。终态行不得复制已有 attempt 的 token 与成本。所有统计边界内的领域失败均尝试写终态,**包括已有 attempt 错误行的直接 RequestRejectedError/ResultInvalidError**;不再沿用“该类错误已录所以外层不录”的旧假设,400 密集负载的错误行可能翻倍,调用失败计数必须只取 terminal_failure。
|
||||||
|
|
||||||
|
**不变量(I3,统一措辞)**:
|
||||||
|
|
||||||
|
| 结束形态 | 终态行数 |
|
||||||
|
| --- | --- |
|
||||||
|
| 以**领域错误**结束的逻辑调用 | 每次调用**尝试写一条**;持久化 best effort(recorder 写失败按既有降级只落 warning),故 SQL 可见行数 ≤ 1 |
|
||||||
|
| 取消 | 三个 client **同策略尽力写一条**,允许 0 条 |
|
||||||
|
| 非领域异常(编程错) | **0 条**,原样传播,本版无统计保证 |
|
||||||
|
|
||||||
|
需要补的路径:chat 结构化耗尽(发生在 transport 成功之后,现无任何失败行)、embedding / OCR 的无源、准入拒绝、重试耗尽与尝试外取消。**取消口径统一(I4)**:chat 现由 TelemetryMW 对任何取消补终态(telemetry.py:487-495,含尝试内取消),embedding / OCR 按同一口径尽力补,避免下游按 `event_kind` 统计取消时拿到路径相关的结果。
|
||||||
|
|
||||||
|
终态与 attempt **不是重复事实**(前者描述逻辑终态,后者描述尝试),用 `event_kind` 区分;**禁止按 `error IS NOT NULL` 跨两类直接计失败调用次数**。chat 现有 TelemetryMW 终态路径收敛到公开边界的单一 helper,避免两处同时写;embedding / OCR 复用该 helper。
|
||||||
|
|
||||||
|
**终态行的请求摘要(M4)**:复用既有 200 字符输入摘要口径,描述**本次调用的整体输入**,但不扩大单行正文预算——embedding 终态取 `<embed texts=N batches=M>` 计数占位 + 第一批(至多 `batch_size` 条、每条 200 字符,与逐批行同款构造);OCR 终态沿用 `<ocr:{kind} image_bytes=…>` 占位,图像 bytes 永不入库。**失败批的具体文本由同 `logical_call_id` 的 attempt 行给出**,终态行不保存全量原输入。
|
||||||
|
|
||||||
|
**错误文本口径(I7)**:OCR 现落 `"类名: msg"`(ocr.py:445-449,按类名归组的既有 metric 口径),chat / embed 落裸 `str(exc)`。改成"Emitter 收异常对象"后,该差异由统一出口的**显式文本策略参数**保留(OCR 保留类名前缀),**不再在三处复制参数列表**。
|
||||||
|
|
||||||
|
**取消时的终态写(残余风险,显式定策)**:该 `await` 本身是新的取消点。策略是**取消优先、不屏蔽**:外部取消落在这一 await 上时,`CancelledError` 照常传播(调用方可能因此看到 `CancelledError` 而非领域错误,与 TelemetryMW 现有行为同款);不 shield、不建新后台任务。冻结统计快照是同步动作,不 await。
|
||||||
|
|
||||||
|
终态行成本 NULL、usage `unavailable`;聚合费用仍只由 attempt / cache_hit 行决定。终态快照在写入前冻结,故不含自身写入耗时;成功响应快照包含其返回前已完成的内联遥测耗时。失败异常不附快照,不为对齐再 UPDATE 旧行。
|
||||||
|
|
||||||
|
取消 attempt 既有字符串 `"cancelled"` 保留:Emitter接收 `PolyGatewayError | str | None`,字符串不解析猜测诊断,error_type/cause_type/http_status_code/error_body均NULL;终态取消同样使用明确取消文案。终态既有latency_ms与新增total_latency_ms取同一冻结快照,避免双时钟微差。
|
||||||
|
|
||||||
|
## 7. recorder 兼容:装配期机械闸(C3)
|
||||||
|
|
||||||
|
`TelemetryEmitter._record` 的 `except Exception` 会把旧 recorder 的 `TypeError` 吞成 warning(telemetry.py:463),后果是自定义 recorder 在下游升级后**100% 丢遥测且调用照常成功**——正是"遥测必录"要防的形态。文档级迁移清单挡不住它。
|
||||||
|
|
||||||
|
机械闸:在 `TelemetryEmitter.__init__`(三个 client 的唯一汇流点,与 `text_cap` 值域校验同处)对 `recorder.record_llm_call` 做**一次** `inspect.signature(...).bind(**<完整新 kwargs 形状>)`,**不执行写入**;含 `**kwargs`(`VAR_KEYWORD`)者自动通过。校验失败 → 装配期抛错。若目标不可 inspect(C 实现等),同样按**配置错误**当场报错,不进入"运行期静默丢行"。
|
||||||
|
|
||||||
|
边界诚实声明:签名 bind 只证明该形状能被接受,**不能证明函数体真的落这些列**;这是一道装配闸,不是行为验证。它既不是被否掉的 `runtime_checkable` 判定,也不是捕 `TypeError` 重试写入。是否扩主 `TelemetryRecorder` Protocol(备选:独立扩展端口保留旧实现)是 §10 的人类批准项;本草案不同时实现两套接口,自带两个 recorder 的 `**fields` 签名可接受新增参数,但其 schema、INSERT 字段与契约测试仍须同步,不能称后端完全不受影响。
|
||||||
|
|
||||||
|
校验所用参数名从 `TelemetryRecorder.record_llm_call` 的协议签名派生,不手抄第四份字段清单;只用哨兵值做bind形状校验,不读取真实请求数据。结构化说明的限条数/限长复用现有常量,若需命名常量则在既有规则所有者中定义并由两个消费者引用,不复制数值。
|
||||||
|
|
||||||
|
## 8. 下游可见变更与文档同步
|
||||||
|
|
||||||
|
**SQL 迁移清单(I6,批准项须按此逐条看)**:
|
||||||
|
|
||||||
|
| 影响面 | 变化 | 下游动作 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| 失败行数 | 新增 `terminal_failure` 行(每失败调用至多 1) | 计失败调用改 `WHERE event_kind = 'terminal_failure'` |
|
||||||
|
| `error IS NOT NULL` | 同时命中 attempt 与 terminal 两类 | 不再作为"失败调用数"的判据 |
|
||||||
|
| `AVG(latency_ms)` | terminal 行携带**逻辑总耗时**,量级大于单次尝试 | 时延看板一律按 `event_kind` 分组或过滤 |
|
||||||
|
| 费用聚合 | terminal 行 `cost` 恒 NULL、usage `unavailable` | 费用仍只由 attempt / cache_hit 行决定,口径不变 |
|
||||||
|
| 成功侧 | **不加**任何成功汇总行 | 成功逻辑调用总耗时仍从响应 `call_stats` 读,不从 SQL 读 |
|
||||||
|
| `http_status_code` | 失败行上可能是 200(monkey_ocr.py:265-270 的 `success != true` 带 200 上抛) | 该列不可作失败判据 |
|
||||||
|
|
||||||
|
**文档同步(M5,发布前必须同批)**:README:23 的"必录 26 字段"、README:399 与 ARCHITECTURE.md:592 的 `PGW_TELEMETRY_TEXT_CAP` 覆盖面四处枚举(须明确:`error_body` 沿用 `summarize_body` 上限,`error` 保留既有文本口径并仅对新增结构化说明限长;二者**不在 cap 覆盖内**)、ARCHITECTURE.md:565 的必录字段清单与 §7.8 补列一节、`.env.example` 相关注释、CHANGELOG 与 wiki(docs-convention §2)。**字段数与物理列数一律以 `inspect.signature` / `len(COLUMNS)` 实测改写,不凭记忆**(现状:26 个 INSERT 字段 + `created_at` = 27 物理列;本版新增 10 列)。
|
||||||
|
|
||||||
|
## 9. 非功能与测试矩阵
|
||||||
|
|
||||||
|
| 维度 | 要求 |
|
||||||
|
| --- | --- |
|
||||||
|
| 并发 | 每调用独立对象;同一 client 并发不串 logical ID / 计数 / 统计;无全局状态 |
|
||||||
|
| 取消 | 各等待点穿透;`finally` 释放既有资源;终态写取消优先;不新增 shield 与后台任务 |
|
||||||
|
| 降级 | recorder 写失败不改统计与主结果;准入后端仍 fail-closed;收尾失败仍原 warning |
|
||||||
|
| 持久化 | schema 单一事实源;SQLite auto / PG manual 裁剪 INSERT 保持;不 ALTER 默认生产 PG、不改旧列、不回填旧行 |
|
||||||
|
| 幂等 | attempt ID 唯一,终态独立 ID,不重复写同一终态;缓存命中不复制历史统计;不 UPDATE 计费 |
|
||||||
|
|
||||||
|
验收优先离线:真实 client + 内存后端 + FakeClock + MockTransport + 临时 SQLite,复用 1.3.4 设施;不重跑未变的模型能力矩阵。
|
||||||
|
|
||||||
|
| 测试族 | 必须证明 |
|
||||||
|
| --- | --- |
|
||||||
|
| logical 计数 | 一次成功、失败重试、免预算 429、多源拒绝、缓存命中、结构化重问、embedding 多批、OCR 双 HTTP、空输入(0 尝试且 0 遥测行) |
|
||||||
|
| 计时 | 缓存 IO、退避、准入等待、重问、收尾均计入;关闭 recorder 仍正确;毫秒/秒不混用 |
|
||||||
|
| 失败与取消 | 领域失败恰一次尝试写终态;取消三条路径同策略(允许 0 行);**终态写 await 上被取消 → `CancelledError` 传播**;permit / 探针释放不变;非领域异常 0 行且原样传播 |
|
||||||
|
| 保真诊断 | 503 包装不改回 529;直接 529 记 529;空 Connect/Read/Write/PoolTimeout 文案有类型;embedding HTTP 失败的 `exc.operation` 为 `embedding`;新列 `operation` 恒为四值之一且不随异常变化 |
|
||||||
|
| 归因 SQL | §5 那条按 `logical_call_id` 的查询同时给出终态 reason 文案与逐源状态码/正文;终态行三列为 NULL;结构化耗尽的 `error` 含有界 validation/repair 说明且不含 `raw_text` |
|
||||||
|
| 行语义 | 三类行均带 scope;每失败调用至多一条终态;attempt 与 terminal 区分;费用不重复;`AVG(latency_ms)` 按 `event_kind` 分组的断言 |
|
||||||
|
| 装配闸 | 旧签名 recorder → 装配期报错(非 warning);`**kwargs` recorder 通过;不可 inspect → 配置错误 |
|
||||||
|
| 存储兼容 | SQLite 新旧表、PG manual 缺列裁剪 / auto 追加、旧行 NULL、新旧进程混写 |
|
||||||
|
| 变异 | 计数位置、上下文复制、缓存历史回放、提前 `str()` 压平、终态双计费用分别红→绿;PG 真实集成 + 常规全套 + 独立验证 |
|
||||||
|
|
||||||
|
## 10. 集中人类批准项
|
||||||
|
|
||||||
|
| # | 决策 | 推荐 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| 1 | 公开响应结构 | 一个 `CallStats` 对象而非四类响应各铺三字段;需确认命名与消费便利性 |
|
||||||
|
| 2 | 失败侧统计范围 | 不改/不复制异常;失败统计只落终态行,调用方仅在成功响应读 `call_stats`;需确认该取舍可接受 |
|
||||||
|
| 3 | recorder 兼容路线 | 扩主 `TelemetryRecorder` Protocol + 装配期 bind 闸;备选独立扩展端口保留旧实现;需确认是否存在必须兼容的自定义 recorder |
|
||||||
|
| 4 | 新增失败终态行 | 补漏但不加成功汇总;须批准 §8 表中**全部五项**下游可见变化(不止行数) |
|
||||||
|
| 5 | 取消时终态写取消优先 | 调用方可能看到 `CancelledError` 而非领域错误(同 TelemetryMW 现状);需确认接受 |
|
||||||
|
| 6 | `operation` 值域与异常侧修正 | 新列固定四值;`_status_to_error` 增 `operation` 参数、`embed` 传 `embedding`(修正现存误标,属下游可见的历史数据口径变化) |
|
||||||
|
|
||||||
|
## 11. 独立审查处理表
|
||||||
|
|
||||||
|
| 项 | 结论 | 落点 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| C1 终态缺诊断来源 | **不采纳"定向读 `__cause__` / `per_source_reasons` 扩列"**;终态保留自身 NULL 状态,归因由 `logical_call_id` 关联 attempt 行 + 既有 reason 文案完成,并写死 SQL 验收 | §5 |
|
||||||
|
| C2 结构化耗尽可定位 | 采纳(变形):有界说明并入现有 `error` 字符串,不写 `error_body`、不重复存 `raw_text` | §5 |
|
||||||
|
| C3 recorder 静默失败 | 采纳:装配期一次 `signature.bind` 形状校验,含 `**kwargs`,不可 inspect 即配置错误;明确不验证函数体 | §7 |
|
||||||
|
| I1 / I2 operation 污染与未归一 | 采纳:新列固定四值由调用点给定,绝不读 `exc.operation`;只修 embedding 误标,其余异常侧词表不动 | §5 |
|
||||||
|
| I3 / I4 终态不变量与取消口径 | 采纳(定稿措辞):领域失败每调用尝试写一条、持久化 best effort;取消三路同策略尽力允许 0;非领域异常 0 条 | §6 |
|
||||||
|
| I5 上下文缺席语义 | 采纳:`None` → NULL,不造 ID | §5 |
|
||||||
|
| I6 迁移影响不止行数 | 采纳:列全五项 SQL 影响并进批准项 | §8、§10 |
|
||||||
|
| I7 OCR error 文本口径 | 采纳:保留类名前缀,由统一出口的显式文本策略参数承载,不复制参数列表 | §6 |
|
||||||
|
| M1 OCR 校验与统计边界 | 采纳:上下文在 `image` 校验通过后创建 | §4 |
|
||||||
|
| M2 embed 空输入 | 采纳:0 尝试且不写任何遥测行 | §3 |
|
||||||
|
| M3 失败行可能带 200 | 采纳:写明该列不可作失败判据 | §8 |
|
||||||
|
| M4 终态请求摘要未定 | 采纳:复用 200 字符口径,终态描述整体输入,不扩预算,不存全量原输入 | §6 |
|
||||||
|
| M5 文档同步缺项 | 采纳:列全六处并要求实测改数字 | §8 |
|
||||||
|
| M6 Emitter 不知 scope | 采纳:构造期注入 | §5 |
|
||||||
|
| 残余风险(终态写成新取消点) | 采纳:显式定策"取消优先不屏蔽",并进测试族与批准项 | §6、§9、§10 |
|
||||||
|
|
||||||
|
自审:方案 B 复用既有 Emitter / schema 与三条循环,不需要 #22 / #24 的新调度。未采纳的两项(异常 first-write-wins、终态搬运最后一次 attempt 的状态与正文)理由已写在正文,不是遗漏。本文档无代码实现与测试通过声明;**§10 六项已于 2026-09-09 获人类批准**,实施边界与红绿证据要求以上述实施计划为准。
|
||||||
@@ -7,7 +7,7 @@ date: 2026-09-09
|
|||||||
|
|
||||||
# 1.3.4 推理契约验证与发布准备
|
# 1.3.4 推理契约验证与发布准备
|
||||||
|
|
||||||
> 最新状态(2026-09-09):发布准备完成;用户已正式批准将未补全模型矩阵、失败/UNKNOWN/不可达/缺轮及缺下游现行配置证据作为本版验收例外,保留原始结论而非 PASS。可移交合并与包发布;本轮未 merge/push/tag/构建/上传,合并后门与外部产物验收仍待执行。以下各节是分阶段历史,不追改当时结论;最新证据与例外见文末。原始输出在 `tests/outputs/134/`,不提交。
|
> 最新状态(2026-09-09):**1.3.4 已发布并完成外部验收,#21/#25/#26 已评论关闭**。main/tag 指向 `af57f93adce24b43fd10b6d8e1281ab8ee43c0a8`;合并后门、下载独立安装及页面结果见文末。用户批准的未补全矩阵、FAIL/UNKNOWN/不可达/缺轮及缺下游配置例外保持原结论,不冒充 PASS。以下为分阶段历史,不追改当时结论;原始输出在 `tests/outputs/134/`,不提交。
|
||||||
|
|
||||||
## 基线与修改边界
|
## 基线与修改边界
|
||||||
|
|
||||||
@@ -233,3 +233,36 @@ pi-lens 仍报非 conda 解释器缺 httpx/pytest/dotenv/pydantic 及旧 S
|
|||||||
conda 启动器既有 RequestsDependencyWarning 保留,不宣称零告警。本轮 conda 内实际导入 dotenv/httpx/redis.asyncio 成功;工具的非conda LSP旧诊断不转成代码修改或忽略规则。
|
conda 启动器既有 RequestsDependencyWarning 保留,不宣称零告警。本轮 conda 内实际导入 dotenv/httpx/redis.asyncio 成功;工具的非conda LSP旧诊断不转成代码修改或忽略规则。
|
||||||
|
|
||||||
**可移交合并与包发布,不等于已发布。** 父会话按本版例外边界完成本次文档/版本差异审查,再执行合并后静态/日常门及未豁免的发布检查;不把本次例外解释为必须补全模型矩阵,也不把豁免项勾成已跑通过。merge/push/tag/构建/twine上传/下载解包独立安装/Release及registry页面检查均尚未执行;只能在实际完成后记录。不得覆盖已有同版本不同字节。
|
**可移交合并与包发布,不等于已发布。** 父会话按本版例外边界完成本次文档/版本差异审查,再执行合并后静态/日常门及未豁免的发布检查;不把本次例外解释为必须补全模型矩阵,也不把豁免项勾成已跑通过。merge/push/tag/构建/twine上传/下载解包独立安装/Release及registry页面检查均尚未执行;只能在实际完成后记录。不得覆盖已有同版本不同字节。
|
||||||
|
|
||||||
|
## 1.3.4 发布完成与外部验收(2026-09-09)
|
||||||
|
|
||||||
|
父会话已审 `dae12f9` 发布准备 diff,用户授权发布及指定例外;本轮无新生产/测试改动、不派子代理。已有红绿/变异与独立报告按适用范围复用,716份历史证据 SHA-256 复核不变。以下日志均相对 `tests/outputs/134/publish-20260909/`,命令无掩盖退出码管道;长跑由 tmux `pgw134-publish` 串行执行,`PYTHONUNBUFFERED=1`,每门独立 `.exit`。
|
||||||
|
|
||||||
|
| 步骤 | 实际结果与证据 |
|
||||||
|
| --- | --- |
|
||||||
|
| 远端核验/合并 | fetch后 origin/main=`a716f12` 无新变更;精确文件名检查 registry 无1.3.4,tag无占用、Release404。`--no-ff` 合并为 `af57f93adce24b43fd10b6d8e1281ab8ee43c0a8`,与批准 `dae12f9` 树零差异;`merge.log`/`merge-summary.log` |
|
||||||
|
| 合并后 `make lint` | exit0,ruff/import-linter 1 kept、0 broken,无自动修改;`lint.log/.exit` |
|
||||||
|
| 合并后 `make test` | **1518 passed、23 skipped、108 deselected,95%覆盖率,276.42秒,exit0**;`daily.log/.exit`。skip与deselected不计通过 |
|
||||||
|
| M2 AUTO定向 slow | **2 passed、80 deselected,46.85秒,exit0**;各5轮、并发1,空wire流式开启命题通过;`m2-auto.log/.exit`。M2.5 run `d4b158162ad543e5a4745d21b29ab03e`,M2.7 run `07a388cafa9f4fcf95dc0c6876fd0751`,均 planned=completed=5、无缺轮;实际逐轮/命题报告已读取 |
|
||||||
|
| Redis时间语义 slow | contracts/integration选择 **18 passed、156 deselected,1109.45秒,exit0**;`redis-time.log/.exit`。`gates.exit=0`,未重启全型号矩阵 |
|
||||||
|
| push与tag | main推送成功;注释tag对象 `0bdb0f70e4667a2fe50a567f0809a5a421c5442a`,解引用同上述main;`push-main.log`/`push-tag.log`/`remote-refs-after.log` |
|
||||||
|
| 构建/上传 | 核实项目绝对dist路径且不是链接后清旧1.3.3产物;conda `python -m build`、`twine check dist/*`、twine上传均exit0,wheel/sdist各一份。凭据只从tea内存读取进入TWINE_PASSWORD,无token argv/日志;`build`/`twine-check`/`upload` 的 `.log/.exit` |
|
||||||
|
| 独立下载/解包 | registry下载wheel与sdist,与本地构建SHA-256逐字匹配;包内五个关键生产文件与发布提交相同,wheel METADATA版本/Markdown正文、sdist README均与已发布README相符;`download-final.log/.exit`、`download-verification.json` |
|
||||||
|
| 独立安装与行为 | `/tmp/pgw134-registry-eyges3d7/installed/polygateway/__init__.py`,仓库外 `python -I` 并显式target来源验证;M2空AUTO、M3 AUTO在error/nearest均拒绝、M3 medium、同值/新增raw冲突与raw-only保留全部通过 |
|
||||||
|
| Release/包页面 | Release POST201,正文逐字来自CHANGELOG本节。匿名实际读取包页面、单版Release及Releases列表,均HTTP200、正文含迁移/例外;包页面有目标仓库链接,认证包API的 repository.full_name=`iomgaa/PolyGateway`;`pages-final.log/.exit`、`external-verification.json`及HTML/可见文本原件 |
|
||||||
|
| issue收尾 | 仅#21/#25/#26评论后关闭,GET各自核实closed;评论明确验证范围、失败例外、缓存迁移及“不识别所有渠道故障”;`issues.log/.exit`和`issue*-after.json`。未改#19/#22/#23/#24 |
|
||||||
|
|
||||||
|
产物 SHA-256:wheel `86ad5cc025bfda127c4f0e4bbe1252d1bb8943b7678f9ff5561200bac71fe2a2`;sdist `85620f993ff9d19845088a071d251049e3dfae8d035c05652bdb62b4340a1a66`。
|
||||||
|
|
||||||
|
外部亲查地址:[包页面](https://gitea.iomgaa.online/iomgaa/-/packages/pypi/polygateway/1.3.4)、[v1.3.4 Release](https://gitea.iomgaa.online/iomgaa/PolyGateway/releases/tag/v1.3.4)、[Releases列表](https://gitea.iomgaa.online/iomgaa/PolyGateway/releases)。结果补记在独立 `docs/1.3.4-release-evidence` 分支,不改变已发布main/tag或覆盖同版本产物。
|
||||||
|
|
||||||
|
### 真实失败与恢复(原件保留,不改写成功)
|
||||||
|
|
||||||
|
| 检查失败 | 根因/处置与边界 |
|
||||||
|
| --- | --- |
|
||||||
|
| 最初索引grep误报占用 | `1.3.4` 被当正则匹配历史sha片段;改用完整字面 `polygateway-1.3.4`,并核对tag/Release均不存在。没有实际同版占用,没有覆盖 |
|
||||||
|
| 首次sdist下载exit1 | 私有索引无setuptools,pip即使 `--no-deps` 仍启构建隔离;`download.log/.exit`保留。复用已下载wheel,sdist加 `--no-build-isolation` 使用现有conda构建工具后exit0;不新增依赖、不重传包 |
|
||||||
|
| 包link POST400 | 返回 `invalid argument`,`release-create.log/.exit`保留exit1;不把400当成功/不猜根因。匿名页面已有仓库链接,认证GET包API证实本版正确关联,故无需解绑重挂;Release创建201不重复执行 |
|
||||||
|
| 首次页面验证exit1 | 三个匿名页面及Release正文均通过,但额外包API匿名GET401;`pages.log/.exit`保留。仅该API沿现有tea认证GET后200,最终所有页面/API核对exit0;不扩大为发布包匿名不可下载 |
|
||||||
|
|
||||||
|
上述操作差异已补入CLAUDE发布清单。conda启动器既有RequestsDependencyWarning仍保留。用户验收例外完全沿前节:embedding503与claude命题仍FAIL、M3非流UNKNOWN及其余未覆盖/缺下游资料未变;本轮成功不外推全矩阵或所有渠道。1.3.4发布任务到此停止,1.3.5由父会话继续。
|
||||||
|
|||||||
@@ -0,0 +1,290 @@
|
|||||||
|
---
|
||||||
|
type: finding
|
||||||
|
node_id: finding:2026-09-09-135-call-observability-validation
|
||||||
|
title: "1.3.5 T2/T3/T4 验收证据:36 列遥测、失败终态、PG 存储兼容与变异矩阵"
|
||||||
|
date: 2026-09-09
|
||||||
|
---
|
||||||
|
|
||||||
|
# 1.3.5 T2/T3 验收证据
|
||||||
|
|
||||||
|
> 范围:**仅 T2(遥测 10 列 / 诊断保真 / scope+operation / 装配闸)与 T3(终态行 / 取消 / 统一出口)**,
|
||||||
|
> 外加计划 T4 中"签名与列数机械迁移"那一片(与 schema 同批完成,避免先提交 schema 却留写入缺键)。
|
||||||
|
> **不含** T4 的 PG 集成、变异矩阵与文档同步——另任务承接,缺口见 §5。
|
||||||
|
> 设计:`designs/2026-09-09-135-call-observability-design.md`;计划:`plans/2026-09-09-135-call-observability.md`。
|
||||||
|
> 基线 HEAD `87c261b`(T1 已提交,1419 unit 全绿)。全部命令在 `PolyGateway` conda 环境执行。
|
||||||
|
|
||||||
|
## 1. 红绿证据链
|
||||||
|
|
||||||
|
TDD 纪律要求"先失败后通过",且红必须是**行为红**而非 import 红。下表每行都对应本会话的真实工具输出。
|
||||||
|
|
||||||
|
| # | 阶段 | 命令 | 结果 |
|
||||||
|
| --- | --- | --- | --- |
|
||||||
|
| 0 | 基线 | `pytest tests/unit -q` | **1419 passed**(对照底) |
|
||||||
|
| 1 | 红(T2/T3 目标行为) | `pytest tests/unit/test_telemetry.py -k "RowLevelObservability or RecorderShapeGate"` | **26 failed**,证据 `tests/outputs/135/red-01-emitter-rows.txt` |
|
||||||
|
| 2 | 实现后全量红面 | `pytest tests/unit -q` | **137 failed / 1308 passed**(机械迁移面暴露),`red-02-after-impl.txt` |
|
||||||
|
| 3 | 迁移中 | 同上 | 60 → 25 → 8 → 4 failed(`red-03`/`red-04`/`red-05`) |
|
||||||
|
| 4 | 绿 | `pytest tests/unit -q` | **1467 passed, 0 failed** |
|
||||||
|
| 5 | 静态门 | `make check`(ruff lint+format + import-linter) | **Contracts: 1 kept, 0 broken** |
|
||||||
|
|
||||||
|
第 1 步的红是行为红而非 import 红:新用例调用的是**已存在**的 `TelemetryEmitter`,
|
||||||
|
失败形态是"缺 `scope=`/`operation=`/`stats=` 关键字"与"断言的列不存在",不是模块导不进来。
|
||||||
|
|
||||||
|
补测阶段另有两次真实红(均由 conda 实跑暴露、当场修正,非噪音):
|
||||||
|
`test_client.py` 的 `NameError: ResultInvalidError / ChatRequest`(漏 import)、
|
||||||
|
`TestTerminalRowSqlSemantics` 的 `'coroutine' object has no attribute 'execute'`(async helper 漏 await)。
|
||||||
|
|
||||||
|
## 2. 核心要求逐条对应
|
||||||
|
|
||||||
|
### 2.1 36 列与 Emitter 完整一致(不留"schema 有列、写入缺键")
|
||||||
|
|
||||||
|
一次性同批改完五处列定义 + 端口签名 + Emitter 写入,故不存在中间态。
|
||||||
|
|
||||||
|
| 判据 | 证据 |
|
||||||
|
| --- | --- |
|
||||||
|
| `len(COLUMNS) == 36`、物理列 37 | `test_telemetry.py::TestSchemaModule::test_columns_and_ddl_are_frozen`;`TestSQLiteSchemaMode` 断言 23 → 37 |
|
||||||
|
| 五处列序一致(DDL/BACKFILL×2/COLUMNS) | 新建库与 ALTER 追加列序同为 `_EXPECTED_COLUMNS` |
|
||||||
|
| 端口实测 36 字段、10 新参 keyword-only 且无默认值 | `test_ports.py::TestTelemetryRecorderSignature`(`inspect.signature` 实测,不凭记忆) |
|
||||||
|
| **Emitter 实参键集合 == `schema.COLUMNS`** | `TestEmitterRecorderContract` 三入口逐个断言 `set(rows[0]) == set(COLUMNS)` |
|
||||||
|
| 1.2.1 冻结 INSERT 未被改写 | 按 `_PRE_135_COLUMNS`(26 列)重现原文;全量 36 列另按占位符个数断言 |
|
||||||
|
|
||||||
|
装配闸(C3):`_assert_recorder_shape` 在 `TelemetryEmitter.__init__` 做一次 `signature.bind`,
|
||||||
|
参数名**从协议签名派生**而非手抄第四份清单——`test_gate_derives_parameter_names_from_the_protocol`
|
||||||
|
用 monkeypatch 换掉协议后闸自动跟随,证明没有硬编码。旧签名 recorder / 无该方法 / 不可 inspect
|
||||||
|
一律装配期 `ValueError`(不是 warning:降级铁律管的是运行期写失败,不是配置错误)。
|
||||||
|
|
||||||
|
### 2.2 三个 client 的**真实链路**失败终态
|
||||||
|
|
||||||
|
不是只测 Emitter,而是驱动真实 client + MockTransport 到落库。
|
||||||
|
|
||||||
|
| 链路 | 用例 | 断言 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| chat 重试耗尽 | `TestChatTerminalFailureRows::test_retry_exhaustion_writes_exactly_one_terminal_row` | 3 条 attempt + **恰 1 条**终态;终态 `attempts == 3` |
|
||||||
|
| chat 结构化耗尽 | `test_structured_exhaustion_writes_the_only_failure_row` | attempt 行**全是成功行**,终态是唯一失败记录;error 含有界 `validation=`/`repair=` 且 < 1200 字符、不含 raw_text |
|
||||||
|
| chat 400 直拒 | `test_request_rejected_now_has_both_an_attempt_and_a_terminal_row` | 尝试行 + 终态行**各 1**(已批准的行数翻倍);两行共享同一 `logical_call_id` |
|
||||||
|
| embedding | `test_embedding.py::TestReasonlessTelemetryContract::test_failed_attempts_still_have_null_effort` | attempt 数 == 脚本长度,终态恰 1 |
|
||||||
|
| OCR 两方法 | `test_ocr_client.py` 同名用例(参数化 `recognize_text`/`parse_layout`) | 终态恰 1,且 `operation` 为**公开方法名** |
|
||||||
|
|
||||||
|
去重:`test_terminal_row_is_written_once_per_logical_call` 连调出口 3 次,SQL 可见仍 1 条(`claim_terminal`)。
|
||||||
|
非领域异常:`test_non_domain_exception_writes_no_terminal_row` —— `KeyError` 原样传播、**0 条**终态、分类不被改写。
|
||||||
|
|
||||||
|
**双写已消除**:`TelemetryMW` 的两个终态分支删除,改由三个 client 的公开边界经
|
||||||
|
`emit_terminal_once` 统一写出;`TestTelemetryMW::test_scope_level_failure_is_not_written_here_anymore`
|
||||||
|
与 `test_cancellation_is_not_written_here_anymore` 锁死"本层不再写终态",防回归双计。
|
||||||
|
|
||||||
|
### 2.3 取消口径
|
||||||
|
|
||||||
|
- chat 取消:`test_cancellation_writes_at_most_one_terminal_row` —— 恰 1 条,`error == "cancelled"`,
|
||||||
|
且 `error_type` 为 NULL(**字符串不解析猜诊断**)。
|
||||||
|
- 三链路同策略"尽力写一条、允许 0";`emit_terminal_once` **不 shield、不开后台任务**,
|
||||||
|
快照冻结是同步动作;写入 await 上再被取消则 `CancelledError` 原样传播(与 TelemetryMW 历史行为同款)。
|
||||||
|
|
||||||
|
### 2.4 SQL 不双计(按真实 SQLite 落库断言)
|
||||||
|
|
||||||
|
`TestTerminalRowSqlSemantics` 用真实 `SQLiteRecorder` 驱动一次失败 chat 后直接查表:
|
||||||
|
|
||||||
|
| 迁移影响 | 断言 |
|
||||||
|
| --- | --- |
|
||||||
|
| 失败计数判据 | `error IS NOT NULL` 得 **3**(2 尝试 + 1 终态),`event_kind='terminal_failure'` 得 **1** |
|
||||||
|
| 费用不双计 | 终态行 `cost IS NOT NULL` 计数为 **0**;且 `usage_source='unavailable'`、token 全 0 |
|
||||||
|
| 时延分组 | 终态 `latency_ms` ≥ 任何单次尝试(含退避),故看板必须按 `event_kind` 分组 |
|
||||||
|
| 双时钟微差 | 终态 `latency_ms == total_latency_ms`(同一份冻结快照) |
|
||||||
|
| 逻辑两列归属 | 尝试行 `attempts`/`total_latency_ms` 恒 NULL |
|
||||||
|
| §5 归因查询 | 同一 `logical_call_id` 同时给出整池 reason 文案与逐源 503 现场;终态 `http_status_code` 为 NULL(C1 不冒充) |
|
||||||
|
|
||||||
|
### 2.5 诊断保真与 operation 修正
|
||||||
|
|
||||||
|
- 中转把 529 改写成 503 → **记 503 不猜回 529**;直接 529 记 529。
|
||||||
|
- 空 `str()` 的 Connect/Read/Write/PoolTimeout → `cause_type` 落对应 httpx 类名,`error` 退回类名。
|
||||||
|
- 成功行五列全 NULL(**不统一填 200**)。
|
||||||
|
- `_status_to_error` 增 keyword `operation`:`embed()` 非 200 改传 `"embedding"`(修正历史误标),
|
||||||
|
流式与非流式 chat 两处仍 `"chat"`(按实施计划 §2 归属表,未按设计行号误标)。
|
||||||
|
- 新列 `operation` 恒为公开方法四值,**绝不读 `exc.operation`**:
|
||||||
|
`test_operation_is_given_by_the_call_site_not_the_exception` 用 `exc.operation="download_result"` 反证。
|
||||||
|
- OCR `"类名: msg"` 前缀由出口的显式策略参数 `class_prefixed_error` 承载,不再三处各拼一遍。
|
||||||
|
|
||||||
|
## 3. 有界 validation 说明的单一所有者
|
||||||
|
|
||||||
|
`structured.py` 的 `_MAX_FEEDBACK_ERRORS`/`_MAX_ERROR_CHARS`/`_format_errors` 改名为
|
||||||
|
公开的 `MAX_FEEDBACK_ERRORS`/`MAX_ERROR_CHARS`/`format_bounded_errors`,
|
||||||
|
由"重问反馈"与"终态结构化说明"两个消费者共同引用,**数值只有一份**。
|
||||||
|
行为逐字不变(`test_structured.py` 22 项全绿,含反馈文案用例)。
|
||||||
|
|
||||||
|
## 4. 未改动确认(防越界)
|
||||||
|
|
||||||
|
`errors.py`、`admission.py`、`ratelimit.py`、`breaker.py`、`sources.py`、`thinking.py`、
|
||||||
|
`providers.py`、`telemetry/sqlite.py`、`telemetry/postgres.py`、`transports/monkey_ocr.py`
|
||||||
|
一字未动——两个 recorder 靠 `**fields` + `schema.COLUMNS` 自动吃到新列。
|
||||||
|
缓存 key 公式、重试预算与退避、429 免预算、stall 算法、取消结算、推理能力表均未触碰。
|
||||||
|
唯一顺带修正:`RetryMW.__init__` 的 `emitter` 注解由 `object | None` 收紧为
|
||||||
|
`TelemetryEmitter | None`(TYPE_CHECKING 导入,同层不破分层契约),因本轮改了它的 `_emit`。
|
||||||
|
|
||||||
|
## 5. T4 验收(PG 存储兼容、变异矩阵、文档同步)
|
||||||
|
|
||||||
|
基线 HEAD `393f2bf`(1467 unit 全绿),全部命令在 `PolyGateway` conda 环境执行。
|
||||||
|
|
||||||
|
### 5.1 PG 存储兼容(真实实验室 Postgres,复用 `pg_sandbox`)
|
||||||
|
|
||||||
|
机械迁移:`_EXPECTED_COLUMNS` 27 → 37 列、`_record_minimal` 字段字典补 10 键(与单测同款)、
|
||||||
|
`_PRE_TENANT_COLUMNS` 的缺列集由4 列扩到 14 列。新十列一律由 `_CALL_OBSERVABILITY_COLUMNS` 派生,
|
||||||
|
两处 manual 档告警的逐字断言改成按 `COLUMNS` 序派生的 `_PRE_TENANT_MISSING_NOTICE`——
|
||||||
|
另抄一份列名必然漂移,而漂移的表现是“manual 档没补列”这条断言假绿。
|
||||||
|
|
||||||
|
| 阶段 | 命令 | 结果 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| 机械迁移前(已知必红) | `pytest tests/integration/test_postgres_telemetry.py -q -x` | **1 failed / 18 passed**:manual 档列序断言 `Right contains 10 more items, first extra item: 'scope'` |
|
||||||
|
| 机械迁移后 | 同上(无 `-x`) | **27 passed**,EXIT=0,`tests/outputs/135/pg-telemetry-after-mechanical.log` |
|
||||||
|
| 新增四项验收后 | 同上 | **30 passed**,EXIT=0,`tests/outputs/135/pg-telemetry-new-cases.log` |
|
||||||
|
|
||||||
|
新增 `TestCallObservabilityColumnsAcceptance`(对应计划 T4 的 PG 四项),共用一张 27 列的 1.3.4 形态旧表(`pre_135_schema`):
|
||||||
|
|
||||||
|
| 验收项 | 用例与关键断言 |
|
||||||
|
| --- | --- |
|
||||||
|
| auto 追加 10 列 + 旧行 NULL | `test_pre_135_table_gains_the_ten_columns_and_old_rows_stay_null`:物理列 27 → 37 且列序 == `_EXPECTED_COLUMNS`;attempt 行与 terminal 行十列取值**整体比对**(不是逐条 in);历史行 `dict.fromkeys(...)` 十列全 NULL |
|
||||||
|
| manual 缺列裁剪 | `test_manual_trims_the_insert_on_a_pre_135_table`:表结构逐字不动(== `_PRE_135_COLUMNS`);裁剪后 26 列逐列等于提交值(防整体错位);恰 1 条告警且含可直接粘贴的首/末列 ALTER;无“写入失败”/“补列失败”,`degraded is False` |
|
||||||
|
| 新旧进程混写 | `test_old_and_new_writers_share_one_table`:新版建表写 36 列 → 旧版进程用 `insert_sql("postgres", 26 列集)` 写入 → 新版再写;三行共存、表结构不变、旧行新列全 NULL、无写入失败 warning |
|
||||||
|
| 下游口径验收 | 同上用例尾部:`WHERE event_kind = 'terminal_failure'` 计得 1;`event_kind IS NULL` 计得 1(混写期旧行既不误计成失败也不误计成成功) |
|
||||||
|
|
||||||
|
纪律:未引用 `assert_no_leftovers`(它是 `test_pg_sandbox.py` 的模块级 fixture,对本文件不可见,上提它要改 `conftest.py`);
|
||||||
|
未新建沙箱设施、未碰共享表 `llm_calls`、未读或打印 DSN。新增的只有一个 `_execute_args`(带参数单语句)与
|
||||||
|
`_minimal_fields`(从 `_record_minimal` 拆出的字段字典,供“旧进程”复用同一份取值)。
|
||||||
|
|
||||||
|
### 5.2 变异矩阵(仓库外副本,主工作区生产代码零改动)
|
||||||
|
|
||||||
|
驱动脚本 `/tmp/pgw-135-mut/run_mutations.py`;每项“还原副本 → 施加单点变异(断言替换命中)→ 跑指定节点 → 还原”。
|
||||||
|
完整日志 `tests/outputs/135/mutations.log`,脚本总退出码 **EXIT=0**。
|
||||||
|
|
||||||
|
| # | 变异 | exit | 被杀断言(节选) |
|
||||||
|
| --- | --- | --- | --- |
|
||||||
|
| M1 | `register_attempt()` 挪到 transport 成功之后 | 1 | `test_failed_retries_are_counted`、`test_budget_free_429_still_counts_as_an_attempt`、`test_retry_exhausted_counts_every_attempt` |
|
||||||
|
| M2 | `ChatRequest` 每次 `replace` 复制出新上下文 | 1 | `TestLogicalCallStats` 4 项 + `test_retry_exhaustion_writes_exactly_one_terminal_row` |
|
||||||
|
| M3 | `_rehydrate` 去掉 `call_stats=None` 覆盖 | 1 | `test_historic_dict_never_impersonates_call_stats` |
|
||||||
|
| M4 | Emitter 入口提前 `str(exc)` 压平 | 1 | 529/503 保真、4 个空超时文案 `cause_type`、类名前缀策略、结构化有界说明等 9 项 |
|
||||||
|
| M5 | 终态行复制最后一次 attempt 的 token/cost | 1 | `test_terminal_rows_never_contribute_to_cost`、`test_terminal_row_costs_nothing` |
|
||||||
|
| M6 | 去掉 `claim_terminal` 去重 | 1 | `test_terminal_row_is_written_once_per_logical_call`、`test_claim_terminal_is_true_once` |
|
||||||
|
| M7 | 装配闸改为捕获 `TypeError` 后 warning | 1 | `test_old_signature_recorder_is_refused_at_assembly`、`test_uninspectable_recorder_is_a_configuration_error` |
|
||||||
|
|
||||||
|
还原校验:副本 `.py` 文件集合散列与纯净态**逐字一致**(`66b58b9a…`),还原后同一批节点 **172 passed**。
|
||||||
|
|
||||||
|
> **方法论陷阱(影响本仓所有变异证据的有效性)**:只设 `PYTHONPATH=<副本>/src` 是**无效的**——
|
||||||
|
> `pyproject.toml` 的 `[tool.pytest.ini_options] pythonpath = ["src"]` 会把**仓库内**的 `src` 抢先塞进 `sys.path[0]`,
|
||||||
|
> 于是测的仍是原代码。首轮实跑七项变异**全部“存活”(exit=0)**就是这个坑;
|
||||||
|
> 改用 `-o pythonpath=<副本>` 覆盖后七项全部被杀。今后做变异必须先证“副本真的被导入”,
|
||||||
|
> 否则“变异存活”会被误读成“测试不够强”,而真相是变异根本没生效。
|
||||||
|
|
||||||
|
### 5.3 文档同步(字段数一律 `inspect` 实测,不凭记忆)
|
||||||
|
|
||||||
|
实测值:`len(inspect.signature(TelemetryRecorder.record_llm_call).parameters) - 1 == 36`,`len(COLUMNS) == 36`,物理列 37。
|
||||||
|
|
||||||
|
| 位置 | 改了什么 |
|
||||||
|
| --- | --- |
|
||||||
|
| `README.md` 能力表 | “必录 26 字段” → 36 字段 + 三类行与诊断列;新增“逻辑调用统计”一行 |
|
||||||
|
| `README.md` 新小节 | 《1.3.5 逻辑调用统计与失败诊断》:`call_stats` 读法、**SQL 迁移五项**、归因查询、存储侧升级 |
|
||||||
|
| `README.md` cap 覆盖面 | 补“`error_body` 沿用 `summarize_body` 上限、结构化说明自带限长,**两者都不在 cap 覆盖内**” |
|
||||||
|
| `ARCHITECTURE.md` §7.8 | 必录字段 26 → 36(十列逐个列出);新增“逻辑调用十列”段(列语义表 + 不变量 I3/I4 + `operation` vs `exc.operation` 两个语义 + 装配闸);cap 段补两处诊断文本不在覆盖面 |
|
||||||
|
| `CHANGELOG.md` | 新建《未发布》:公共面四项变更表 + 下游必须做的事(点名 `WHERE event_kind` 与装配期报错) |
|
||||||
|
| `.env.example` | `PGW_TELEMETRY_TEXT_CAP` 块补 1.3.5 覆盖面例外 |
|
||||||
|
| `schemas/llm-calls.md` | 标题 26 → 36 字段;十列逐行登记;新增《三类行与失败归因口径》(含归因 SQL 与迁移四条) |
|
||||||
|
| `metrics/call-telemetry-coverage.md` | 新增《1.3.5 三类行与逻辑调用覆盖》;live 基线列**不写伪百分比** |
|
||||||
|
|
||||||
|
版本号与发布步骤**未动**(任务边界);`pyproject.toml` / `__init__.py` 仍为 1.3.4。
|
||||||
|
|
||||||
|
### 5.4 本轮收口验证
|
||||||
|
|
||||||
|
| 检查 | 命令 | 结果 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| 静态 | `make check`(ruff format+lint + import-linter) | 见 §7 实跑记录 |
|
||||||
|
| 全量单测 | `pytest tests/unit -q` | 见 §7 |
|
||||||
|
| 目标集成 | `pytest tests/integration/test_postgres_telemetry.py -q` | **30 passed** |
|
||||||
|
|
||||||
|
## 6. 剩余缺口(不归本任务,不自称已关)
|
||||||
|
|
||||||
|
| 缺口 | 说明 |
|
||||||
|
| --- | --- |
|
||||||
|
| 独立验证 | 未派全新上下文 verifier(合并前硬门,由父会话前台派) |
|
||||||
|
| slow / e2e | 未跑,属发布清单第 4 步(CLAUDE §4.4.1) |
|
||||||
|
| live 覆盖基线 | `metrics/call-telemetry-coverage.md` 的实际基线列仍待首次生产运行填入 |
|
||||||
|
| 下游自建 recorder | 装配闸只能证明形状可被接受,证不了函数体真的落这些列(已写进 README/CHANGELOG) |
|
||||||
|
|
||||||
|
## 7. 环境噪音记录(不是缺陷)
|
||||||
|
|
||||||
|
自动检查器用**系统解释器 Python 3.13.9**(无 `redis`/`pydantic`/`httpx`/`loguru`/`asyncpg` 等依赖),
|
||||||
|
持续报 `test_client.py` 2 项失败与大量 "Import could not be resolved"、`StrEnum is unknown import symbol`。
|
||||||
|
已核实为环境问题、非本轮引入:
|
||||||
|
|
||||||
|
- 失败根因是 `ModuleNotFoundError: No module named 'redis'`(optional extra),本轮 diff 对 redis 零改动;
|
||||||
|
- 在**未改动的 HEAD** 上用同一系统解释器复跑,同样 2 failed / 90 passed;
|
||||||
|
- 项目强制环境 `conda run -n PolyGateway`(Python 3.12.13)下:`test_client.py` 98 passed、全量 1467 passed。
|
||||||
|
|
||||||
|
判据以 CLAUDE.md §2 规定的 conda 环境与 `make check` 为准。
|
||||||
|
|
||||||
|
**T4 轮次同样现象(已逐项复现并关闭)**:检查器报 `tests/integration/test_postgres_telemetry.py` “2/3 failed”
|
||||||
|
与 6 处 `Import "asyncpg" could not be resolved`。根因与上同:`asyncpg>=0.29` 是 optional extra
|
||||||
|
(`pyproject.toml:25` 的 `postgres`),检查器解释器里没装。已做确定性复现:
|
||||||
|
|
||||||
|
- 那 3 条恰是本文件**仅有的不依赖真实 PG 的用例**,其中 2 条要造 `PostgresRecorder`;
|
||||||
|
- 用 `/home/iomgaa/miniconda3/bin/python`(无 asyncpg)跑这 3 条:**2 failed / 1 passed / 0.09s**,与检查器报告逐字吹合;
|
||||||
|
- 同 3 条在 `conda run -n PolyGateway` 下:**3 passed**;整文件 **30 passed**(真实 PG);
|
||||||
|
- 被标记的 6 行均为**本轮未触及的旧行**,本轮只新增 1 处同款函数内 `import asyncpg`。
|
||||||
|
|
||||||
|
未为此修改代码:给旧行加 type-ignore 属任务外改动(反 gold-plating),且并非真修复。
|
||||||
|
|
||||||
|
## 8. 1.3.5 发布准备(2026-09-09,唯一 writer 会话)
|
||||||
|
|
||||||
|
范围仅**发布准备文档与版本号**:README 安装下界、CHANGELOG 定版、两处版本、本节记录。生产代码与测试**零改动**(`git diff` 只有 `CHANGELOG.md` / `README.md` / `pyproject.toml` / `__init__.py` 各 1 行,外加本文件追加的这一节)。未 merge/push/tag/构建/上传。
|
||||||
|
|
||||||
|
### 8.1 先查远端占用(改文件之前)
|
||||||
|
|
||||||
|
| 检查 | 结果 |
|
||||||
|
| --- | --- |
|
||||||
|
| `git ls-remote --tags origin` | 最高 `refs/tags/v1.3.4`,**无 v1.3.5**;远端分支只有 `main`(`af57f93`)与 `docs/1.3.4-release-evidence` |
|
||||||
|
| 本地 tag | 同样止于 `v1.3.4` |
|
||||||
|
|
||||||
|
远端未被占用是**本次时点**的事实,父会话真正 push/tag 前仍须复查以防竞态。
|
||||||
|
|
||||||
|
### 8.2 版本与文档数字(数字一律实测)
|
||||||
|
|
||||||
|
| 项 | 结果 |
|
||||||
|
| --- | --- |
|
||||||
|
| 两处版本 | `pyproject.toml` 与 `src/polygateway/__init__.py` 同为 `1.3.5`;由 `tests/unit/test_package.py` 机械断言一致(**6 passed**) |
|
||||||
|
| README 安装下界 | `>=1.3.4,<2` → `>=1.3.5,<2`(本版含装配期形状闸与 SQL 口径迁移,旧下界会让下游装到不含新列的包) |
|
||||||
|
| README 迁移醒目度 | 《1.3.5 逻辑调用统计与失败诊断》为顶层小节且带 `[!WARNING]`(点名"失败行变多、旧失败 SQL 会多数、自建 recorder 装配期报错"),能力表"逻辑调用统计"一行直链该锚点;沿用 1.3.4 的同款版式,未重排既有 1.3.4 迁移节 |
|
||||||
|
| CHANGELOG 定版 | `## 未发布` → `## 1.3.5(2026-09-09)`,日期取自本机 `date +%F` 实际值,正文未改 |
|
||||||
|
| 字段数复核 | `inspect.signature(TelemetryRecorder.record_llm_call)` 去 self **36 参**、`len(schema.COLUMNS) == 36`、探针实测物理列 **37**——README/CHANGELOG 的 36/37 与实测吻合,非凭记忆 |
|
||||||
|
|
||||||
|
README 静态数字未发现错误,故未做任何顺带修改。
|
||||||
|
|
||||||
|
### 8.3 复用既有证据的适用边界(不拿旧证据顶替本版统计)
|
||||||
|
|
||||||
|
| 证据 | 是否复用 | 边界 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| 独立验证(全新上下文 verifier,父会话前台派) | 复用结论:**0 阻塞** | 审的是本分支 `b4812e1` 的 1.3.5 变更面;本会话未重复派子代理,也未把它当作 live 覆盖或发布后检查的替代 |
|
||||||
|
| 本版最终全套件 `make test` | **本版实跑,不复用** | `final-gates/make-test.log/.exit`:**1605 passed / 23 skipped / 108 deselected / 95%,exit 0** |
|
||||||
|
| 本版真实 PG 集成 | **本版实跑,不复用** | `final-gates/pg-telemetry-verbose.log/.exit`:**30 passed,exit 0**(含新增四项列兼容验收) |
|
||||||
|
| 本版 unit | **本版实跑** | 本轮版本号改动后复跑 `pytest tests/unit -q`:**1469 passed,exit 0**(`release/unit.log/.exit`) |
|
||||||
|
| 1.3.4 模型矩阵/逐型号推理证据 | **按适用条件复用** | 1.3.5 对 `thinking.py`、能力表、wire 片段、缓存 key 公式、重试/限流/熔断语义**一字未改**(§4 已逐文件确认),故 1.3.4 的型号级结论在其原有边界内继续成立——连同它的 FAIL/UNKNOWN/不可达/缺轮**一并继承**,不因本版而升格。它**不能**充当 1.3.5 新增 API/schema 的证据,也不提供本版的测试统计数字 |
|
||||||
|
| 1.3.4 的全模型矩阵重跑 | **不跑** | 本版未改推理路径;用户已批准不再补全模型矩阵。本会话不发全型号请求 |
|
||||||
|
|
||||||
|
本版**改变的公共面**(`CallStats` 与四类响应新字段、端口 10 新参、遥测 10 列与 `terminal_failure` 行)全部由新写的离线真链路用例(三个 client + MockTransport 直到落库)、真实 SQLite 断言、真实 PG 30 项承担,见 §2、§2.4、§5.1。
|
||||||
|
|
||||||
|
### 8.4 本轮受影响路径的真实现场(并发 1、超时不压、无全模型请求)
|
||||||
|
|
||||||
|
| 亲跑 | 命令与证据 | 结果 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| 真实网关冒烟(复用既有 e2e,不另造工具) | `pytest tests/e2e/test_smoke_gateway.py -m slow -v`,tmux `pgw135-smoke`,`release/smoke-gateway.log/.exit` | **4 passed,exit 0**(流式/非流式/结构化 json/结构化模型四节点,9.55s) |
|
||||||
|
| 有界现场探针(**恰 1 次**真实调用,全程走库) | `release/probe_call_stats.py` → `release/probe-call-stats.log/.exit`,tmux `pgw135-probe` | **exit 0**:`MiniMax-M3`/源 `minimax_1`,`call_stats.attempts=1`、`total_latency_ms=2581` ≥ 单次尝试 `2562`、`logical_call_id` 与落库行逐字一致;临时 SQLite 物理列 **37**、写入面 **36**、恰 1 条 `event_kind='attempt'` 行、`operation='chat'`、`scope='LLM'`、逻辑两列与四个诊断列全 NULL |
|
||||||
|
|
||||||
|
探针脚本只落在 `tests/outputs/135/release/`(该目录 gitignore,不入库),不新增生产代码、测试或平台设施,未发裸 HTTP,沿用 `.env` 现有超时与单源配置。
|
||||||
|
|
||||||
|
### 8.5 提交前收口门
|
||||||
|
|
||||||
|
| 门 | 证据 | 结果 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| `make check` | `release/check.log/.exit` | **exit 0**:94 文件格式通过、ruff 通过、import-linter **1 kept / 0 broken** |
|
||||||
|
| 包单测(两处版本一致) | `release/package.log/.exit` | **6 passed,exit 0** |
|
||||||
|
| 全量 unit | `release/unit.log/.exit` | **1469 passed,exit 0** |
|
||||||
|
|
||||||
|
23 项 skip 的理由已逐条留档(`final-gates/skip-reasons.log`):17 项 redis 时间语义由 integration 变体覆盖、6 项需实验室语料 `data/soak/chs_images`;**skip 不计通过**。conda 启动器既有 `RequestsDependencyWarning` 保留,不宣称零告警。
|
||||||
|
|
||||||
|
### 8.6 尚未执行(不得当成已完成)
|
||||||
|
|
||||||
|
merge、push、`git tag -a v1.3.5`、`python -m build`、`twine check`/`upload`、`pip download` 解包验证、Gitea Release 与包页面/仓库关联检查**全部未执行**;`pytest -m slow` 的其余 e2e(本轮只跑了 `test_smoke_gateway.py` 四节点)与 live 覆盖基线同样未跑。§6 的四项缺口除"独立验证"已由父会话关闭外,其余保持开启。
|
||||||
@@ -465,6 +465,13 @@
|
|||||||
"relation": "implements",
|
"relation": "implements",
|
||||||
"evidence": "复用既有26字段,四种行来源与无推理成败NULL;不增加生产数据面",
|
"evidence": "复用既有26字段,四种行来源与无推理成败NULL;不增加生产数据面",
|
||||||
"added": "2026-09-09T06:32:06.527808+00:00"
|
"added": "2026-09-09T06:32:06.527808+00:00"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"source": "plan:2026-09-09-135-call-observability",
|
||||||
|
"target": "design:2026-09-09-135-call-observability-design",
|
||||||
|
"relation": "implements",
|
||||||
|
"evidence": "1.3.5 逻辑调用统计与结构化失败诊断实施计划落地已批准设计",
|
||||||
|
"added": "2026-09-09T13:42:00.298915+00:00"
|
||||||
}
|
}
|
||||||
]
|
]
|
||||||
}
|
}
|
||||||
@@ -1,8 +1,8 @@
|
|||||||
# Research Wiki 索引
|
# Research Wiki 索引
|
||||||
|
|
||||||
> 自动生成,更新时间:2026-09-09 06:32 UTC
|
> 自动生成,更新时间:2026-09-09 16:49 UTC
|
||||||
|
|
||||||
## design (42)
|
## design (43)
|
||||||
|
|
||||||
- [1.3.4 推理意图与测试证据设计](designs/2026-09-09-134-thinking-contracts-design.md) `design:2026-09-09-134-thinking-contracts-design`
|
- [1.3.4 推理意图与测试证据设计](designs/2026-09-09-134-thinking-contracts-design.md) `design:2026-09-09-134-thinking-contracts-design`
|
||||||
- [2026-07-20-m1-core-design](designs/2026-07-20-m1-core-design.md) `design:2026-07-20-m1-core-design`
|
- [2026-07-20-m1-core-design](designs/2026-07-20-m1-core-design.md) `design:2026-07-20-m1-core-design`
|
||||||
@@ -24,6 +24,7 @@
|
|||||||
- [2026-08-19-issue14-admission-wait-policy-design](designs/2026-08-19-issue14-admission-wait-policy-design.md) `design:2026-08-19-issue14-admission-wait-policy-design`
|
- [2026-08-19-issue14-admission-wait-policy-design](designs/2026-08-19-issue14-admission-wait-policy-design.md) `design:2026-08-19-issue14-admission-wait-policy-design`
|
||||||
- [2026-08-24-issue15-telemetry-pool-lifecycle-design](designs/2026-08-24-issue15-telemetry-pool-lifecycle-design.md) `design:2026-08-24-issue15-telemetry-pool-lifecycle-design`
|
- [2026-08-24-issue15-telemetry-pool-lifecycle-design](designs/2026-08-24-issue15-telemetry-pool-lifecycle-design.md) `design:2026-08-24-issue15-telemetry-pool-lifecycle-design`
|
||||||
- [2026-09-04-reasoning-effort-design](designs/2026-09-04-reasoning-effort-design.md) `design:2026-09-04-reasoning-effort-design`
|
- [2026-09-04-reasoning-effort-design](designs/2026-09-04-reasoning-effort-design.md) `design:2026-09-04-reasoning-effort-design`
|
||||||
|
- [2026-09-09-135-call-observability-design](designs/2026-09-09-135-call-observability-design.md) `design:2026-09-09-135-call-observability-design`
|
||||||
- [est_tokens 解耦: 拆分限流预扣与遥测用量兜底(issue #2)](designs/est-tokens-decoupling.md) `design:est-tokens-decoupling`
|
- [est_tokens 解耦: 拆分限流预扣与遥测用量兜底(issue #2)](designs/est-tokens-decoupling.md) `design:est-tokens-decoupling`
|
||||||
- [GatewaySettings 装配校验补齐(第二轮)](designs/settings-invariants-round-2.md) `design:settings-invariants-round-2`
|
- [GatewaySettings 装配校验补齐(第二轮)](designs/settings-invariants-round-2.md) `design:settings-invariants-round-2`
|
||||||
- [GatewaySettings 跨字段不变量守卫的生效范围](designs/settings-invariant-guards.md) `design:settings-invariant-guards`
|
- [GatewaySettings 跨字段不变量守卫的生效范围](designs/settings-invariant-guards.md) `design:settings-invariant-guards`
|
||||||
@@ -47,9 +48,10 @@
|
|||||||
- [调用方自定义维度设计(issue #11)](designs/issue11-caller-dimensions.md) `design:issue11-caller-dimensions`
|
- [调用方自定义维度设计(issue #11)](designs/issue11-caller-dimensions.md) `design:issue11-caller-dimensions`
|
||||||
- [采样参数透传设计(issue #4)](designs/sampling-params.md) `design:sampling-params`
|
- [采样参数透传设计(issue #4)](designs/sampling-params.md) `design:sampling-params`
|
||||||
|
|
||||||
## finding (15)
|
## finding (16)
|
||||||
|
|
||||||
- [1.3.4 T0–T4 与 T7 确定性验证](findings/2026-09-09-134-thinking-contracts-validation.md) `finding:2026-09-09-134-thinking-contracts-validation`
|
- [1.3.4 推理契约验证与发布准备](findings/2026-09-09-134-thinking-contracts-validation.md) `finding:2026-09-09-134-thinking-contracts-validation`
|
||||||
|
- [1.3.5 T2/T3/T4 验收证据:36 列遥测、失败终态、PG 存储兼容与变异矩阵](findings/2026-09-09-135-call-observability-validation.md) `finding:2026-09-09-135-call-observability-validation`
|
||||||
- [2026-07-20-m2-soak-workload](findings/2026-07-20-m2-soak-workload.md) `finding:2026-07-20-m2-soak-workload`
|
- [2026-07-20-m2-soak-workload](findings/2026-07-20-m2-soak-workload.md) `finding:2026-07-20-m2-soak-workload`
|
||||||
- [2026-07-21-m25-acceptance](findings/2026-07-21-m25-acceptance.md) `finding:2026-07-21-m25-acceptance`
|
- [2026-07-21-m25-acceptance](findings/2026-07-21-m25-acceptance.md) `finding:2026-07-21-m25-acceptance`
|
||||||
- [2026-07-21-p6-soak-baseline](findings/2026-07-21-p6-soak-baseline.md) `finding:2026-07-21-p6-soak-baseline`
|
- [2026-07-21-p6-soak-baseline](findings/2026-07-21-p6-soak-baseline.md) `finding:2026-07-21-p6-soak-baseline`
|
||||||
@@ -65,9 +67,10 @@
|
|||||||
- [P7 OCR soak 验收: 99.73% 与 13 不变量全 PASS](findings/p7-ocr-soak.md) `finding:p7-ocr-soak`
|
- [P7 OCR soak 验收: 99.73% 与 13 不变量全 PASS](findings/p7-ocr-soak.md) `finding:p7-ocr-soak`
|
||||||
- [推理开关与 reasoning_tokens: 供应商实测与业界做法](findings/2026-08-02-thinking-switch-and-reasoning-tokens.md) `finding:2026-08-02-thinking-switch-and-reasoning-tokens`
|
- [推理开关与 reasoning_tokens: 供应商实测与业界做法](findings/2026-08-02-thinking-switch-and-reasoning-tokens.md) `finding:2026-08-02-thinking-switch-and-reasoning-tokens`
|
||||||
|
|
||||||
## plan (37)
|
## plan (38)
|
||||||
|
|
||||||
- [1.3.4 推理契约实施计划](plans/2026-09-09-134-thinking-contracts.md) `plan:2026-09-09-134-thinking-contracts`
|
- [1.3.4 推理契约实施计划](plans/2026-09-09-134-thinking-contracts.md) `plan:2026-09-09-134-thinking-contracts`
|
||||||
|
- [1.3.5 逻辑调用统计与结构化失败诊断实施计划](plans/2026-09-09-135-call-observability.md) `plan:2026-09-09-135-call-observability`
|
||||||
- [2026-07-20-m1-core-plan](plans/2026-07-20-m1-core-plan.md) `plan:2026-07-20-m1-core-plan`
|
- [2026-07-20-m1-core-plan](plans/2026-07-20-m1-core-plan.md) `plan:2026-07-20-m1-core-plan`
|
||||||
- [2026-07-20-m2-distributed-plan](plans/2026-07-20-m2-distributed-plan.md) `plan:2026-07-20-m2-distributed-plan`
|
- [2026-07-20-m2-distributed-plan](plans/2026-07-20-m2-distributed-plan.md) `plan:2026-07-20-m2-distributed-plan`
|
||||||
- [2026-07-21-m25-resilience-plan](plans/2026-07-21-m25-resilience-plan.md) `plan:2026-07-21-m25-resilience-plan`
|
- [2026-07-21-m25-resilience-plan](plans/2026-07-21-m25-resilience-plan.md) `plan:2026-07-21-m25-resilience-plan`
|
||||||
@@ -111,7 +114,7 @@
|
|||||||
|
|
||||||
## schema (1)
|
## schema (1)
|
||||||
|
|
||||||
- [表结构: llm_calls(遥测 26 字段)](schemas/llm-calls.md) `schema:llm-calls`
|
- [表结构: llm_calls(遥测 36 字段)](schemas/llm-calls.md) `schema:llm-calls`
|
||||||
|
|
||||||
## metric (2)
|
## metric (2)
|
||||||
|
|
||||||
|
|||||||
@@ -156,3 +156,6 @@
|
|||||||
- [2026-09-09 05:39 UTC] 重建索引: 98 篇页面
|
- [2026-09-09 05:39 UTC] 重建索引: 98 篇页面
|
||||||
- [2026-09-09 06:32 UTC] 新增边: schema:llm-calls --implements--> design:2026-09-09-134-thinking-contracts-design
|
- [2026-09-09 06:32 UTC] 新增边: schema:llm-calls --implements--> design:2026-09-09-134-thinking-contracts-design
|
||||||
- [2026-09-09 06:32 UTC] 重建索引: 98 篇页面
|
- [2026-09-09 06:32 UTC] 重建索引: 98 篇页面
|
||||||
|
- [2026-09-09 13:42 UTC] 新增边: plan:2026-09-09-135-call-observability --implements--> design:2026-09-09-135-call-observability-design
|
||||||
|
- [2026-09-09 13:42 UTC] 重建索引: 100 篇页面
|
||||||
|
- [2026-09-09 16:49 UTC] 重建索引: 101 篇页面
|
||||||
|
|||||||
@@ -17,3 +17,17 @@ date: 2026-07-20
|
|||||||
| live 覆盖 | 逐轮 PASS/FAIL/UNCOVERED、计划轮数与缺轮分别统计;必需单元不因 pytest exit 0 自动放行 | 未执行;UNKNOWN/缺轮/skip 不能记PASS |
|
| live 覆盖 | 逐轮 PASS/FAIL/UNCOVERED、计划轮数与缺轮分别统计;必需单元不因 pytest exit 0 自动放行 | 未执行;UNKNOWN/缺轮/skip 不能记PASS |
|
||||||
|
|
||||||
复用 schema:llm-calls(无新字段/DDL),证据索引见 `findings/2026-09-09-134-thinking-contracts-validation.md`。独立错误取证只在 tests 内存,Markdown 只记录白名单安全摘要与布尔校验,不使用生产遥测旁路补失踪尝试。生产埋点仍是 TelemetryEmitter 单点出口。
|
复用 schema:llm-calls(无新字段/DDL),证据索引见 `findings/2026-09-09-134-thinking-contracts-validation.md`。独立错误取证只在 tests 内存,Markdown 只记录白名单安全摘要与布尔校验,不使用生产遥测旁路补失踪尝试。生产埋点仍是 TelemetryEmitter 单点出口。
|
||||||
|
|
||||||
|
## 1.3.5 三类行与逻辑调用覆盖
|
||||||
|
|
||||||
|
本版把覆盖度的计量单位从"一次尝试"改成"一次逻辑调用"——此前结构化耗尽、embedding/OCR 的无源与准入拒绝根本没有任何行,"每次调用必录"在这几条路径上是不成立的。
|
||||||
|
|
||||||
|
| 指标 | 确定性阈值/证据 | 实际 live 基线 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| 领域失败的终态行覆盖 | chat 结构化耗尽、embedding/OCR 的 `no_sources`、准入拒绝、`retry_exhausted`、尝试外取消各恰有 **1** 条;单测以真实临时 SQLite 抓实 | 待首次实际运行,不填伪百分比 |
|
||||||
|
| 至多一条(I3) | 同一逻辑调用重复进出口不产生第二条(`claim_terminal`);recorder 写失败仅 warning,故 SQL 可见 ≤ 1 | 待首次实际运行 |
|
||||||
|
| 非领域异常 0 条(I4) | 编程错(如 `KeyError`)不写终态行、原样传播、分类不被改写 | 待首次实际运行 |
|
||||||
|
| 诊断列保真 | 中转把 529 改写成 503 则记 503(**不猜回**);空 `str()` 的 httpx 超时类落 `cause_type`;成功行五列 NULL | 待首次实际运行 |
|
||||||
|
| 存储兼容 | 真实 PG 沙箱: auto 追加十列、manual 裁剪写入、旧行新列恒 NULL、新旧进程混写共存 | 2026-09-09 实跑 30 passed(见下方证据索引) |
|
||||||
|
|
||||||
|
本版**新增十列**(见 schema:llm-calls),不新建表、不新增依赖。证据索引见 `findings/2026-09-09-135-call-observability-validation.md`;覆盖度真实基线仍待首次生产运行填入,不写伪百分比。
|
||||||
|
|||||||
@@ -0,0 +1,455 @@
|
|||||||
|
---
|
||||||
|
type: plan
|
||||||
|
node_id: plan:2026-09-09-135-call-observability
|
||||||
|
title: "1.3.5 逻辑调用统计与结构化失败诊断实施计划"
|
||||||
|
date: 2026-09-09
|
||||||
|
---
|
||||||
|
|
||||||
|
# 1.3.5 逻辑调用统计与结构化失败诊断实施计划
|
||||||
|
|
||||||
|
> 设计:`research-wiki/designs/2026-09-09-135-call-observability-design.md`,**人类于 2026-09-09 正式批准**(§10 六项批准项全数获批)。
|
||||||
|
> 计划审核门:Claude 自审 + **独立模型替代审查**(用户已同意以独立模型替代 Codex 那一道,结论仍须逐条核验后就地修订);plan 无人类门,审毕直接执行。
|
||||||
|
> 目标:把治理单位从"一次尝试"补齐到"一次逻辑调用"——四种响应带 `CallStats`,遥测补 10 列诊断/归因字段与 `terminal_failure` 行(issue #19、#23)。
|
||||||
|
> 方案:设计方案 B——每调用一个显式传递的私有可变上下文 + 领域异常下沉到单一遥测出口;复用既有 Emitter / schema / 三条治理循环,不新增表、不新增依赖、不引入追踪平台。
|
||||||
|
> 技术:Python 3.12+、asyncio、frozen dataclass、`inspect.signature`、pytest + FakeClock + MockTransport、临时 SQLite、真实 PG 沙箱、ruff、import-linter。
|
||||||
|
> 基线 HEAD:`a81cc91`(分支 `feature/1.3.5-call-observability`,工作区仅 `CLAUDE.md` 既有 markdown 格式差异与未跟踪 `.pi/`,两者本计划一律不动、不暂存)。
|
||||||
|
|
||||||
|
本计划不涉及 `reference/` 参考实现迁移(治理主循环、Lua 限流、熔断状态机、退避公式一字不改),**保真校验不适用**。不得变更:重试预算与退避、429 免预算与 stall 算法、取消结算、限流/熔断语义、推理能力表与档位解析、缓存 key 公式、`#22`/`#24` 的调度机制。
|
||||||
|
|
||||||
|
## 1. 边界、授权与执行纪律
|
||||||
|
|
||||||
|
| 项目 | 固定边界 |
|
||||||
|
| --- | --- |
|
||||||
|
| 唯一 writer | 一工作区一 writer;父会话负责前台委派与审核派发。用户已授权本轮无需逐步请示,1.3.X 合并/发布授权沿用;跨到 1.4、新公共决策或验证豁免须停下确认 |
|
||||||
|
| 公共承诺 | 只做设计已批准的四项公共面变更:`CallStats` 导出、四响应新增字段、`TelemetryRecorder` 扩 10 参、`terminal_failure` 行;**不新增其它公共 API、不改既有字段名与位置** |
|
||||||
|
| 依赖铁律 | `ports.py`/`types.py`/`errors.py` 保持最内层,`types.py` 不 import 任何实现层;`middleware/` 只依赖端口与内核;`transports/`、`telemetry/`、`backends/` 互不依赖(import-linter 执法) |
|
||||||
|
| 取消 | `CancelledError` 永不吞没;终态写**取消优先、不 shield、不开后台任务**;快照冻结是同步动作,不 await |
|
||||||
|
| 降级方向 | recorder 写失败仍只 warning;限流/熔断后端仍 fail-closed;装配期签名不符 → **当场报错**(不是 warning) |
|
||||||
|
| 证据与秘密 | 不打印 `.env`、token、Authorization;不提交 `.pi/`、`tests/outputs/`、reference;命令输出只记安全路径、状态与退出码 |
|
||||||
|
| 证据复用 | 已发布 1.3.4 的有效证据(能力矩阵、live 轮次、发布外部验证)**直接引用不重建**;本版**不补跑未变更的模型能力矩阵**,无需新增付费调用 |
|
||||||
|
|
||||||
|
Skill 纪律:T0 已执行 `writing-plans`;T1–T3 行为变更执行 `test-driven-development`(先失败后通过的证据须落在本会话工具输出里);T1 触及运行时数据落库,执行 `structured-logging`;每次提交执行 `commit`(英文祈使标题、无 AI 签名、显式路径暂存);T4 前执行 `requesting-code-review` 与 `verification-before-completion`,收到意见执行 `receiving-code-review`;异常先 `systematic-debugging` 定根因。
|
||||||
|
|
||||||
|
## 2. 文件职责与不变接缝
|
||||||
|
|
||||||
|
| 动作 | 精确路径 | 职责 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| 修改 | `src/polygateway/types.py` | 新增 `CallStats`、私有 `_CallContext`、`CallOperation`/`EventKind` 词表;`ChatRequest` 追加内部上下文字段;四种响应追加 `call_stats` |
|
||||||
|
| 修改 | `src/polygateway/__init__.py` | 导出 `CallStats`(`__all__` 保序插入);版本号在 T4 统一 |
|
||||||
|
| 修改 | `src/polygateway/ports.py` | `TelemetryRecorder.record_llm_call` 追加 10 个 keyword-only 无默认值参数(唯一签名事实源) |
|
||||||
|
| 修改 | `src/polygateway/telemetry/schema.py` | `SQLITE_DDL` / `PG_DDL` / `SQLITE_BACKFILL` / `_PG_BACKFILL_DECLS` / `COLUMNS` **五处**同序同增 10 列,追加在物理列末尾(`PG_BACKFILL`、`_ALTER_BY_BACKEND`、`telemetry_schema_sql` 自动派生,不手改) |
|
||||||
|
| 修改 | `src/polygateway/middleware/telemetry.py` | Emitter 构造期注入 `scope` + 装配闸;三个 emit 入口收 `operation` 与领域异常对象;诊断字段单一提取 helper;`event_kind`;终态出口 helper;`TelemetryMW` 只保留 cache_hit |
|
||||||
|
| 修改 | `src/polygateway/middleware/structured.py` | 有界错误说明常量与拼装函数改为库内可复用(重问反馈与遥测说明同一口径,数值只一份) |
|
||||||
|
| 修改 | `src/polygateway/middleware/retry.py` | transport 调用前登记一次尝试;`_emit` 传异常对象与 `operation="chat"` |
|
||||||
|
| 修改 | `src/polygateway/middleware/cache.py` | `_serialize` 剔除 `call_stats`;`_rehydrate` 显式覆盖为 `None`(防历史 dict 冒充) |
|
||||||
|
| 修改 | `src/polygateway/client.py` | 自存 `now`/`emitter`;`chat` 创建上下文、附加统计、领域失败与取消经单一终态出口 |
|
||||||
|
| 修改 | `src/polygateway/embedding.py` | `embed` 拥有上下文(空输入 0 尝试 0 遥测行);逐批传递;终态请求摘要按 §3.5 |
|
||||||
|
| 修改 | `src/polygateway/ocr.py` | 上下文在 `image` 校验通过后创建;两公开方法各自给 `operation`;错误文本保留类名前缀(经出口的显式策略参数) |
|
||||||
|
| 修改 | `src/polygateway/transports/openai_compat.py` | `_status_to_error` 增 keyword-only `operation`;三个调用点显式给值:`:512`(`embed` 非 200)传 `"embedding"`(修正历史误标)、`:527`(流式 chat)与 `:625`(非流式 chat)传 `"chat"`;`ocr_text`/`parse`/`download_result` 词表不动。**归属以本表为准**:设计 §5 把 `:527` 也叙述成 `embed()` 的分支,实测 `:527` 属 `_complete_stream`(流式 chat)、`embed` 只有 `:512` 一处;勿按设计行号把两条 chat 失败回退误标成 embedding |
|
||||||
|
| 修改 | `tests/unit/test_types.py`、`tests/unit/test_ports.py` | `CallStats`/上下文纯行为、端口签名实测(含无默认值与 keyword-only) |
|
||||||
|
| 修改 | `tests/unit/test_telemetry.py` | 列序/列数、三类行语义、诊断保真、装配闸、SQLite 新旧表、`_record_minimal` 字段字典 |
|
||||||
|
| 修改 | `tests/unit/test_retry.py`、`test_client.py`、`test_cache.py`、`test_structured.py` | 计数/计时/缓存命中/结构化耗尽终态与历史 dict 防护 |
|
||||||
|
| 修改 | `tests/unit/test_embedding.py`、`test_ocr_client.py`、`test_openai_compat.py`、`test_monkey_ocr.py` | 多批、空输入、双 HTTP 一次尝试、`exc.operation` 修正、200 失败行 |
|
||||||
|
| 修改 | `tests/unit/test_pricing.py`、`tests/unit/test_usage_source_domain.py` | **仅 Emitter 调用点机械迁移**(`TelemetryEmitter(` 补 `scope=`、`emit_*` 补 `operation=`、`emit_terminal_failure` 去 `latency_ms` 改传 `stats`);两文件的 `_MemoryRecorder` 是 `**fields` 形态,recorder 签名不动 |
|
||||||
|
| 修改 | `tests/integration/test_postgres_telemetry.py` | PG auto 追加 / manual 缺列裁剪 / 旧行 NULL / 新旧进程混写(真实 `pg_sandbox`) |
|
||||||
|
| 修改 | `README.md`、`CHANGELOG.md`、`.env.example`、`research-wiki/ARCHITECTURE.md`、`research-wiki/schemas/llm-calls.md`、`research-wiki/metrics/call-telemetry-coverage.md` | 字段数实测改写、cap 覆盖面澄清、SQL 迁移五项、终态行语义 |
|
||||||
|
| 新建(验收时) | `research-wiki/findings/2026-09-09-135-call-observability-validation.md` | 红绿、变异、失败与豁免索引,≤300 行;原始输出留 `tests/outputs/135/` |
|
||||||
|
|
||||||
|
**不改**:`errors.py`(异常类与分类逐字不动,不加可变字段)、`middleware/admission.py`、`middleware/ratelimit.py`、`middleware/breaker.py`、`sources.py`、`thinking.py`、`providers.py`、`telemetry/sqlite.py`、`telemetry/postgres.py`(两个 recorder 靠 `**fields` + `schema.COLUMNS` 自动吃到新列,逻辑零改动)、`transports/monkey_ocr.py`(双 HTTP 仍在同一 transport 调用内,不拆)。若实现时发现必须突破本清单,先说明设计依据与最小原因交父会话核定,不顺手改。
|
||||||
|
|
||||||
|
## 3. 跨任务接口(可执行定义,禁止占位)
|
||||||
|
|
||||||
|
### 3.1 统计内核(`types.py`)
|
||||||
|
|
||||||
|
`types.py` 需新增 `import uuid`、`from collections.abc import Callable` 与 `from typing import Literal`(`Mapping`/`Any` 已在;全文现无 `Literal`)。
|
||||||
|
|
||||||
|
**运行时求值约束(`types.py` 无 `from __future__ import annotations`,实测 :1-17)**:`Callable` 与 `Literal` 必须是**运行时 import**,不得放进 `TYPE_CHECKING`(`_CallContext.__init__` 的函数注解与 `CallOperation` 别名都在 def/赋值时求值);且 `_CallContext` 必须**定义在 `ChatRequest`(:339)之前**,否则 `call_context: _CallContext | None` 的类注解在类创建时即 `NameError`。
|
||||||
|
|
||||||
|
上下文是**每调用一个实例**的单任务对象:chat 重试、结构化重问、embedding 分批都在同一任务内串行推进,故计数无需锁;严禁提升为 client 实例属性。
|
||||||
|
|
||||||
|
```python
|
||||||
|
CallOperation = Literal["chat", "embed", "recognize_text", "parse_layout"]
|
||||||
|
CALL_OPERATIONS: tuple[CallOperation, ...] = ("chat", "embed", "recognize_text", "parse_layout")
|
||||||
|
EventKind = Literal["attempt", "cache_hit", "terminal_failure"]
|
||||||
|
EVENT_KINDS: tuple[EventKind, ...] = ("attempt", "cache_hit", "terminal_failure")
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class CallStats:
|
||||||
|
"""一次公开调用的统计快照;第三方合成响应的 `None` 表示未知,不得伪造 0。"""
|
||||||
|
|
||||||
|
logical_call_id: str
|
||||||
|
attempts: int
|
||||||
|
total_latency_ms: int
|
||||||
|
|
||||||
|
|
||||||
|
class _CallContext:
|
||||||
|
"""私有可变逻辑调用上下文:只持计数、单调时钟与终态去重位,不做 I/O。"""
|
||||||
|
|
||||||
|
__slots__ = ("logical_call_id", "_now", "_started", "_attempts", "_terminal_claimed")
|
||||||
|
|
||||||
|
def __init__(self, *, now: Callable[[], float]) -> None: ...
|
||||||
|
|
||||||
|
def register_attempt(self) -> None:
|
||||||
|
"""transport 调用前登记一次尝试(含免预算 429 与端口本地拒绝)。"""
|
||||||
|
|
||||||
|
def snapshot(self) -> CallStats:
|
||||||
|
"""同步冻结当前快照;绝不 await,可多次调用。"""
|
||||||
|
|
||||||
|
def claim_terminal(self) -> bool:
|
||||||
|
"""首次 True、其后 False:保证每逻辑调用至多写一条终态行。"""
|
||||||
|
```
|
||||||
|
|
||||||
|
`ChatRequest` 追加(末尾,`dataclasses.replace` 保留同一引用;`StructuredMW` 的 replace 已核对不重建它):
|
||||||
|
|
||||||
|
```python
|
||||||
|
call_context: _CallContext | None = field(default=None, compare=False, repr=False)
|
||||||
|
"""库内部逻辑调用上下文;`None` = 库内现场构造的请求,遥测 logical_call_id 落 NULL。"""
|
||||||
|
```
|
||||||
|
|
||||||
|
`LLMResponse`、`EmbeddingResponse`、`OcrTextResult`、`OcrLayoutResult` 各追加**末尾**字段:
|
||||||
|
|
||||||
|
```python
|
||||||
|
call_stats: CallStats | None = None
|
||||||
|
```
|
||||||
|
|
||||||
|
### 3.2 遥测出口(`middleware/telemetry.py`)
|
||||||
|
|
||||||
|
Emitter 是全库唯一 `record_llm_call` 调用点,本版新增的一切诊断/归因取值也只在这里定型。
|
||||||
|
|
||||||
|
```python
|
||||||
|
class TelemetryEmitter:
|
||||||
|
def __init__(
|
||||||
|
self,
|
||||||
|
recorder: TelemetryRecorder,
|
||||||
|
*,
|
||||||
|
scope: str,
|
||||||
|
pricing: PricingTable | None = None,
|
||||||
|
text_cap: int | None,
|
||||||
|
) -> None:
|
||||||
|
"""`scope` 构造期注入(三个 client 各一行),使三类行都带池名;不拿 source_name 顶替。
|
||||||
|
|
||||||
|
同处执行装配闸 `_assert_recorder_shape(recorder)`。
|
||||||
|
"""
|
||||||
|
|
||||||
|
async def emit_attempt(
|
||||||
|
self,
|
||||||
|
*,
|
||||||
|
request: ChatRequest,
|
||||||
|
source: SourceConfig,
|
||||||
|
call_id: str,
|
||||||
|
latency_ms: int,
|
||||||
|
response: LLMResponse | None,
|
||||||
|
error: PolyGatewayError | str | None,
|
||||||
|
reasoning_applies: bool,
|
||||||
|
operation: CallOperation,
|
||||||
|
class_prefixed_error: bool = False,
|
||||||
|
) -> None:
|
||||||
|
"""`event_kind='attempt'`;失败异常对象在此提取 status/cause/body 四列。"""
|
||||||
|
|
||||||
|
async def emit_cache_hit(
|
||||||
|
self, *, request: ChatRequest, response: LLMResponse, operation: CallOperation
|
||||||
|
) -> None:
|
||||||
|
"""`event_kind='cache_hit'`;attempts/total_latency_ms 列恒 NULL。"""
|
||||||
|
|
||||||
|
async def emit_terminal_failure(
|
||||||
|
self,
|
||||||
|
*,
|
||||||
|
request: ChatRequest,
|
||||||
|
call_id: str,
|
||||||
|
error: PolyGatewayError | str,
|
||||||
|
operation: CallOperation,
|
||||||
|
stats: CallStats,
|
||||||
|
class_prefixed_error: bool = False,
|
||||||
|
) -> None:
|
||||||
|
"""`event_kind='terminal_failure'`;`latency_ms` 与 `total_latency_ms` 同取 `stats`。"""
|
||||||
|
```
|
||||||
|
|
||||||
|
`emit_terminal_failure` **不再收 `latency_ms`**(同一冻结快照供两列,避免双时钟微差)。诊断提取收敛为一个纯 helper,只读领域异常的既有属性,**不遍历任意对象、不猜正文**:
|
||||||
|
|
||||||
|
```python
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class _ErrorFields:
|
||||||
|
"""一行遥测的错误列;未知一律 None。"""
|
||||||
|
|
||||||
|
error: str | None
|
||||||
|
error_type: str | None
|
||||||
|
cause_type: str | None
|
||||||
|
http_status_code: int | None
|
||||||
|
error_body: str | None
|
||||||
|
|
||||||
|
|
||||||
|
def _error_fields(
|
||||||
|
error: PolyGatewayError | str | None,
|
||||||
|
*,
|
||||||
|
event_kind: EventKind,
|
||||||
|
class_prefixed: bool,
|
||||||
|
) -> _ErrorFields:
|
||||||
|
"""三种入参形态的唯一定型点(设计 §5/§6)。"""
|
||||||
|
```
|
||||||
|
|
||||||
|
判定规则(测试逐条钉死):
|
||||||
|
|
||||||
|
| 入参 | error | error_type | cause_type / http_status_code / error_body |
|
||||||
|
| --- | --- | --- | --- |
|
||||||
|
| `None` | None | None | 全 None |
|
||||||
|
| `str`(如既有 `"cancelled"`) | 原样 | None | 全 None(**不解析字符串猜诊断**) |
|
||||||
|
| 领域异常,`event_kind='attempt'` | 见下 | `type(exc).__name__` | `type(exc.__cause__).__name__ or None` / `exc.status_code` / `summarize_body` 已产出的 `exc.body_text or None` |
|
||||||
|
| 领域异常,`event_kind='terminal_failure'` | 见下 | `type(exc).__name__` | **全 None**(C1:不搬最后一次 attempt 的状态与正文冒充整池归因) |
|
||||||
|
|
||||||
|
error 文本:`str(exc)` 为空退回 `type(exc).__name__`;`class_prefixed=True` 时前置 `"{类名}: "`(OCR 既有 metric 归组口径);取消路径一律传字符串(attempt 行沿用既有 `"cancelled"`,终态行用同一明确取消文案),故 `error_type` 与其余三列均 NULL;`ResultInvalidError` 且为终态时并入有界结构化说明:
|
||||||
|
|
||||||
|
```python
|
||||||
|
def _structured_detail(exc: ResultInvalidError) -> str:
|
||||||
|
"""结构化耗尽的有界说明:`repair=` 至多 200 字符 + `validation=` 至多 3 条×200 字符;
|
||||||
|
**不含 raw_text**(模型正文预算已由 attempt 行的 response 列承担),两段以 ` | ` 拼接。"""
|
||||||
|
```
|
||||||
|
|
||||||
|
复用 `structured.py` 的既有规则所有者,不复制数值:把 `_MAX_FEEDBACK_ERRORS`/`_MAX_ERROR_CHARS` 改名为 `MAX_FEEDBACK_ERRORS`/`MAX_ERROR_CHARS`,`_format_errors` 改名 `format_bounded_errors(errors: Sequence[str]) -> str`(行为逐字不变),`StructuredMW` 与 `_structured_detail` 两个消费者共同引用。
|
||||||
|
|
||||||
|
装配闸(设计 §7,C3):
|
||||||
|
|
||||||
|
```python
|
||||||
|
def _assert_recorder_shape(recorder: TelemetryRecorder) -> None:
|
||||||
|
"""装配期一次 `signature.bind` 形状校验:不执行写入,只证明该形状能被接受。
|
||||||
|
|
||||||
|
参数名从 `TelemetryRecorder.record_llm_call` 的协议签名派生(不手抄第四份清单),
|
||||||
|
绑定用哨兵 `None`,不读真实请求数据。`**kwargs`(VAR_KEYWORD)自动通过;
|
||||||
|
`TypeError` → `ValueError` 装配期报错;不可 inspect(C 实现等)同样按配置错误报错。
|
||||||
|
"""
|
||||||
|
```
|
||||||
|
|
||||||
|
终态唯一出口(公开边界 helper,三个 client 共用):
|
||||||
|
|
||||||
|
```python
|
||||||
|
async def emit_terminal_once(
|
||||||
|
emitter: TelemetryEmitter | None,
|
||||||
|
*,
|
||||||
|
request: ChatRequest,
|
||||||
|
context: _CallContext,
|
||||||
|
error: PolyGatewayError | str,
|
||||||
|
operation: CallOperation,
|
||||||
|
class_prefixed_error: bool = False,
|
||||||
|
) -> None:
|
||||||
|
"""去重(claim_terminal)+ 同步冻结快照 + best effort 写入。
|
||||||
|
|
||||||
|
`emitter is None` 或已写过 → 直接返回;写入侧异常按既有降级只落 warning;
|
||||||
|
**`CancelledError` 原样传播**(取消优先,不 shield、不开后台任务)。
|
||||||
|
"""
|
||||||
|
```
|
||||||
|
|
||||||
|
`TelemetryMW` 相应收缩:删除其 `except (GatewayUnavailableError, GovernanceBackendError, SourceNotConfiguredError)` 与 `except CancelledError` 两个终态分支(改由 `GatewayClient.chat` 的边界统一写,避免两处同时写),保留 `cache_hit` 记录并传 `operation="chat"`。
|
||||||
|
|
||||||
|
### 3.3 `_record` 的 10 个新列取值(唯一定型点)
|
||||||
|
|
||||||
|
| 列 | attempt | cache_hit | terminal_failure |
|
||||||
|
| --- | --- | --- | --- |
|
||||||
|
| `scope` | 构造期注入值 | 同 | 同 |
|
||||||
|
| `operation` | 调用点给定的四值之一,**绝不读 `exc.operation`** | 同 | 同 |
|
||||||
|
| `logical_call_id` | `request.call_context.logical_call_id`,上下文缺席 → NULL(不造 ID) | 同 | 同 |
|
||||||
|
| `event_kind` | `'attempt'` | `'cache_hit'` | `'terminal_failure'` |
|
||||||
|
| `http_status_code` / `cause_type` / `error_body` | 见 §3.2 表(成功行全 NULL,成功不统一填 200) | 全 NULL | 全 NULL |
|
||||||
|
| `error_type` | 该行自身错误类名 | NULL | 自身类名(`AllSourcesExhausted` / `CircuitOpenError` / `ResultInvalidError` / …) |
|
||||||
|
| `attempts` / `total_latency_ms` | NULL | NULL | `stats` 两字段 |
|
||||||
|
|
||||||
|
其余 26 列口径逐字不变;终态行仍 `cost=None`、`usage_source='unavailable'`、token 0,不复制 attempt 的用量与费用。
|
||||||
|
|
||||||
|
### 3.4 schema 与端口(`telemetry/schema.py`、`ports.py`)
|
||||||
|
|
||||||
|
10 列按**同一顺序**追加进五处(`SQLITE_DDL`、`PG_DDL`、`SQLITE_BACKFILL`、`_PG_BACKFILL_DECLS`、`COLUMNS`),全部可空、无默认值,物理位置在现有末列 `reasoning_effort` 之后:
|
||||||
|
|
||||||
|
| 顺序 | 列名 | SQLite | Postgres |
|
||||||
|
| --- | --- | --- | --- |
|
||||||
|
| 1 | `scope` | TEXT | TEXT |
|
||||||
|
| 2 | `operation` | TEXT | TEXT |
|
||||||
|
| 3 | `logical_call_id` | TEXT | TEXT |
|
||||||
|
| 4 | `event_kind` | TEXT | TEXT |
|
||||||
|
| 5 | `http_status_code` | INTEGER | INTEGER |
|
||||||
|
| 6 | `error_type` | TEXT | TEXT |
|
||||||
|
| 7 | `cause_type` | TEXT | TEXT |
|
||||||
|
| 8 | `error_body` | TEXT | TEXT |
|
||||||
|
| 9 | `attempts` | INTEGER | INTEGER |
|
||||||
|
| 10 | `total_latency_ms` | INTEGER | INTEGER |
|
||||||
|
|
||||||
|
`COLUMNS` 由 26 → 36,物理列(含 `created_at`)27 → 37。**不建索引、不改旧列、不回填旧行、不 ALTER 默认生产 PG**(manual 档仍裁剪写入)。`ports.py` 按同序追加 10 个 keyword-only 无默认值参数,docstring 更新为"36 字段冻结",并说明 `error_body` 沿用 `summarize_body` 上限、不进 `PGW_TELEMETRY_TEXT_CAP` 覆盖面。
|
||||||
|
|
||||||
|
### 3.5 三条链路的上下文所有权
|
||||||
|
|
||||||
|
| 链路 | 创建点 | 传递 | 附加统计 | 终态 |
|
||||||
|
| --- | --- | --- | --- | --- |
|
||||||
|
| chat | `GatewayClient.chat`:overlay/维度/档位三项校验**之后**(校验异常保持原行为,在统计边界外) | 放进 `ChatRequest.call_context`,洋葱各层经 `replace` 保留同一引用;`RetryMW._attempt` 在 `transport.complete` 前 `register_attempt()`(**上下文为 `None` 时跳过**——库内现场构造的 `ChatRequest` 不得因此报错) | 返回前 `dataclasses.replace(response, call_stats=ctx.snapshot())`(含缓存命中路径与内联遥测耗时) | `except PolyGatewayError` / `except CancelledError` 各调 `emit_terminal_once`,随后原样 `raise`;非领域异常不捕、无终态 |
|
||||||
|
| embed | `EmbeddingClient.embed`:`texts` 类型校验与**调用方维度校验**(`validate_caller_dimensions`)之后;`expected_dim` 校验在 `_attempt` 内,本就在统计边界内 | 显式参数传到 `_embed_batch` → `_attempt`;`_emit` 现场构造的 `ChatRequest` 带 `call_context=ctx`;`transport.embed` 前登记 | 合并结果 `replace(..., call_stats=ctx.snapshot())`;**空输入返回真实 `attempts=0` 统计且不写任何遥测行** | 同上,`operation="embed"`;终态 messages = `<embed texts=N batches=M>` 占位 + 第一批(至多 `batch_size` 条、每条 200 字符,与逐批行同款构造) |
|
||||||
|
| OCR | `OcrClient._call`:`image` 的 `bytes`/非空校验**通过之后**(M1 例外) | `_call` 拥有上下文并返回 `tuple[_AttemptOutcome, CallStats]`,两个公开方法据此附加统计;`transport` 调用前登记(layout 的 POST+ZIP GET 计 **1** 次) | `OcrTextResult` / `OcrLayoutResult` 的 `call_stats` | `_call` 内 `except PolyGatewayError` / `except CancelledError` 调 `emit_terminal_once`,`operation` 由公开方法传入(`recognize_text` / `parse_layout`),`class_prefixed_error=True`;`no_sources` 的 `raise` 在循环之前,`try` 必须**包住该 raise**,否则无源终态行写不出 |
|
||||||
|
|
||||||
|
`GatewayClient` 需自存 `self._now` 与 `self._emitter`(现未保存);统计生效与否**不由 telemetry 是否启用决定**(`emitter is None` 时统计照常,仅无行可写)。
|
||||||
|
|
||||||
|
## 4. 任务与提交点
|
||||||
|
|
||||||
|
### T0:设计批准状态、计划与基线(本任务)
|
||||||
|
|
||||||
|
- [x] 设计文档状态行改为"人类已批准(2026-09-09)",新建本计划(≤600 行)。
|
||||||
|
- [x] 记录基线:`git status --short --branch`、`git log --oneline -3`、HEAD `a81cc91`;确认源码零差异,`CLAUDE.md` 既有 markdown 差异与 `.pi/` 一律不动、不暂存。
|
||||||
|
- [ ] 基线验证(由执行者在 T1 之前跑一次,作为"先失败"的对照底):`make check`;`conda run -n PolyGateway pytest tests/unit -q` → 预期全绿。**基线计数以本会话实跑输出为准**(近期会话记录为 1385 项量级),不拿计划里的数字当期待值;实际失败照录,不改期待绕过。
|
||||||
|
- [ ] 计划自审 + 独立模型审查(替代 Codex,用户已同意);意见逐条核验后就地修订。
|
||||||
|
- [ ] wiki 登记:`.claude/tools/research_wiki.py add_entity/add_edge/rebuild_index`(design ↔ plan `implements`),登记前先确认工具不覆盖同路径已有文档。
|
||||||
|
- [ ] 提交点:`docs: record approved call observability design and plan`(生产改动前的回滚点)。
|
||||||
|
|
||||||
|
### T1:统计内核与三条链路的逻辑边界(不动遥测列)
|
||||||
|
|
||||||
|
**文件**:`types.py`、`__init__.py`、`client.py`、`embedding.py`、`ocr.py`、`middleware/retry.py`、`middleware/cache.py`;测试 `tests/unit/test_types.py`、`test_client.py`、`test_retry.py`、`test_cache.py`、`test_embedding.py`、`test_ocr_client.py`、`test_structured.py`。
|
||||||
|
|
||||||
|
按 §3.1 与 §3.5 实现。先写测试并确认在旧实现上红(`AttributeError: 'LLMResponse' object has no attribute 'call_stats'` 不算行为红——先落一个"同一次调用的重试次数无处可读"的行为断言,再实现)。
|
||||||
|
|
||||||
|
| 红绿组 | 必须证明 |
|
||||||
|
| --- | --- |
|
||||||
|
| 计数 | 一次成功=1;失败重试=实际尝试数;免预算 429 计入;多源拒绝(端口本地拒绝)计入;结构化重问计入同一上下文且不重置;embedding 三批=3;OCR layout 双 HTTP=1;缓存命中=0;空输入=0 |
|
||||||
|
| 逻辑 ID | 重试/重问/分批共享同一 `logical_call_id`;同一 client 并发两次调用互不串(`asyncio.gather` 两路各自计数与 ID);`parent_call_id` 语义不变 |
|
||||||
|
| 计时(FakeClock) | 缓存 IO、退避 sleep、准入等待、重问、内联遥测收尾全部计入 `total_latency_ms`;毫秒/秒不混用(1.5s → 1500);`emitter=None` 时统计仍正确。**替身构造要求**:假缓存后端的 `get`/`set` 与假 recorder 的 `record_llm_call` 内部**必须主动推进 FakeClock**,否则"缓存 IO/内联遥测计入总耗时"的断言会退化成恒等于 0 的空转绿 |
|
||||||
|
| 缓存不毒化 | `_serialize` 输出无 `call_stats` 键;手写含 `"call_stats": {...}` 的历史条目命中后 `response.call_stats is None`(**dict 不得冒充 `CallStats`**);缓存 key 逐字节不变(黄金值) |
|
||||||
|
| 附加点 | 失败异常上**不附任何统计字段**(`hasattr(exc, "call_stats") is False`);`CancelledError` 类型与语义不变;非领域异常原样传播 |
|
||||||
|
| 空输入 | `embed([])` 返回 `attempts=0`、真实 `logical_call_id`,且注入的内存 recorder **零行** |
|
||||||
|
|
||||||
|
**验证**:`conda run -n PolyGateway pytest tests/unit/test_types.py tests/unit/test_client.py tests/unit/test_retry.py tests/unit/test_cache.py tests/unit/test_embedding.py tests/unit/test_ocr_client.py tests/unit/test_structured.py -q` → 目标断言先红后绿,其余保留行为绿;`make check`(含 import-linter:`types.py` 不得引入实现层 import)。
|
||||||
|
|
||||||
|
- [ ] 提交点:`feat: track logical call statistics across governed calls`
|
||||||
|
|
||||||
|
### T2:遥测 10 列、诊断保真、scope/operation 与装配闸
|
||||||
|
|
||||||
|
**文件**:`telemetry/schema.py`、`ports.py`、`middleware/telemetry.py`、`middleware/structured.py`、`middleware/retry.py`、`transports/openai_compat.py`、三个 client 的 Emitter 构造行;测试 `tests/unit/test_telemetry.py`、`test_ports.py`、`test_openai_compat.py`、`test_monkey_ocr.py`、`test_structured.py`。
|
||||||
|
|
||||||
|
按 §3.2–§3.4 实现(本任务只产出 attempt / cache_hit 两类行的新列,终态行留 T3)。先写测试确认旧实现红:现状下 `error` 列是被 `str()` 压平的自由文本、无 `scope`/`operation` 列、旧签名 recorder 只落 warning。
|
||||||
|
|
||||||
|
| 红绿组 | 必须证明 |
|
||||||
|
| --- | --- |
|
||||||
|
| 列与 SQL | `len(COLUMNS) == 36`、物理列 37、五处列序一致(新建库与 ALTER 追加列序相同);`insert_sql` 两端语句更新;`telemetry_schema_sql` 输出与库内 DDL 同源 |
|
||||||
|
| 端口 | `inspect.signature` 实测 10 个新参存在、keyword-only、无默认值;docstring 字段数与实测一致 |
|
||||||
|
| 诊断保真 | 中转把 529 改写成 503 → 记 503(**不猜回 529**);直接 529 → 529;空 `str()` 的 Connect/Read/Write/PoolTimeout → error 落类名、`cause_type` 为对应 httpx 类名;`error_body` 为 `summarize_body` 摘要且不等于 `raw_text`;成功行五列 NULL(不填 200) |
|
||||||
|
| operation | `embed` 非 200 → `exc.operation == "embedding"`(历史误标修正);新列 `operation` 恒为四值之一,与 `exc.operation` 无关、不随异常变化;`monkey_ocr` 的 `success != true` 带 **200** 的失败行 → `http_status_code == 200`(该列不可作失败判据) |
|
||||||
|
| scope | attempt 与 cache_hit 行都带 scope;model/provider/source 未选出时仍留原空值 |
|
||||||
|
| 字符串入参 | 取消 attempt 的 `"cancelled"` 仍原样落 `error`,其余四列 NULL(**不解析字符串**) |
|
||||||
|
| 装配闸 | 旧签名 recorder → 构造 `TelemetryEmitter`(即三个 client 装配)**抛错**而非 warning;`**kwargs` recorder 通过;不可 inspect 的对象 → 配置错误报错;参数名确由协议签名派生(改协议后闸自动跟随的断言) |
|
||||||
|
| 有界说明 | `format_bounded_errors` 重命名后 `StructuredMW` 反馈文案逐字不变(黄金串);常量只有一份定义 |
|
||||||
|
|
||||||
|
**验证**:`conda run -n PolyGateway pytest tests/unit/test_telemetry.py tests/unit/test_ports.py tests/unit/test_openai_compat.py tests/unit/test_monkey_ocr.py tests/unit/test_structured.py -q`;`make check`。
|
||||||
|
|
||||||
|
- [ ] 提交点:`feat: record scope, operation and failure diagnostics per row`
|
||||||
|
|
||||||
|
### T3:终态行、取消口径与统一出口
|
||||||
|
|
||||||
|
**文件**:`middleware/telemetry.py`(终态 helper 与 `TelemetryMW` 收缩)、`client.py`、`embedding.py`、`ocr.py`;测试 `tests/unit/test_telemetry.py`、`test_client.py`、`test_embedding.py`、`test_ocr_client.py`、`test_structured.py`、`test_retry.py`。
|
||||||
|
|
||||||
|
按 §3.2 的 `emit_terminal_once` 与 §3.5 的三条链路实现。先写测试确认旧实现红:结构化耗尽当前**没有任何失败行**;embedding/OCR 的无源、准入拒绝、重试耗尽与尝试外取消同样无终态行。
|
||||||
|
|
||||||
|
| 红绿组 | 必须证明 |
|
||||||
|
| --- | --- |
|
||||||
|
| 补漏 | chat 结构化耗尽、embedding/OCR 的 `no_sources`、准入拒绝、`retry_exhausted`、尝试外取消各恰有 **1** 条 `terminal_failure` |
|
||||||
|
| 不变量 I3 | 领域失败每调用至多 1 条(recorder 写失败仅 warning,SQL 可见 ≤1);重复调用出口不产生第二条(`claim_terminal`);直接 `RequestRejectedError` / `ResultInvalidError` 现在**既有 attempt 错误行也有终态行**(400 密集负载错误行翻倍是已批准的下游可见变化) |
|
||||||
|
| 非领域异常 | 编程错(如 `KeyError`)→ **0 条**终态行、原样传播、分类不被改写 |
|
||||||
|
| 取消三路 | chat / embed / OCR 同策略尽力写一条(允许 0);**终态写的 await 上被取消 → `CancelledError` 传播**(不 shield、无后台任务);permit 与探针释放行为不变(`inflight == 0`) |
|
||||||
|
| 归因 SQL | 设计 §5 那条 `WHERE logical_call_id = :lcid` 查询同时给出终态 reason 文案与逐源状态码/正文;终态行 `http_status_code`/`cause_type`/`error_body` 三列 NULL;结构化耗尽的终态 `error` 含有界 validation/repair 说明且**不含 `raw_text`** |
|
||||||
|
| 行语义 | 三类行均带 scope;`event_kind` 可区分;`SUM(cost)` 不因终态行变化(终态 `cost IS NULL`、usage `unavailable`);`AVG(latency_ms)` 按 `event_kind` 分组的断言;终态 `latency_ms == total_latency_ms`(同一快照) |
|
||||||
|
| 快照时机 | 终态快照不含自身写入耗时(FakeClock:写入内推进时钟,列值不变);成功响应快照含返回前已完成的内联遥测耗时 |
|
||||||
|
| 摘要 | embedding 终态 messages 为占位 + 第一批截断文本,不含全量原输入;OCR 终态沿用 `<ocr:{kind} image_bytes=…>`,图像 bytes 不入库;OCR 终态 error 保留类名前缀 |
|
||||||
|
|
||||||
|
**验证**:`conda run -n PolyGateway pytest tests/unit -q`(全量单测,含上述文件);`make check`。
|
||||||
|
|
||||||
|
- [ ] 提交点:`feat: emit one terminal failure row per logical call`
|
||||||
|
|
||||||
|
### T4:旧测试机械核对、存储兼容、变异证据、文档与独立验证
|
||||||
|
|
||||||
|
**文件**:下述机械核对清单 + `tests/integration/test_postgres_telemetry.py` + 文档清单 + 验收 finding。
|
||||||
|
|
||||||
|
**一次机械核对(禁止分散反复修)**:本版真正的破坏面**不只是 recorder 签名,还有 Emitter 侧**(`TelemetryEmitter.__init__` 新增必填 `scope`、三个 `emit_*` 新增必填 `operation`、`emit_terminal_failure` 去 `latency_ms` 改收 `stats`),这些关键词不含 `record_llm_call`/`COLUMNS`。故全量清单用:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
grep -rn "record_llm_call\|COLUMNS\|_EXPECTED_COLUMNS\|TelemetryEmitter(\|emit_attempt(\|emit_cache_hit(\|emit_terminal_failure(" tests/ --include=*.py
|
||||||
|
```
|
||||||
|
|
||||||
|
一轮改完再跑,不逐个文件试错。已核实的免改项:`tests/unit/test_backpressure.py:231` 的假 emitter 是 `emit_attempt(self, *args, **kwargs)`,兼容;`tests/integration/` 无 Emitter 构造点。已知点:
|
||||||
|
|
||||||
|
| 位置 | 动作 |
|
||||||
|
| --- | --- |
|
||||||
|
| `tests/unit/test_ports.py:99` `_DummyRecorder` | 显式签名补齐 10 参(它是"新签名可实现"的活证据,不改成 `**kwargs`) |
|
||||||
|
| `tests/unit/test_ports.py:264` `TestTelemetryRecorderSignature` | 新参进 `no default` / keyword-only 参数化 |
|
||||||
|
| `tests/unit/test_telemetry.py:40` `_EXPECTED_COLUMNS`、:220/:321/:597/:639/:647/:686-698 计数与尾部断言 | 26→36、27→37、尾部 10 列、旧表 backfill 目标列数 |
|
||||||
|
| `tests/unit/test_telemetry.py:108` `_record_minimal` | 字段字典补 10 键(默认 NULL 形态) |
|
||||||
|
| `tests/integration/test_postgres_telemetry.py:100` 字段字典 | 同上(该函数返回值被逐列断言消费,改动须与 `COLUMNS` 同序) |
|
||||||
|
| `test_client.py` / `test_embedding.py` / `test_ocr_client.py` / `test_openai_compat.py` / `test_pricing.py` / `test_cache.py` / `test_usage_source_domain.py` 的 `_MemoryRecorder` | 均为 `**fields` 形态,**recorder 签名无需改**;只需核对断言里的字段计数与新列期望 |
|
||||||
|
| `tests/unit/test_pricing.py`、`tests/unit/test_usage_source_domain.py` 的 **Emitter 调用点** | **须改**:`TelemetryEmitter(` 补 `scope=`、`emit_attempt(`/`emit_cache_hit(` 补 `operation=`;`test_usage_source_domain.py:297` 的 `emit_terminal_failure(...)` 同时缺 `scope`/`operation`/`stats` 且多传 `latency_ms`,不改必 `TypeError`(recorder 形态兼容 ≠ emitter 调用点兼容) |
|
||||||
|
|
||||||
|
**存储兼容**(真实 PG,复用 `tests/integration/conftest.py` 的 `pg_sandbox` / `pg_catalog_probe`,不新建沙箱设施;**不引用 `assert_no_leftovers`**——它是 `tests/integration/test_pg_sandbox.py:19` 的模块级 fixture,对 `test_postgres_telemetry.py` 不可见,上提它要改 §2 清单外的 `conftest.py`。本版不新增沙箱资源创建路径,残留风险与 1.3.4 逐字相同,由该文件既有用例覆盖,属可复用的既有证据):
|
||||||
|
|
||||||
|
- SQLite:新建库 37 列;旧表(1.3.4 形态 27 列)auto 档补齐 10 列且列序与新建库一致;manual 档不发 DDL、按现有列裁剪写入并发一条点名缺列的 warning;旧行新列为 NULL。
|
||||||
|
- PG(验收取以下**四项**):auto 追加 10 列;**manual 缺列裁剪**写入成功且不抛(`_trim_columns` 路径);旧行新列为 NULL;新旧进程混写同一表(旧列集写入 + 新列集写入并存)。
|
||||||
|
|
||||||
|
**变异证据**(仓库外临时副本 + `PYTHONPATH=<副本>/src`,先确认 `polygateway.__file__` 指向副本;逐个变异 → 跑指定节点记 exit 1 与被杀断言 → 恢复校验散列 → exit 0;**绝不在主工作区改生产代码凑红**):
|
||||||
|
|
||||||
|
| 变异 | 必须被杀死的断言 |
|
||||||
|
| --- | --- |
|
||||||
|
| `register_attempt()` 移到 transport 调用之后的 `except` 分支外/内错位 | 失败重试与 429 计数断言 |
|
||||||
|
| `ChatRequest` 上下文字段改为 `replace` 时新建实例(模拟上下文复制) | 重问/分批共享同一 `logical_call_id` 的断言 |
|
||||||
|
| `_rehydrate` 去掉 `call_stats=None` 覆盖 | 历史 dict 冒充 `CallStats` 的断言 |
|
||||||
|
| Emitter 入口提前 `str(exc)` 压平 | `error_type`/`http_status_code`/`error_body` 保真断言 |
|
||||||
|
| 终态行复制最后一次 attempt 的 token/cost | 费用聚合与终态 `cost IS NULL` 断言 |
|
||||||
|
| 去掉 `claim_terminal` 去重 | 每失败调用至多一条终态的断言 |
|
||||||
|
| 装配闸改为捕获 `TypeError` 后 warning | 旧签名 recorder 装配期报错的断言 |
|
||||||
|
|
||||||
|
**文档同步(发布前必须同批;wiki 站点自 2026-08-02 下线,按 docs-convention §2 的下线期条款,承接方为 README / CHANGELOG / .env.example / ARCHITECTURE 四处)**:
|
||||||
|
|
||||||
|
| 位置 | 改什么 |
|
||||||
|
| --- | --- |
|
||||||
|
| `README.md:23` | "必录 26 字段" → 实测值(`len(inspect.signature(TelemetryRecorder.record_llm_call).parameters) - 1`,预期 36),不凭记忆 |
|
||||||
|
| `README.md:26/399/455`、`ARCHITECTURE.md:592`、`.env.example:109` | `PGW_TELEMETRY_TEXT_CAP` 覆盖面仍是四处;明确 `error_body` 沿用 `summarize_body` 上限、`error` 的新增结构化说明另有独立限长,**二者都不在 cap 覆盖内** |
|
||||||
|
| `README.md` 能力表 + 新增小节 | 四响应的 `call_stats` 读法;设计 §8 的 SQL 迁移**五项**(失败行数改判据、`error IS NOT NULL` 不再是判据、`AVG(latency_ms)` 须按 `event_kind` 分组、费用口径不变、失败行可能带 200) |
|
||||||
|
| `ARCHITECTURE.md:565` 必录字段清单 + §7.8 补列一节 | 追加 10 列语义、`event_kind` 三态、终态行不变量 I3/I4、`operation` 与 `exc.operation` 是两个语义 |
|
||||||
|
| `CHANGELOG.md` 未发布段 | 公共面四项 + 下游动作清单(点名"计失败调用改 `WHERE event_kind = 'terminal_failure'`"与自定义 recorder 的装配期报错) |
|
||||||
|
| `research-wiki/schemas/llm-calls.md`、`metrics/call-telemetry-coverage.md` | 复用既有实体登记新列与三类行口径;真实覆盖基线待首次运行填,不写伪百分比 |
|
||||||
|
|
||||||
|
**验收命令与证据**:
|
||||||
|
|
||||||
|
| 检查 | 命令 / 要求 |
|
||||||
|
| --- | --- |
|
||||||
|
| 静态 | `make check`;`git diff --check`;`conda run -n PolyGateway python -m compileall -q src/polygateway` |
|
||||||
|
| 日常全量 | `make test`(真实退出码、coverage ≥80%,连接依赖 skip 单列) |
|
||||||
|
| 集成 | `conda run -n PolyGateway pytest tests/integration/test_postgres_telemetry.py tests/integration/test_governance_stack.py -q` |
|
||||||
|
| 契约 | `conda run -n PolyGateway pytest tests/contracts -q`(限流契约随实现一起交付的既有套件) |
|
||||||
|
| 变异 | 上表七项逐条 exit 1 → 还原 exit 0,日志留 `tests/outputs/135/` |
|
||||||
|
| 独立验证 | 由**父会话前台派全新上下文 verifier**:只给批准设计、本计划、分支 diff 与命令,不给实现自评;至少覆盖"正确性/回归"与"下游可见变化/范围"两角度,Critical/Important 清零 |
|
||||||
|
| slow | `pytest -m slow` 属发布清单第 4 步(CLAUDE §4.4.1),在合并 main 之后统一跑;**本版不新增 live 轮次、不补跑未变更的模型能力矩阵**,1.3.4 已有有效证据直接引用 |
|
||||||
|
|
||||||
|
长跑用 tmux,`PYTHONUNBUFFERED=1`,输出重定向到 `tests/outputs/135/`,命令后**不得接管道**(退出码失真),完成判定用 `wait`/PID 轮询,不用会自匹配的 `pgrep -f`。
|
||||||
|
|
||||||
|
- [ ] 提交点:`docs: document logical call telemetry and migration impact`(机械核对与存储兼容若需单独回滚点,可先提 `test: align telemetry fixtures with the 36-field recorder`,仍在 5 个提交内)
|
||||||
|
|
||||||
|
## 5. 测试矩阵 → 任务映射(设计 §9 逐族落位)
|
||||||
|
|
||||||
|
| 设计测试族 | 任务 |
|
||||||
|
| --- | --- |
|
||||||
|
| logical 计数(含空输入 0 尝试 0 行) | T1 |
|
||||||
|
| 计时(缓存/退避/准入/重问/收尾、关 recorder) | T1(快照时机的终态部分在 T3) |
|
||||||
|
| 失败与取消(三路同策略、终态 await 取消传播、非领域异常 0 行) | T3 |
|
||||||
|
| 保真诊断(529/503、空超时文案、`exc.operation`、新列四值) | T2 |
|
||||||
|
| 归因 SQL(终态 reason + 逐源现场、结构化说明无 `raw_text`) | T3 |
|
||||||
|
| 行语义(三类行 scope、至多一条终态、费用不重复、`AVG` 分组) | T2(前两项)+ T3 |
|
||||||
|
| 装配闸(旧签名报错、`**kwargs` 通过、不可 inspect) | T2 |
|
||||||
|
| 存储兼容(SQLite 新旧表、PG manual/auto、旧行 NULL、混写) | T4 |
|
||||||
|
| 变异(计数位置、上下文复制、缓存回放、提前压平、终态双计费用) | T4 |
|
||||||
|
|
||||||
|
**共享测试设施一律复用,不新建**:`tests/contracts/conftest.py:26` 与 `tests/unit/test_ocr_client.py:344` 的 `FakeClock`(注入 `now`/`sleep`,确定性计时);各测试文件既有的 `_MemoryRecorder`(`**fields`)与脚本化 MockTransport;`tmp_path` + 真实 `SQLiteRecorder(auto_migrate=...)`;`tests/integration/conftest.py` 的 PG 沙箱三件套。真实 LLM 输出如产生,按 CLAUDE §4.6 落 `tests/outputs/<module>/`。
|
||||||
|
|
||||||
|
## 6. 阻塞矩阵与发布交接
|
||||||
|
|
||||||
|
| 情形 | 本库可完成 | 不可自行宣称/处置 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| 无 PG 可用 | 单测与 SQLite 全部覆盖;PG 用例 skip 并单列 | 不得把 skip 记作通过;发布前须补跑或取人类具名豁免 |
|
||||||
|
| 下游自定义 recorder 未知 | 装配闸 + 迁移文档 + `**kwargs` 兼容路径 | 不能声称"后端完全不受影响":其 schema、INSERT 字段与契约测试仍须同步 |
|
||||||
|
| 设计外漏洞 | 独立记录实际文件与反例,交父会话核定 | 不顺手实施 #20 之外的 issue、不新增表/端口/deadline/hedging |
|
||||||
|
| 发布 | 门全绿后按 CLAUDE §4.4.1 逐步执行(文档先行 → CHANGELOG 定版 → 双处版本号 → 合并 main → `make lint`/`make test`/`pytest -m slow` → tag → 构建 → 上传 → 下载验证 → Release + 挂仓库 + 页面核对) | 本计划**不复制**该清单,也不预先勾选任何发布步骤;只 bump 版本号不叫发布 |
|
||||||
|
|
||||||
|
## 7. 自审
|
||||||
|
|
||||||
|
- 设计每节可指到任务:§3→T1、§4→T1、§5→T2/T3、§6→T3、§7→T2、§8→T4、§9→§5 映射表、§10 六项批准项全部落在 T1–T3 的公共面改动内。
|
||||||
|
- 无占位符与待定项:跨任务消费的类型(`CallStats`、`_CallContext`、`_ErrorFields`)、四个 emit 入口、两个 helper(`_assert_recorder_shape`、`emit_terminal_once`)、10 列取值表、10 列 DDL 类型均已写出可执行定义;被引用的 `PolyGatewayError`、`ResultInvalidError`、`summarize_body`、`format_bounded_errors`、`FakeClock`、`pg_sandbox` 全部指向既有实现或本计划已定义项。
|
||||||
|
- 一致性核对:`emit_terminal_failure` 去掉 `latency_ms` 后,唯一调用者是 `emit_terminal_once`;`TelemetryMW` 的终态分支删除后 chat 终态只剩客户端边界一处;`operation` 只由调用点给定,链路上无任何位置读 `exc.operation`。
|
||||||
|
- 未采纳项(异常上挂可变统计、终态搬运最后一次 attempt 的状态与正文、成功侧汇总行)理由在设计正文,本计划不复活。
|
||||||
|
- 本计划编写过程**未运行 pytest、未做变异、未调用任何模型、未提交**;T0 基线验证与其后各任务的红绿证据由执行者在自己的会话内出示。
|
||||||
@@ -1,11 +1,11 @@
|
|||||||
---
|
---
|
||||||
type: schema
|
type: schema
|
||||||
node_id: schema:llm-calls
|
node_id: schema:llm-calls
|
||||||
title: "表结构: llm_calls(遥测 26 字段)"
|
title: "表结构: llm_calls(遥测 36 字段)"
|
||||||
date: 2026-07-20
|
date: 2026-07-20
|
||||||
---
|
---
|
||||||
|
|
||||||
# 表结构: llm_calls(遥测 26 字段)
|
# 表结构: llm_calls(遥测 36 字段)
|
||||||
|
|
||||||
## 列定义(冻结,M1 设计 §4.4 / ARCH §7.8)
|
## 列定义(冻结,M1 设计 §4.4 / ARCH §7.8)
|
||||||
|
|
||||||
@@ -31,6 +31,37 @@ date: 2026-07-20
|
|||||||
| meta | TEXT / JSONB NOT NULL DEFAULT '' / '{}' | 调用方自定义维度(同批,≤16 个 KV);SQLite 存 canonical JSON 串,PG 存 JSONB |
|
| meta | TEXT / JSONB NOT NULL DEFAULT '' / '{}' | 调用方自定义维度(同批,≤16 个 KV);SQLite 存 canonical JSON 串,PG 存 JSONB |
|
||||||
| thinking_observation | TEXT | 本次推理是否真的发生的三态裁定(2026-08-25,issue #16/#17);`observed` / `absent` / `unknown`。见下方口径 |
|
| thinking_observation | TEXT | 本次推理是否真的发生的三态裁定(2026-08-25,issue #16/#17);`observed` / `absent` / `unknown`。见下方口径 |
|
||||||
| reasoning_effort | TEXT | 按四种行来源记录的推理意图/实际编码档位(2026-09-09 澄清,issue #20/#26);八档 `Effort` 字面量之一,NULL = 调用方未表态(与 `none`「明确要求不推理」不可混同)。见下方口径 |
|
| reasoning_effort | TEXT | 按四种行来源记录的推理意图/实际编码档位(2026-09-09 澄清,issue #20/#26);八档 `Effort` 字面量之一,NULL = 调用方未表态(与 `none`「明确要求不推理」不可混同)。见下方口径 |
|
||||||
|
| scope | TEXT | 池名(2026-09-09,issue #19/#23);Emitter 构造期注入,三类行都带,**不拿 `source_name` 顶替** |
|
||||||
|
| operation | TEXT | `chat` / `embed` / `recognize_text` / `parse_layout`,由调用点给定;与 `PolyGatewayError.operation` 是两个语义,链路上不得读后者填本列 |
|
||||||
|
| logical_call_id | TEXT | 一次逻辑调用一个 ID(重试/换源/重问/分批共享);上下文缺席落 NULL,**不造 ID** |
|
||||||
|
| event_kind | TEXT | 三态 `attempt` / `cache_hit` / `terminal_failure`——三类行的唯一机械判据。见下方口径 |
|
||||||
|
| http_status_code | INTEGER | 失败 attempt 行的实收状态码(中转改写过就记改写后的,**不猜回原值**);成功行与终态行恒 NULL,且 200 也可能是失败行(MonkeyOCR `success != true`) |
|
||||||
|
| error_type | TEXT | 该行自身错误的类名;取消路径传字符串故为 NULL |
|
||||||
|
| cause_type | TEXT | `__cause__` 的类名(如 `ReadTimeout`)——httpx 超时类的 `str()` 为空,只靠 error 列分不出是哪种超时;仅失败 attempt 行非空 |
|
||||||
|
| error_body | TEXT | 网关响应正文摘要(`summarize_body` 上限,**不在 `PGW_TELEMETRY_TEXT_CAP` 覆盖面内**);仅失败 attempt 行非空 |
|
||||||
|
| attempts | INTEGER | 该逻辑调用真实打出去的尝试次数(免预算 429 也计);**只属终态行** |
|
||||||
|
| total_latency_ms | INTEGER | 该逻辑调用的总墙钟(含缓存 IO、退避、准入等待、重问);**只属终态行**,与该行 `latency_ms` 同取一份冻结快照 |
|
||||||
|
|
||||||
|
## 三类行与失败归因口径(2026-09-09,issue #19/#23)
|
||||||
|
|
||||||
|
遥测行不再只有"一次尝试"一种。`event_kind` 三态同时决定其余列的取值面:
|
||||||
|
|
||||||
|
| event_kind | 什么时候写 | 列取值 |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| `attempt` | 每次真实尝试(含失败与取消) | 失败时诊断四列可非空;`attempts`/`total_latency_ms` NULL |
|
||||||
|
| `cache_hit` | 缓存命中 | 诊断四列与快照两列全 NULL |
|
||||||
|
| `terminal_failure` | 每次**领域失败**的整池终态,每逻辑调用至多一条 | `attempts`/`total_latency_ms` 非空;`http_status_code`/`cause_type`/`error_body` 恒 NULL;`cost` NULL、`usage_source='unavailable'`、token 0 |
|
||||||
|
|
||||||
|
两条不变量: 每次领域失败至多一条终态行(I3,`claim_terminal()` 去重);非领域异常(编程错)**零条**终态行、原样传播(I4)。
|
||||||
|
|
||||||
|
**终态行三列恒 NULL 是红线**: 把最后一次 attempt 的状态码与正文搬上来,等于拿最后一个源冒充整池归因。逐源现场由同一 `logical_call_id` 的 attempt 行给出:
|
||||||
|
|
||||||
|
```sql
|
||||||
|
SELECT event_kind, source_name, http_status_code, error_type, cause_type, error, error_body
|
||||||
|
FROM llm_calls WHERE logical_call_id = :lcid ORDER BY created_at;
|
||||||
|
```
|
||||||
|
|
||||||
|
下游口径迁移四条: ① 计失败调用改 `WHERE event_kind = 'terminal_failure'`;② `error IS NOT NULL` 不再是失败调用判据(跨两类行);③ `AVG(latency_ms)` 须按 `event_kind` 分组(终态行是整个逻辑调用的总耗时);④ 费用口径不变(终态行 cost 恒 NULL)。
|
||||||
|
|
||||||
## usage/成本口径(2026-07-30,est_tokens 解耦)
|
## usage/成本口径(2026-07-30,est_tokens 解耦)
|
||||||
|
|
||||||
|
|||||||
@@ -39,6 +39,7 @@ from polygateway.thinking import (
|
|||||||
)
|
)
|
||||||
from polygateway.types import (
|
from polygateway.types import (
|
||||||
EFFORT_ORDER,
|
EFFORT_ORDER,
|
||||||
|
CallStats,
|
||||||
Effort,
|
Effort,
|
||||||
EmbeddingResponse,
|
EmbeddingResponse,
|
||||||
LLMResponse,
|
LLMResponse,
|
||||||
@@ -50,13 +51,14 @@ from polygateway.types import (
|
|||||||
ThinkingObservation,
|
ThinkingObservation,
|
||||||
)
|
)
|
||||||
|
|
||||||
__version__ = "1.3.4"
|
__version__ = "1.3.5"
|
||||||
|
|
||||||
__all__ = [
|
__all__ = [
|
||||||
"DEFAULT_PROFILES",
|
"DEFAULT_PROFILES",
|
||||||
"EFFORT_ORDER",
|
"EFFORT_ORDER",
|
||||||
"Effort",
|
"Effort",
|
||||||
"AllSourcesExhausted",
|
"AllSourcesExhausted",
|
||||||
|
"CallStats",
|
||||||
"CircuitOpenError",
|
"CircuitOpenError",
|
||||||
"EmbeddingClient",
|
"EmbeddingClient",
|
||||||
"EmbeddingResponse",
|
"EmbeddingResponse",
|
||||||
|
|||||||
@@ -9,6 +9,7 @@
|
|||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
import asyncio
|
import asyncio
|
||||||
|
import dataclasses
|
||||||
import hashlib
|
import hashlib
|
||||||
import json
|
import json
|
||||||
import random
|
import random
|
||||||
@@ -19,11 +20,12 @@ from polygateway.backends.memory.breaker import InMemoryGate
|
|||||||
from polygateway.backends.memory.cache import InMemoryCache
|
from polygateway.backends.memory.cache import InMemoryCache
|
||||||
from polygateway.backends.memory.limiter import InMemoryLimiter
|
from polygateway.backends.memory.limiter import InMemoryLimiter
|
||||||
from polygateway.config import GatewaySettings
|
from polygateway.config import GatewaySettings
|
||||||
|
from polygateway.errors import PolyGatewayError
|
||||||
from polygateway.middleware.base import compose
|
from polygateway.middleware.base import compose
|
||||||
from polygateway.middleware.cache import CacheMW
|
from polygateway.middleware.cache import CacheMW
|
||||||
from polygateway.middleware.retry import RetryMW
|
from polygateway.middleware.retry import RetryMW
|
||||||
from polygateway.middleware.structured import StructuredMW
|
from polygateway.middleware.structured import StructuredMW
|
||||||
from polygateway.middleware.telemetry import TelemetryEmitter, TelemetryMW
|
from polygateway.middleware.telemetry import TelemetryEmitter, TelemetryMW, emit_terminal_once
|
||||||
from polygateway.ports import TelemetryStatusProvider
|
from polygateway.ports import TelemetryStatusProvider
|
||||||
from polygateway.pricing import PricingTable
|
from polygateway.pricing import PricingTable
|
||||||
from polygateway.providers import get_provider
|
from polygateway.providers import get_provider
|
||||||
@@ -46,6 +48,7 @@ from polygateway.types import (
|
|||||||
Effort,
|
Effort,
|
||||||
LLMResponse,
|
LLMResponse,
|
||||||
TelemetryStatus,
|
TelemetryStatus,
|
||||||
|
_CallContext,
|
||||||
coerce_effort,
|
coerce_effort,
|
||||||
validate_caller_dimensions,
|
validate_caller_dimensions,
|
||||||
validate_request_overlay,
|
validate_request_overlay,
|
||||||
@@ -237,7 +240,7 @@ class GatewayClient:
|
|||||||
rng: Any = random.random,
|
rng: Any = random.random,
|
||||||
) -> None:
|
) -> None:
|
||||||
emitter = (
|
emitter = (
|
||||||
TelemetryEmitter(telemetry, pricing=pricing, text_cap=text_cap)
|
TelemetryEmitter(telemetry, scope=scope, pricing=pricing, text_cap=text_cap)
|
||||||
if telemetry is not None
|
if telemetry is not None
|
||||||
else None
|
else None
|
||||||
)
|
)
|
||||||
@@ -289,6 +292,10 @@ class GatewayClient:
|
|||||||
self._structured_available = structured_strategy is not None
|
self._structured_available = structured_strategy is not None
|
||||||
self._terminal = terminal # 内部引用: 装配自省/测试用
|
self._terminal = terminal # 内部引用: 装配自省/测试用
|
||||||
self._handler = compose(middlewares, terminal)
|
self._handler = compose(middlewares, terminal)
|
||||||
|
# 逻辑调用统计需要同一只注入钟(1.3.5);现之前只传给中间件未自存
|
||||||
|
self._now = now
|
||||||
|
# 终态行由公开边界统一写出(T3),故边界也需持有 emitter
|
||||||
|
self._emitter = emitter
|
||||||
self._transport = transport
|
self._transport = transport
|
||||||
self._telemetry = telemetry
|
self._telemetry = telemetry
|
||||||
self._cache = cache
|
self._cache = cache
|
||||||
@@ -370,6 +377,8 @@ class GatewayClient:
|
|||||||
else coerce_effort(reasoning_effort, origin="chat(reasoning_effort=...)")
|
else coerce_effort(reasoning_effort, origin="chat(reasoning_effort=...)")
|
||||||
)
|
)
|
||||||
validate_thinking_raw(sampling, effort=effort, wire=None, origin="chat overlay")
|
validate_thinking_raw(sampling, effort=effort, wire=None, origin="chat overlay")
|
||||||
|
# 三项校验均已通过 → 进入统计边界(设计 §3: 输入校验异常在边界之外,保持原行为)
|
||||||
|
context = _CallContext(now=self._now)
|
||||||
request = ChatRequest(
|
request = ChatRequest(
|
||||||
messages=messages,
|
messages=messages,
|
||||||
session_id=session_id,
|
session_id=session_id,
|
||||||
@@ -383,8 +392,31 @@ class GatewayClient:
|
|||||||
reasoning_effort=effort,
|
reasoning_effort=effort,
|
||||||
tenant_id=dimension_tenant_id,
|
tenant_id=dimension_tenant_id,
|
||||||
meta=dimensions,
|
meta=dimensions,
|
||||||
|
call_context=context,
|
||||||
)
|
)
|
||||||
return await self._handler(request)
|
try:
|
||||||
|
response = await self._handler(request)
|
||||||
|
except PolyGatewayError as exc:
|
||||||
|
# 统计边界内的一切领域失败均尝试写一条终态行(1.3.5 设计 §6 I3),
|
||||||
|
# 包括已有 attempt 错误行的 RequestRejected / ResultInvalid——两类行描述
|
||||||
|
# 的不是同一件事(尝试 vs 逻辑终态),由 `event_kind` 区分
|
||||||
|
await emit_terminal_once(
|
||||||
|
self._emitter, request=request, context=context, error=exc, operation="chat"
|
||||||
|
)
|
||||||
|
raise
|
||||||
|
except asyncio.CancelledError:
|
||||||
|
# 尽力而为且**取消优先**: 不 shield、不开后台任务;写入那一次 await 上
|
||||||
|
# 再被取消则 `CancelledError` 照常传播(与 TelemetryMW 历史行为同款)
|
||||||
|
await emit_terminal_once(
|
||||||
|
self._emitter,
|
||||||
|
request=request,
|
||||||
|
context=context,
|
||||||
|
error="cancelled",
|
||||||
|
operation="chat",
|
||||||
|
)
|
||||||
|
raise
|
||||||
|
# 快照在返回前冻结: 故它含缓存命中路径与已完成的内联遥测耗时
|
||||||
|
return dataclasses.replace(response, call_stats=context.snapshot())
|
||||||
|
|
||||||
async def aclose(self) -> None:
|
async def aclose(self) -> None:
|
||||||
"""幂等释放**自建**资源: transport、遥测、缓存、限流/熔断后端。
|
"""幂等释放**自建**资源: transport、遥测、缓存、限流/熔断后端。
|
||||||
|
|||||||
@@ -16,6 +16,7 @@
|
|||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
import asyncio
|
import asyncio
|
||||||
|
import dataclasses
|
||||||
import math
|
import math
|
||||||
import random
|
import random
|
||||||
import time
|
import time
|
||||||
@@ -41,12 +42,13 @@ from polygateway.middleware.admission import SourceAdmission, settle_and_release
|
|||||||
from polygateway.middleware.breaker import BreakerGate
|
from polygateway.middleware.breaker import BreakerGate
|
||||||
from polygateway.middleware.ratelimit import QuotaGate
|
from polygateway.middleware.ratelimit import QuotaGate
|
||||||
from polygateway.middleware.retry import StallClock, _failure_reason, backoff_delay
|
from polygateway.middleware.retry import StallClock, _failure_reason, backoff_delay
|
||||||
from polygateway.middleware.telemetry import TelemetryEmitter
|
from polygateway.middleware.telemetry import TelemetryEmitter, emit_terminal_once
|
||||||
from polygateway.types import (
|
from polygateway.types import (
|
||||||
ChatRequest,
|
ChatRequest,
|
||||||
EmbeddingResponse,
|
EmbeddingResponse,
|
||||||
LLMResponse,
|
LLMResponse,
|
||||||
TelemetryStatus,
|
TelemetryStatus,
|
||||||
|
_CallContext,
|
||||||
strip_unsupported_extra_body,
|
strip_unsupported_extra_body,
|
||||||
validate_caller_dimensions,
|
validate_caller_dimensions,
|
||||||
)
|
)
|
||||||
@@ -127,7 +129,9 @@ class EmbeddingClient:
|
|||||||
self._transport = transport
|
self._transport = transport
|
||||||
self._retry = retry
|
self._retry = retry
|
||||||
self._emitter = (
|
self._emitter = (
|
||||||
TelemetryEmitter(telemetry, pricing=pricing, text_cap=text_cap) if telemetry else None
|
TelemetryEmitter(telemetry, scope=self._scope, pricing=pricing, text_cap=text_cap)
|
||||||
|
if telemetry
|
||||||
|
else None
|
||||||
)
|
)
|
||||||
self._telemetry = telemetry
|
self._telemetry = telemetry
|
||||||
# 限流/熔断后端在此之外只以 QuotaGate/BreakerGate 的形态存在,自持一份
|
# 限流/熔断后端在此之外只以 QuotaGate/BreakerGate 的形态存在,自持一份
|
||||||
@@ -184,7 +188,11 @@ class EmbeddingClient:
|
|||||||
dimension_tenant_id, dimensions = validate_caller_dimensions(
|
dimension_tenant_id, dimensions = validate_caller_dimensions(
|
||||||
tenant_id, meta, origin="embed(tenant_id=..., meta=...)"
|
tenant_id, meta, origin="embed(tenant_id=..., meta=...)"
|
||||||
)
|
)
|
||||||
|
# 校验均已通过 → 进入统计边界(设计 §3.5: `texts` 类型与调用方维度校验之后)
|
||||||
|
context = _CallContext(now=self._now)
|
||||||
if not texts:
|
if not texts:
|
||||||
|
# 合法零尝试: 返回真实统计(attempts=0),且**不写任何遥测行**
|
||||||
|
# ——与 cache_hit 不同,不要按"遥测必录"推断它有台账行(设计 §3 M2)
|
||||||
return EmbeddingResponse(
|
return EmbeddingResponse(
|
||||||
vectors=[],
|
vectors=[],
|
||||||
dim=0,
|
dim=0,
|
||||||
@@ -195,7 +203,40 @@ class EmbeddingClient:
|
|||||||
latency_ms=0,
|
latency_ms=0,
|
||||||
call_id=str(uuid.uuid4()),
|
call_id=str(uuid.uuid4()),
|
||||||
source_name="",
|
source_name="",
|
||||||
|
call_stats=context.snapshot(),
|
||||||
)
|
)
|
||||||
|
try:
|
||||||
|
return await self._embed_all(
|
||||||
|
texts, session_id, parent_call_id, dimension_tenant_id, dimensions, context
|
||||||
|
)
|
||||||
|
except PolyGatewayError as exc:
|
||||||
|
await self._emit_terminal(
|
||||||
|
texts, session_id, parent_call_id, dimension_tenant_id, dimensions, context, exc
|
||||||
|
)
|
||||||
|
raise
|
||||||
|
except asyncio.CancelledError:
|
||||||
|
# 三条链路同一口径尽力写一条(允许 0 条);取消优先,不 shield
|
||||||
|
await self._emit_terminal(
|
||||||
|
texts,
|
||||||
|
session_id,
|
||||||
|
parent_call_id,
|
||||||
|
dimension_tenant_id,
|
||||||
|
dimensions,
|
||||||
|
context,
|
||||||
|
"cancelled",
|
||||||
|
)
|
||||||
|
raise
|
||||||
|
|
||||||
|
async def _embed_all(
|
||||||
|
self,
|
||||||
|
texts: list[str],
|
||||||
|
session_id: str | None,
|
||||||
|
parent_call_id: str | None,
|
||||||
|
tenant_id: str | None,
|
||||||
|
meta: dict[str, Any],
|
||||||
|
context: _CallContext,
|
||||||
|
) -> EmbeddingResponse:
|
||||||
|
"""切批串行执行并合并;无源的 raise 必须在本方法内——否则无源终态行写不出。"""
|
||||||
if not self._sources:
|
if not self._sources:
|
||||||
raise AllSourcesExhausted(scope=self._scope, reason="no_sources", retry_after_s=0.0)
|
raise AllSourcesExhausted(scope=self._scope, reason="no_sources", retry_after_s=0.0)
|
||||||
outcomes = []
|
outcomes = []
|
||||||
@@ -205,11 +246,49 @@ class EmbeddingClient:
|
|||||||
texts[start : start + self._batch_size],
|
texts[start : start + self._batch_size],
|
||||||
session_id,
|
session_id,
|
||||||
parent_call_id,
|
parent_call_id,
|
||||||
dimension_tenant_id,
|
tenant_id,
|
||||||
dimensions,
|
meta,
|
||||||
|
context,
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
return self._merge(outcomes)
|
# 全批共享同一上下文,故分批是实现细节而非 N 次独立逻辑调用
|
||||||
|
return dataclasses.replace(self._merge(outcomes), call_stats=context.snapshot())
|
||||||
|
|
||||||
|
async def _emit_terminal(
|
||||||
|
self,
|
||||||
|
texts: list[str],
|
||||||
|
session_id: str | None,
|
||||||
|
parent_call_id: str | None,
|
||||||
|
tenant_id: str | None,
|
||||||
|
meta: dict[str, Any],
|
||||||
|
context: _CallContext,
|
||||||
|
error: PolyGatewayError | str,
|
||||||
|
) -> None:
|
||||||
|
"""终态行的请求摘要(设计 §6 M4): 计数占位 + 第一批截断文本。
|
||||||
|
|
||||||
|
描述的是**本次调用的整体输入**但不扩大单行正文预算: 失败批的具体文本由同
|
||||||
|
`logical_call_id` 的 attempt 行给出,终态行不保存全量原输入。
|
||||||
|
"""
|
||||||
|
batches = math.ceil(len(texts) / self._batch_size)
|
||||||
|
messages = [{"role": "user", "content": f"<embed texts={len(texts)} batches={batches}>"}]
|
||||||
|
# 与逐批行同款构造(至多 `batch_size` 条、每条 200 字符)
|
||||||
|
messages += [
|
||||||
|
{"role": "user", "content": t[:_TELEMETRY_TEXT_CAP]} for t in texts[: self._batch_size]
|
||||||
|
]
|
||||||
|
await emit_terminal_once(
|
||||||
|
self._emitter,
|
||||||
|
request=ChatRequest(
|
||||||
|
messages=messages,
|
||||||
|
session_id=session_id,
|
||||||
|
parent_call_id=parent_call_id,
|
||||||
|
tenant_id=tenant_id,
|
||||||
|
meta=meta,
|
||||||
|
call_context=context,
|
||||||
|
),
|
||||||
|
context=context,
|
||||||
|
error=error,
|
||||||
|
operation="embed",
|
||||||
|
)
|
||||||
|
|
||||||
# —— 治理循环(与 RetryMW 同构;设计 §7.1 已声明的有限重复)——
|
# —— 治理循环(与 RetryMW 同构;设计 §7.1 已声明的有限重复)——
|
||||||
|
|
||||||
@@ -220,6 +299,7 @@ class EmbeddingClient:
|
|||||||
parent_call_id: str | None,
|
parent_call_id: str | None,
|
||||||
tenant_id: str | None,
|
tenant_id: str | None,
|
||||||
meta: dict[str, Any],
|
meta: dict[str, Any],
|
||||||
|
context: _CallContext,
|
||||||
) -> _BatchOutcome:
|
) -> _BatchOutcome:
|
||||||
fails = 0
|
fails = 0
|
||||||
reasons: dict[str, str] = {}
|
reasons: dict[str, str] = {}
|
||||||
@@ -232,7 +312,7 @@ class EmbeddingClient:
|
|||||||
continue
|
continue
|
||||||
async with clock.attempting():
|
async with clock.attempting():
|
||||||
outcome = await self._attempt(
|
outcome = await self._attempt(
|
||||||
batch, *picked, reasons, session_id, parent_call_id, tenant_id, meta
|
batch, *picked, reasons, session_id, parent_call_id, tenant_id, meta, context
|
||||||
)
|
)
|
||||||
if isinstance(outcome, _BatchOutcome):
|
if isinstance(outcome, _BatchOutcome):
|
||||||
return outcome
|
return outcome
|
||||||
@@ -258,10 +338,13 @@ class EmbeddingClient:
|
|||||||
parent_call_id: str | None,
|
parent_call_id: str | None,
|
||||||
tenant_id: str | None,
|
tenant_id: str | None,
|
||||||
meta: dict[str, Any],
|
meta: dict[str, Any],
|
||||||
|
context: _CallContext,
|
||||||
) -> _BatchOutcome | _FailedBatch:
|
) -> _BatchOutcome | _FailedBatch:
|
||||||
call_id = str(uuid.uuid4())
|
call_id = str(uuid.uuid4())
|
||||||
started = self._now()
|
started = self._now()
|
||||||
actual = 0
|
actual = 0
|
||||||
|
# 登记在 transport 调用**之前**(同 RetryMW): 失败与取消的尝试也真的发出去了
|
||||||
|
context.register_attempt()
|
||||||
try:
|
try:
|
||||||
result = await self._transport.embed(texts=batch, source=source, call_id=call_id)
|
result = await self._transport.embed(texts=batch, source=source, call_id=call_id)
|
||||||
if self._expected_dim is not None and result.dim != self._expected_dim:
|
if self._expected_dim is not None and result.dim != self._expected_dim:
|
||||||
@@ -287,6 +370,7 @@ class EmbeddingClient:
|
|||||||
parent_call_id,
|
parent_call_id,
|
||||||
tenant_id,
|
tenant_id,
|
||||||
meta,
|
meta,
|
||||||
|
context,
|
||||||
result,
|
result,
|
||||||
)
|
)
|
||||||
return _BatchOutcome(result, source, call_id, latency_ms)
|
return _BatchOutcome(result, source, call_id, latency_ms)
|
||||||
@@ -301,6 +385,7 @@ class EmbeddingClient:
|
|||||||
parent_call_id,
|
parent_call_id,
|
||||||
tenant_id,
|
tenant_id,
|
||||||
meta,
|
meta,
|
||||||
|
context,
|
||||||
error=exc,
|
error=exc,
|
||||||
)
|
)
|
||||||
raise
|
raise
|
||||||
@@ -316,6 +401,7 @@ class EmbeddingClient:
|
|||||||
parent_call_id,
|
parent_call_id,
|
||||||
tenant_id,
|
tenant_id,
|
||||||
meta,
|
meta,
|
||||||
|
context,
|
||||||
error="cancelled",
|
error="cancelled",
|
||||||
)
|
)
|
||||||
raise
|
raise
|
||||||
@@ -336,6 +422,7 @@ class EmbeddingClient:
|
|||||||
parent_call_id,
|
parent_call_id,
|
||||||
tenant_id,
|
tenant_id,
|
||||||
meta,
|
meta,
|
||||||
|
context,
|
||||||
error=exc,
|
error=exc,
|
||||||
)
|
)
|
||||||
return _FailedBatch(exc, immediate=dead)
|
return _FailedBatch(exc, immediate=dead)
|
||||||
@@ -372,8 +459,9 @@ class EmbeddingClient:
|
|||||||
parent_call_id: str | None,
|
parent_call_id: str | None,
|
||||||
tenant_id: str | None,
|
tenant_id: str | None,
|
||||||
meta: dict[str, Any],
|
meta: dict[str, Any],
|
||||||
|
context: _CallContext,
|
||||||
result: EmbeddingTransportResult | None = None,
|
result: EmbeddingTransportResult | None = None,
|
||||||
error: object | None = None,
|
error: PolyGatewayError | str | None = None,
|
||||||
) -> None:
|
) -> None:
|
||||||
"""逐批遥测(经同一 Emitter): messages=截断 texts、向量绝不入库。"""
|
"""逐批遥测(经同一 Emitter): messages=截断 texts、向量绝不入库。"""
|
||||||
if self._emitter is None:
|
if self._emitter is None:
|
||||||
@@ -386,6 +474,7 @@ class EmbeddingClient:
|
|||||||
parent_call_id=parent_call_id,
|
parent_call_id=parent_call_id,
|
||||||
tenant_id=tenant_id,
|
tenant_id=tenant_id,
|
||||||
meta=meta,
|
meta=meta,
|
||||||
|
call_context=context,
|
||||||
)
|
)
|
||||||
response = None
|
response = None
|
||||||
if result is not None:
|
if result is not None:
|
||||||
@@ -410,10 +499,12 @@ class EmbeddingClient:
|
|||||||
call_id=call_id,
|
call_id=call_id,
|
||||||
latency_ms=int((self._now() - started) * 1000),
|
latency_ms=int((self._now() - started) * 1000),
|
||||||
response=response,
|
response=response,
|
||||||
error=None if error is None else str(error),
|
# 异常对象原样下传: 状态码/底层异常类型/网关正文在 Emitter 内定型
|
||||||
|
error=error,
|
||||||
# embedding payload 硬编码 {model, input},从不带推理参数;源上即便
|
# embedding payload 硬编码 {model, input},从不带推理参数;源上即便
|
||||||
# 误配了 ENABLE_THINKING,记一个档也是替这次调用声称它没做过的事
|
# 误配了 ENABLE_THINKING,记一个档也是替这次调用声称它没做过的事
|
||||||
reasoning_applies=False,
|
reasoning_applies=False,
|
||||||
|
operation="embed",
|
||||||
)
|
)
|
||||||
|
|
||||||
def _merge(self, outcomes: list[_BatchOutcome]) -> EmbeddingResponse:
|
def _merge(self, outcomes: list[_BatchOutcome]) -> EmbeddingResponse:
|
||||||
|
|||||||
@@ -208,6 +208,10 @@ class CacheMW:
|
|||||||
max_inter_token_ms=None,
|
max_inter_token_ms=None,
|
||||||
call_id=str(uuid.uuid4()),
|
call_id=str(uuid.uuid4()),
|
||||||
structured_data=structured_data,
|
structured_data=structured_data,
|
||||||
|
# 显式覆盖: 历史条目里的 `call_stats` 是个 dict,而 `_RESPONSE_FIELDS`
|
||||||
|
# 过滤**会放行它**——不覆盖就会有 dict 冒充 `CallStats` 漏给调用方。
|
||||||
|
# 本次调用的真实统计由公开边界在返回前追加(设计 §3)
|
||||||
|
call_stats=None,
|
||||||
)
|
)
|
||||||
return LLMResponse(**fields)
|
return LLMResponse(**fields)
|
||||||
except Exception as exc:
|
except Exception as exc:
|
||||||
@@ -230,6 +234,9 @@ class CacheMW:
|
|||||||
def _serialize(self, response: LLMResponse) -> str:
|
def _serialize(self, response: LLMResponse) -> str:
|
||||||
data = dataclasses.asdict(response)
|
data = dataclasses.asdict(response)
|
||||||
data.pop("structured_data", None) # pydantic 实例不可 JSON 往返(设计 §2.1)
|
data.pop("structured_data", None) # pydantic 实例不可 JSON 往返(设计 §2.1)
|
||||||
|
# 统计描述**本次**调用,存进去再放出来等于向下一个调用方谎称
|
||||||
|
# 它重试了 N 次;`asdict` 会把 `CallStats` 摊成 dict,故必须显式剔除
|
||||||
|
data.pop("call_stats", None)
|
||||||
return json.dumps(data, ensure_ascii=False)
|
return json.dumps(data, ensure_ascii=False)
|
||||||
|
|
||||||
async def _safe_get(self, key: str) -> str | None:
|
async def _safe_get(self, key: str) -> str | None:
|
||||||
|
|||||||
@@ -42,6 +42,7 @@ from polygateway.types import LLMResponse
|
|||||||
if TYPE_CHECKING:
|
if TYPE_CHECKING:
|
||||||
from collections.abc import AsyncIterator, Awaitable, Callable
|
from collections.abc import AsyncIterator, Awaitable, Callable
|
||||||
|
|
||||||
|
from polygateway.middleware.telemetry import TelemetryEmitter
|
||||||
from polygateway.ports import (
|
from polygateway.ports import (
|
||||||
GateDecision,
|
GateDecision,
|
||||||
Permit,
|
Permit,
|
||||||
@@ -181,7 +182,7 @@ class RetryMW:
|
|||||||
circuit_open: str = "fail_fast",
|
circuit_open: str = "fail_fast",
|
||||||
cooldown_memo: SourceCooldownMemo | None = None,
|
cooldown_memo: SourceCooldownMemo | None = None,
|
||||||
pacer: AdaptivePacer | None = None,
|
pacer: AdaptivePacer | None = None,
|
||||||
emitter: object | None = None,
|
emitter: TelemetryEmitter | None = None,
|
||||||
now: Callable[[], float] = time.monotonic,
|
now: Callable[[], float] = time.monotonic,
|
||||||
sleep: Callable[[float], Awaitable[None]] = asyncio.sleep,
|
sleep: Callable[[float], Awaitable[None]] = asyncio.sleep,
|
||||||
rng: Callable[[], float] = random.random,
|
rng: Callable[[], float] = random.random,
|
||||||
@@ -278,6 +279,11 @@ class RetryMW:
|
|||||||
call_id = str(uuid.uuid4())
|
call_id = str(uuid.uuid4())
|
||||||
started = self._now()
|
started = self._now()
|
||||||
actual = 0
|
actual = 0
|
||||||
|
# 登记在 transport 调用**之前**(1.3.5 设计 §4): 失败与取消的尝试同样
|
||||||
|
# "真的打出去了",挪到成功之后会让诊断最需要看见的那几次从计数里消失。
|
||||||
|
# 上下文为 None = 库内现场构造的请求,跳过而不是报错
|
||||||
|
if request.call_context is not None:
|
||||||
|
request.call_context.register_attempt()
|
||||||
try:
|
try:
|
||||||
result = await self._transport.complete(
|
result = await self._transport.complete(
|
||||||
messages=request.messages,
|
messages=request.messages,
|
||||||
@@ -408,9 +414,13 @@ class RetryMW:
|
|||||||
started: float,
|
started: float,
|
||||||
*,
|
*,
|
||||||
response: LLMResponse | None = None,
|
response: LLMResponse | None = None,
|
||||||
error: object | None = None,
|
error: PolyGatewayError | str | None = None,
|
||||||
) -> None:
|
) -> None:
|
||||||
"""逐次遥测(经注入的单一 Emitter);遥测失败不得影响调用(铁律)。"""
|
"""逐次遥测(经注入的单一 Emitter);遥测失败不得影响调用(铁律)。
|
||||||
|
|
||||||
|
异常**对象原样下传**而非先 `str()` 压平(1.3.5 设计 §5): 状态码、底层异常
|
||||||
|
类型与网关响应体已经在异常上了,在这里压平就是把它们丢掉。
|
||||||
|
"""
|
||||||
if self._emitter is None:
|
if self._emitter is None:
|
||||||
return
|
return
|
||||||
try:
|
try:
|
||||||
@@ -420,9 +430,11 @@ class RetryMW:
|
|||||||
call_id=call_id,
|
call_id=call_id,
|
||||||
latency_ms=int((self._now() - started) * 1000),
|
latency_ms=int((self._now() - started) * 1000),
|
||||||
response=response,
|
response=response,
|
||||||
error=None if error is None else str(error),
|
error=error,
|
||||||
# chat 路径是唯一带推理参数的路径,故实发档由这里的响应说了算
|
# chat 路径是唯一带推理参数的路径,故实发档由这里的响应说了算
|
||||||
reasoning_applies=True,
|
reasoning_applies=True,
|
||||||
|
# 公开方法四值之一;本中间件只服务 chat 洋葱
|
||||||
|
operation="chat",
|
||||||
)
|
)
|
||||||
except asyncio.CancelledError:
|
except asyncio.CancelledError:
|
||||||
raise
|
raise
|
||||||
|
|||||||
@@ -14,6 +14,8 @@ from typing import TYPE_CHECKING
|
|||||||
from polygateway.errors import ResultInvalidError
|
from polygateway.errors import ResultInvalidError
|
||||||
|
|
||||||
if TYPE_CHECKING:
|
if TYPE_CHECKING:
|
||||||
|
from collections.abc import Sequence
|
||||||
|
|
||||||
from polygateway.ports import CallNext, StructuredOutputStrategy
|
from polygateway.ports import CallNext, StructuredOutputStrategy
|
||||||
from polygateway.types import ChatRequest, LLMResponse
|
from polygateway.types import ChatRequest, LLMResponse
|
||||||
|
|
||||||
@@ -22,12 +24,18 @@ _FEEDBACK_TEMPLATE = (
|
|||||||
"Your previous reply was not valid JSON matching the required schema. "
|
"Your previous reply was not valid JSON matching the required schema. "
|
||||||
"Errors: {errors}. Reply with ONLY the corrected JSON object."
|
"Errors: {errors}. Reply with ONLY the corrected JSON object."
|
||||||
)
|
)
|
||||||
_MAX_FEEDBACK_ERRORS = 3
|
MAX_FEEDBACK_ERRORS = 3
|
||||||
_MAX_ERROR_CHARS = 200
|
MAX_ERROR_CHARS = 200
|
||||||
|
|
||||||
|
|
||||||
def _format_errors(errors: list[str]) -> str:
|
def format_bounded_errors(errors: Sequence[str]) -> str:
|
||||||
clipped = [e[:_MAX_ERROR_CHARS] for e in errors[:_MAX_FEEDBACK_ERRORS]]
|
"""校验错误的有界拼装: 至多 3 条 × 每条 200 字符。
|
||||||
|
|
||||||
|
**本模块是这条规则的所有者**: 重问反馈文案与 1.3.5 终态行的结构化说明
|
||||||
|
两个消费者共用同一份实现与同一组数值——数值复制成两份必然漂移,而漂移后
|
||||||
|
"模型看到的错误"与"台账里记的错误"就不再是同一件事。行为与重命名前逐字相同。
|
||||||
|
"""
|
||||||
|
clipped = [e[:MAX_ERROR_CHARS] for e in list(errors)[:MAX_FEEDBACK_ERRORS]]
|
||||||
return "; ".join(clipped) if clipped else "output could not be parsed"
|
return "; ".join(clipped) if clipped else "output could not be parsed"
|
||||||
|
|
||||||
|
|
||||||
@@ -104,7 +112,10 @@ class StructuredMW:
|
|||||||
messages = [
|
messages = [
|
||||||
*current.messages,
|
*current.messages,
|
||||||
{"role": "assistant", "content": bad_content},
|
{"role": "assistant", "content": bad_content},
|
||||||
{"role": "user", "content": _FEEDBACK_TEMPLATE.format(errors=_format_errors(errors))},
|
{
|
||||||
|
"role": "user",
|
||||||
|
"content": _FEEDBACK_TEMPLATE.format(errors=format_bounded_errors(errors)),
|
||||||
|
},
|
||||||
]
|
]
|
||||||
reask = dataclasses.replace(current, messages=messages)
|
reask = dataclasses.replace(current, messages=messages)
|
||||||
if self._escalation is not None:
|
if self._escalation is not None:
|
||||||
|
|||||||
@@ -2,13 +2,19 @@
|
|||||||
|
|
||||||
Emitter 是全库**唯一**调用 `record_llm_call` 的地方(三项目 4 处逐字复制
|
Emitter 是全库**唯一**调用 `record_llm_call` 的地方(三项目 4 处逐字复制
|
||||||
15 参调用的教训)。分工: RetryMW 经 Emitter 逐次记录每次尝试;TelemetryMW
|
15 参调用的教训)。分工: RetryMW 经 Emitter 逐次记录每次尝试;TelemetryMW
|
||||||
(最外层)只记尝试层看不见的事件——缓存命中、scope 级失败、取消;
|
(最外层)只记尝试层看不见的缓存命中;而**终态失败行**由三个 client 的公开
|
||||||
RequestRejected/ResultInvalid 已被尝试层记录,最外层放行不重复记。
|
边界经 `emit_terminal_once` 统一写出(1.3.5)——两处同时写就会双计。
|
||||||
|
|
||||||
|
一行遥测属于三类事件之一(`event_kind`): `attempt`(一次尝试)、`cache_hit`
|
||||||
|
(未产生网关调用)、`terminal_failure`(一次**逻辑调用**的失败终态)。后两者与
|
||||||
|
前者**不是重复事实**,故统计失败调用次数只能取 `terminal_failure`,
|
||||||
|
不得按 `error IS NOT NULL` 跨两类直接计数(设计 §6/§8)。
|
||||||
"""
|
"""
|
||||||
|
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
import asyncio
|
import asyncio
|
||||||
|
import inspect
|
||||||
import json
|
import json
|
||||||
import time
|
import time
|
||||||
import uuid
|
import uuid
|
||||||
@@ -17,12 +23,10 @@ from typing import TYPE_CHECKING
|
|||||||
|
|
||||||
from loguru import logger
|
from loguru import logger
|
||||||
|
|
||||||
from polygateway.errors import (
|
from polygateway.errors import PolyGatewayError, ResultInvalidError
|
||||||
GatewayUnavailableError,
|
|
||||||
GovernanceBackendError,
|
|
||||||
SourceNotConfiguredError,
|
|
||||||
)
|
|
||||||
from polygateway.middleware.cache import digest_messages
|
from polygateway.middleware.cache import digest_messages
|
||||||
|
from polygateway.middleware.structured import MAX_ERROR_CHARS, format_bounded_errors
|
||||||
|
from polygateway.ports import TelemetryRecorder
|
||||||
from polygateway.thinking import effective_effort
|
from polygateway.thinking import effective_effort
|
||||||
from polygateway.types import Effort, ThinkingObservation, canonical_sampling_json, merge_sampling
|
from polygateway.types import Effort, ThinkingObservation, canonical_sampling_json, merge_sampling
|
||||||
|
|
||||||
@@ -30,9 +34,17 @@ if TYPE_CHECKING:
|
|||||||
from collections.abc import Callable, Mapping
|
from collections.abc import Callable, Mapping
|
||||||
from typing import Any
|
from typing import Any
|
||||||
|
|
||||||
from polygateway.ports import CallNext, TelemetryRecorder
|
from polygateway.ports import CallNext
|
||||||
from polygateway.pricing import PricingTable
|
from polygateway.pricing import PricingTable
|
||||||
from polygateway.types import ChatRequest, LLMResponse, SourceConfig
|
from polygateway.types import (
|
||||||
|
CallOperation,
|
||||||
|
CallStats,
|
||||||
|
ChatRequest,
|
||||||
|
EventKind,
|
||||||
|
LLMResponse,
|
||||||
|
SourceConfig,
|
||||||
|
_CallContext,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
def _canonical_meta_json(meta: Mapping[str, Any]) -> str:
|
def _canonical_meta_json(meta: Mapping[str, Any]) -> str:
|
||||||
@@ -225,26 +237,159 @@ class _AttemptUsage:
|
|||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class _ErrorFields:
|
||||||
|
"""一行遥测的错误列;未知一律 `None`。
|
||||||
|
|
||||||
|
存在的理由是把"三种入参形态 × 两类行"的定型规则收敛到**一处**:
|
||||||
|
改前调用方先 `str(exc)` 压平,状态码、底层异常类型与网关正文全部丢失。
|
||||||
|
"""
|
||||||
|
|
||||||
|
error: str | None = None
|
||||||
|
error_type: str | None = None
|
||||||
|
cause_type: str | None = None
|
||||||
|
http_status_code: int | None = None
|
||||||
|
error_body: str | None = None
|
||||||
|
|
||||||
|
|
||||||
|
def _structured_detail(exc: ResultInvalidError) -> str:
|
||||||
|
"""结构化阶梯耗尽的**有界**说明(设计 §5 C2)。
|
||||||
|
|
||||||
|
`ResultInvalidError("结构化输出阶梯耗尽")` 的 message 不含校验与修复错误,而该
|
||||||
|
失败发生在 StructuredMW 之上——RetryMW 侧的 attempt 行全是**成功行**,终态行是
|
||||||
|
唯一记录。故把说明并入现有 `error` 串。
|
||||||
|
|
||||||
|
**不含 `raw_text`**: 它是模型正文,attempt 行的 `response` 列已按 `text_cap` 记过
|
||||||
|
一份;再存一份等于绕过既有的正文预算。条数与限长复用 `structured.py` 的同一
|
||||||
|
套常量(重问反馈与本说明同一口径),数值只有一份。
|
||||||
|
"""
|
||||||
|
parts: list[str] = []
|
||||||
|
if exc.repair_error:
|
||||||
|
parts.append(f"repair={exc.repair_error[:MAX_ERROR_CHARS]}")
|
||||||
|
if exc.validation_errors:
|
||||||
|
parts.append(f"validation={format_bounded_errors(exc.validation_errors)}")
|
||||||
|
return " | ".join(parts)
|
||||||
|
|
||||||
|
|
||||||
|
def _error_fields(
|
||||||
|
error: PolyGatewayError | str | None,
|
||||||
|
*,
|
||||||
|
event_kind: EventKind,
|
||||||
|
class_prefixed: bool,
|
||||||
|
) -> _ErrorFields:
|
||||||
|
"""三种入参形态的唯一定型点(设计 §5/§6)。
|
||||||
|
|
||||||
|
- `None` → 全 None(成功行不统一填 200: 那会让"有状态码"不再等价于"失败了")。
|
||||||
|
- `str`(取消路径的 `"cancelled"`)→ 原样落 `error`,**不解析字符串猜诊断**。
|
||||||
|
- 领域异常 → 只读它既有的属性,不遍历任意对象、不猜正文。
|
||||||
|
|
||||||
|
**终态行的三列恒为 NULL(C1 红线)**: `GatewayUnavailableError` 家族从不携带
|
||||||
|
状态码与响应体,NULL 正是它自身的真实状态——把最后一次 attempt 的状态码与正文
|
||||||
|
搬上来,就是拿最后一个源冒充整池归因。逐源现场由同一 `logical_call_id` 的
|
||||||
|
attempt 行给出。
|
||||||
|
"""
|
||||||
|
if error is None:
|
||||||
|
return _ErrorFields()
|
||||||
|
if isinstance(error, str):
|
||||||
|
return _ErrorFields(error=error)
|
||||||
|
name = type(error).__name__
|
||||||
|
# 空 `str()` 退回类名(httpx 的 Connect/Read/Write/PoolTimeout 文案就是空的);
|
||||||
|
# `class_prefixed` 是 OCR 的既有口径(按类名归组的 metric),故逐字保留它的拼法
|
||||||
|
text = f"{name}: {error}" if class_prefixed else (str(error) or name)
|
||||||
|
if event_kind == "terminal_failure":
|
||||||
|
if isinstance(error, ResultInvalidError):
|
||||||
|
detail = _structured_detail(error)
|
||||||
|
if detail:
|
||||||
|
text = f"{text} | {detail}"
|
||||||
|
return _ErrorFields(error=text, error_type=name)
|
||||||
|
cause = error.__cause__
|
||||||
|
return _ErrorFields(
|
||||||
|
error=text,
|
||||||
|
error_type=name,
|
||||||
|
cause_type=type(cause).__name__ if cause is not None else None,
|
||||||
|
# getattr 而非直读: 本函数在 `_record` 的降级 try **之外**求值,
|
||||||
|
# 一个非领域异常误传进来不得把一次真实失败换成 AttributeError
|
||||||
|
http_status_code=getattr(error, "status_code", None),
|
||||||
|
# 空串归 None: 既有 `body_text` 的缺省就是空串,而本列的语义是"未知"
|
||||||
|
error_body=getattr(error, "body_text", "") or None,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def _assert_recorder_shape(recorder: TelemetryRecorder) -> None:
|
||||||
|
"""装配期一次 `signature.bind` 形状校验: 不执行写入,只证明该形状能被接受。
|
||||||
|
|
||||||
|
`_record` 的 `except Exception` 会把旧 recorder 的 `TypeError` 吞成 warning,
|
||||||
|
后果是自定义 recorder 在下游升级后**100% 丢遥测且调用照常成功**——正是
|
||||||
|
"遥测必录"要防的形态,而文档级迁移清单挡不住它。故在装配期当场报错
|
||||||
|
(不是 warning: 降级方向的铁律管的是**运行期写失败**,不是装配错误)。
|
||||||
|
|
||||||
|
参数名从 `TelemetryRecorder.record_llm_call` 的协议签名**派生**(不手抄第四份
|
||||||
|
字段清单),绑定用哨兵 `None`,不读任何真实请求数据;`**kwargs`
|
||||||
|
(VAR_KEYWORD)自动通过。不可 inspect(C 实现等)同样按配置错误报错——宁可
|
||||||
|
装配不起来,不进入"运行期静默丢行"。
|
||||||
|
|
||||||
|
边界诚实声明: 它只证明该形状能被接受,**不能证明函数体真的落这些列**。
|
||||||
|
|
||||||
|
Raises:
|
||||||
|
ValueError: 签名不符、不可 inspect,或协议本身不可 inspect。
|
||||||
|
"""
|
||||||
|
try:
|
||||||
|
# 模块全局查找而非常量快照: 协议改了,闸就跟着改(测试可据此机械验证)
|
||||||
|
protocol = inspect.signature(TelemetryRecorder.record_llm_call).parameters
|
||||||
|
except (TypeError, ValueError) as exc: # pragma: no cover - 协议一向可 inspect
|
||||||
|
raise ValueError(f"TelemetryRecorder.record_llm_call 签名不可读取: {exc}") from exc
|
||||||
|
sentinels = {name: None for name in protocol if name != "self"}
|
||||||
|
label = type(recorder).__name__
|
||||||
|
method = getattr(recorder, "record_llm_call", None)
|
||||||
|
if method is None:
|
||||||
|
# 连方法都没有: 比旧签名更明确的配置错误。不让它以裸 AttributeError
|
||||||
|
# 逆流而上——那不属错误四分类,且现场离"注错了东西"这个真因很远
|
||||||
|
raise ValueError(
|
||||||
|
f"注入的遥测 recorder {label} 没有 record_llm_call 方法,不满足 TelemetryRecorder 端口"
|
||||||
|
)
|
||||||
|
try:
|
||||||
|
signature = inspect.signature(method)
|
||||||
|
except (TypeError, ValueError) as exc:
|
||||||
|
raise ValueError(
|
||||||
|
f"遥测 recorder {label} 的 record_llm_call 不可 inspect(如 C 实现),"
|
||||||
|
"无法在装配期确认它接受当前字段形状;请换成 Python 实现或包一层"
|
||||||
|
) from exc
|
||||||
|
try:
|
||||||
|
signature.bind(**sentinels)
|
||||||
|
except TypeError as exc:
|
||||||
|
raise ValueError(
|
||||||
|
f"遥测 recorder {label} 的 record_llm_call 签名与 TelemetryRecorder 不符"
|
||||||
|
f"(当前 {len(sentinels)} 个字段): {exc}。"
|
||||||
|
"这一条故意在装配期报错——放行的后果是每行遥测都被降级成 warning 后丢弃"
|
||||||
|
) from exc
|
||||||
|
|
||||||
|
|
||||||
class TelemetryEmitter:
|
class TelemetryEmitter:
|
||||||
"""从请求与结果组装 26 字段并写入 recorder;一切写失败降级 warning。"""
|
"""从请求与结果组装 36 字段并写入 recorder;一切写失败降级 warning。"""
|
||||||
|
|
||||||
def __init__(
|
def __init__(
|
||||||
self,
|
self,
|
||||||
recorder: TelemetryRecorder,
|
recorder: TelemetryRecorder,
|
||||||
*,
|
*,
|
||||||
|
scope: str,
|
||||||
pricing: PricingTable | None = None,
|
pricing: PricingTable | None = None,
|
||||||
text_cap: int | None,
|
text_cap: int | None,
|
||||||
) -> None:
|
) -> None:
|
||||||
"""`text_cap` 无默认值是有意的: 它是关键行为参数,漏传即静默改变落库正文。
|
"""`text_cap` 与 `scope` 无默认值是有意的: 两者都是关键行为参数。
|
||||||
|
|
||||||
|
`text_cap` 漏传即静默改变落库正文;`scope` 漏传则三类行都失去池名
|
||||||
|
——终态失败可能根本没选出源,但 scope 始终已知,不拿 `source_name` 顶替。
|
||||||
本类是库内部类,唯一构造者是三个公共 Client,必填能保证没有一处漏传。
|
本类是库内部类,唯一构造者是三个公共 Client,必填能保证没有一处漏传。
|
||||||
同理,值域校验也放在这一处: 三个 Client 的 `text_cap` 全部汇流到这里,
|
|
||||||
|
同理,值域校验与**装配闸**都放在这一处: 三个 Client 全部汇流到这里,
|
||||||
`GatewaySettings` 那道只管 env 一条路,而直接构造 Client 是库承诺的另一
|
`GatewaySettings` 那道只管 env 一条路,而直接构造 Client 是库承诺的另一
|
||||||
条公共装配路——`text_cap=0` 会让每条正文只剩一个省略标记(P5 不得静默)。
|
条公共装配路(`text_cap=0` 会让每条正文只剩一个省略标记;P5 不得静默)。
|
||||||
"""
|
"""
|
||||||
if text_cap is not None and text_cap <= 0:
|
if text_cap is not None and text_cap <= 0:
|
||||||
raise ValueError(f"text_cap 必须 > 0(不截断请传 None): {text_cap}")
|
raise ValueError(f"text_cap 必须 > 0(不截断请传 None): {text_cap}")
|
||||||
|
_assert_recorder_shape(recorder)
|
||||||
self._recorder = recorder
|
self._recorder = recorder
|
||||||
|
self._scope = scope
|
||||||
self._pricing = pricing
|
self._pricing = pricing
|
||||||
self._text_cap = text_cap
|
self._text_cap = text_cap
|
||||||
|
|
||||||
@@ -256,8 +401,10 @@ class TelemetryEmitter:
|
|||||||
call_id: str,
|
call_id: str,
|
||||||
latency_ms: int,
|
latency_ms: int,
|
||||||
response: LLMResponse | None,
|
response: LLMResponse | None,
|
||||||
error: str | None,
|
error: PolyGatewayError | str | None,
|
||||||
reasoning_applies: bool,
|
reasoning_applies: bool,
|
||||||
|
operation: CallOperation,
|
||||||
|
class_prefixed_error: bool = False,
|
||||||
) -> None:
|
) -> None:
|
||||||
"""逐次尝试记录(三个 Client 的重试层调用);失败尝试无用量可言,记 0 并标 unavailable。
|
"""逐次尝试记录(三个 Client 的重试层调用);失败尝试无用量可言,记 0 并标 unavailable。
|
||||||
|
|
||||||
@@ -266,7 +413,11 @@ class TelemetryEmitter:
|
|||||||
共用同一个 `SourceConfig` 类型,一个误配了 `ENABLE_THINKING` 的 embedding 源
|
共用同一个 `SourceConfig` 类型,一个误配了 `ENABLE_THINKING` 的 embedding 源
|
||||||
会让下面的回落算出 `auto`,给一次从来不带推理参数的调用挂上一个从未发出过的
|
会让下面的回落算出 `auto`,给一次从来不带推理参数的调用挂上一个从未发出过的
|
||||||
档。**不设默认值**: 与 `TelemetryRecorder` 同一约定,库外无第三方调用者,漏传
|
档。**不设默认值**: 与 `TelemetryRecorder` 同一约定,库外无第三方调用者,漏传
|
||||||
当场 TypeError,好过被静默当成"没表态"。
|
当场 TypeError,好过被静默当成"没表态"。`operation` 同理且另有一层:
|
||||||
|
它只能由调用点给定,**绝不读 `exc.operation`**(后者是 HTTP 子操作)。
|
||||||
|
|
||||||
|
`error` 收**领域异常对象**而非预先 `str()` 压平的文本: 状态码/底层异常类型/
|
||||||
|
网关正文在此提取成四列(设计 §5)。取消路径仍传既有字符串 `"cancelled"`。
|
||||||
"""
|
"""
|
||||||
usage = _AttemptUsage.of(response)
|
usage = _AttemptUsage.of(response)
|
||||||
await self._record(
|
await self._record(
|
||||||
@@ -284,7 +435,7 @@ class TelemetryEmitter:
|
|||||||
ttft_ms=usage.ttft_ms,
|
ttft_ms=usage.ttft_ms,
|
||||||
max_inter_token_ms=usage.max_inter_token_ms,
|
max_inter_token_ms=usage.max_inter_token_ms,
|
||||||
cache_hit=False,
|
cache_hit=False,
|
||||||
error=error,
|
errors=_error_fields(error, event_kind="attempt", class_prefixed=class_prefixed_error),
|
||||||
cached_prompt_tokens=usage.cached_prompt_tokens,
|
cached_prompt_tokens=usage.cached_prompt_tokens,
|
||||||
model_reported=usage.model_reported,
|
model_reported=usage.model_reported,
|
||||||
reasoning_tokens=usage.reasoning_tokens,
|
reasoning_tokens=usage.reasoning_tokens,
|
||||||
@@ -296,10 +447,19 @@ class TelemetryEmitter:
|
|||||||
reasoning_effort=_attempt_effort(
|
reasoning_effort=_attempt_effort(
|
||||||
request=request, source=source, response=response, applies=reasoning_applies
|
request=request, source=source, response=response, applies=reasoning_applies
|
||||||
),
|
),
|
||||||
|
operation=operation,
|
||||||
|
event_kind="attempt",
|
||||||
|
attempts=None,
|
||||||
|
total_latency_ms=None,
|
||||||
)
|
)
|
||||||
|
|
||||||
async def emit_cache_hit(self, *, request: ChatRequest, response: LLMResponse) -> None:
|
async def emit_cache_hit(
|
||||||
"""缓存命中记录: cache_hit=True、latency_ms=0(VT 同款)。"""
|
self, *, request: ChatRequest, response: LLMResponse, operation: CallOperation
|
||||||
|
) -> None:
|
||||||
|
"""缓存命中记录: cache_hit=True、latency_ms=0(VT 同款)。
|
||||||
|
|
||||||
|
逻辑计数两列恒 NULL: 本行描述的是"一次命中",不是一次逻辑调用的终态。
|
||||||
|
"""
|
||||||
await self._record(
|
await self._record(
|
||||||
request=request,
|
request=request,
|
||||||
call_id=response.call_id,
|
call_id=response.call_id,
|
||||||
@@ -315,7 +475,7 @@ class TelemetryEmitter:
|
|||||||
ttft_ms=None,
|
ttft_ms=None,
|
||||||
max_inter_token_ms=None,
|
max_inter_token_ms=None,
|
||||||
cache_hit=True,
|
cache_hit=True,
|
||||||
error=None,
|
errors=_ErrorFields(),
|
||||||
# 决策 B1: 与 model/prompt_tokens 同一口径,原样回放历史值。
|
# 决策 B1: 与 model/prompt_tokens 同一口径,原样回放历史值。
|
||||||
# 统计供应商缓存命中率必须带 WHERE cache_hit = false,否则重复计数。
|
# 统计供应商缓存命中率必须带 WHERE cache_hit = false,否则重复计数。
|
||||||
cached_prompt_tokens=response.cached_prompt_tokens,
|
cached_prompt_tokens=response.cached_prompt_tokens,
|
||||||
@@ -334,12 +494,28 @@ class TelemetryEmitter:
|
|||||||
# 与 sampling 同一口径: 命中行没有选中源,源级档位与 `nearest` 映射
|
# 与 sampling 同一口径: 命中行没有选中源,源级档位与 `nearest` 映射
|
||||||
# 都无从谈起,只记调用方这次要的档(response 里那个是历史那次实发的)
|
# 都无从谈起,只记调用方这次要的档(response 里那个是历史那次实发的)
|
||||||
reasoning_effort=_normalize_effort(request.reasoning_effort),
|
reasoning_effort=_normalize_effort(request.reasoning_effort),
|
||||||
|
operation=operation,
|
||||||
|
event_kind="cache_hit",
|
||||||
|
attempts=None,
|
||||||
|
total_latency_ms=None,
|
||||||
)
|
)
|
||||||
|
|
||||||
async def emit_terminal_failure(
|
async def emit_terminal_failure(
|
||||||
self, *, request: ChatRequest, call_id: str, latency_ms: int, error: str
|
self,
|
||||||
|
*,
|
||||||
|
request: ChatRequest,
|
||||||
|
call_id: str,
|
||||||
|
error: PolyGatewayError | str,
|
||||||
|
operation: CallOperation,
|
||||||
|
stats: CallStats,
|
||||||
|
class_prefixed_error: bool = False,
|
||||||
) -> None:
|
) -> None:
|
||||||
"""scope 级失败/取消记录: 无具体源,溯源字段置空标记。"""
|
"""一次**逻辑调用**的失败终态: 无具体源,溯源字段置空标记。
|
||||||
|
|
||||||
|
`latency_ms` 与 `total_latency_ms` 同取**同一份冻结快照**,避免双时钟微差;
|
||||||
|
故本方法不再收 `latency_ms`。token 与 cost 一律不从 attempt 行复制
|
||||||
|
(费用聚合仍只由 attempt / cache_hit 行决定,口径不变)。
|
||||||
|
"""
|
||||||
await self._record(
|
await self._record(
|
||||||
request=request,
|
request=request,
|
||||||
call_id=call_id,
|
call_id=call_id,
|
||||||
@@ -351,11 +527,13 @@ class TelemetryEmitter:
|
|||||||
prompt_tokens=0,
|
prompt_tokens=0,
|
||||||
completion_tokens=0,
|
completion_tokens=0,
|
||||||
usage_source="unavailable",
|
usage_source="unavailable",
|
||||||
latency_ms=latency_ms,
|
latency_ms=stats.total_latency_ms,
|
||||||
ttft_ms=None,
|
ttft_ms=None,
|
||||||
max_inter_token_ms=None,
|
max_inter_token_ms=None,
|
||||||
cache_hit=False,
|
cache_hit=False,
|
||||||
error=error,
|
errors=_error_fields(
|
||||||
|
error, event_kind="terminal_failure", class_prefixed=class_prefixed_error
|
||||||
|
),
|
||||||
cached_prompt_tokens=None,
|
cached_prompt_tokens=None,
|
||||||
model_reported=None,
|
model_reported=None,
|
||||||
reasoning_tokens=None,
|
reasoning_tokens=None,
|
||||||
@@ -368,6 +546,10 @@ class TelemetryEmitter:
|
|||||||
meta=request.meta,
|
meta=request.meta,
|
||||||
# 可能根本没选出源,故与 sampling 同样只取请求档
|
# 可能根本没选出源,故与 sampling 同样只取请求档
|
||||||
reasoning_effort=_normalize_effort(request.reasoning_effort),
|
reasoning_effort=_normalize_effort(request.reasoning_effort),
|
||||||
|
operation=operation,
|
||||||
|
event_kind="terminal_failure",
|
||||||
|
attempts=stats.attempts,
|
||||||
|
total_latency_ms=stats.total_latency_ms,
|
||||||
)
|
)
|
||||||
|
|
||||||
async def _record(
|
async def _record(
|
||||||
@@ -387,7 +569,9 @@ class TelemetryEmitter:
|
|||||||
ttft_ms: float | None,
|
ttft_ms: float | None,
|
||||||
max_inter_token_ms: float | None,
|
max_inter_token_ms: float | None,
|
||||||
cache_hit: bool,
|
cache_hit: bool,
|
||||||
error: str | None,
|
# 1.3.5: 错误四列已由 `_error_fields` 定型(三种入参形态 × 两类行的唯一规则所有者),
|
||||||
|
# 本方法只搬运——拆成五个平铺参数就是把"一处定型"换回"三处各自拼"
|
||||||
|
errors: _ErrorFields,
|
||||||
cached_prompt_tokens: int | None,
|
cached_prompt_tokens: int | None,
|
||||||
model_reported: str | None,
|
model_reported: str | None,
|
||||||
sampling: str | None,
|
sampling: str | None,
|
||||||
@@ -403,6 +587,11 @@ class TelemetryEmitter:
|
|||||||
# 注释),本方法只搬运——把定型放这里就得再传一遍 response/source,等于把
|
# 注释),本方法只搬运——把定型放这里就得再传一遍 response/source,等于把
|
||||||
# "唯一 record_llm_call 调用点"换成"两处口径判断",那正是要避免的复制
|
# "唯一 record_llm_call 调用点"换成"两处口径判断",那正是要避免的复制
|
||||||
reasoning_effort: str | None,
|
reasoning_effort: str | None,
|
||||||
|
# —— 1.3.5: 行形态与逻辑调用快照 ——
|
||||||
|
operation: CallOperation,
|
||||||
|
event_kind: EventKind,
|
||||||
|
attempts: int | None,
|
||||||
|
total_latency_ms: int | None,
|
||||||
) -> None:
|
) -> None:
|
||||||
try:
|
try:
|
||||||
# 成本换算(M2 §6): 成功行按单价换算;缓存命中 0.0(未产生新调用);
|
# 成本换算(M2 §6): 成功行按单价换算;缓存命中 0.0(未产生新调用);
|
||||||
@@ -413,7 +602,7 @@ class TelemetryEmitter:
|
|||||||
# 用量不可得: 宁可算不出成本,也不算错成本(解耦设计 §3.1 不变式)。
|
# 用量不可得: 宁可算不出成本,也不算错成本(解耦设计 §3.1 不变式)。
|
||||||
# 必须排在 cache_hit 之后——缓存命中未产生新调用,0.0 是事实而非未知
|
# 必须排在 cache_hit 之后——缓存命中未产生新调用,0.0 是事实而非未知
|
||||||
cost = None
|
cost = None
|
||||||
elif error is None and model and self._pricing is not None:
|
elif errors.error is None and model and self._pricing is not None:
|
||||||
cost = self._pricing.cost(
|
cost = self._pricing.cost(
|
||||||
model, prompt_tokens, completion_tokens, cached_prompt_tokens
|
model, prompt_tokens, completion_tokens, cached_prompt_tokens
|
||||||
)
|
)
|
||||||
@@ -425,6 +614,7 @@ class TelemetryEmitter:
|
|||||||
_cap_messages(digest_messages(request.messages), self._text_cap),
|
_cap_messages(digest_messages(request.messages), self._text_cap),
|
||||||
ensure_ascii=False,
|
ensure_ascii=False,
|
||||||
)
|
)
|
||||||
|
context = request.call_context
|
||||||
await self._recorder.record_llm_call(
|
await self._recorder.record_llm_call(
|
||||||
call_id=call_id,
|
call_id=call_id,
|
||||||
parent_call_id=request.parent_call_id,
|
parent_call_id=request.parent_call_id,
|
||||||
@@ -442,7 +632,7 @@ class TelemetryEmitter:
|
|||||||
ttft_ms=ttft_ms,
|
ttft_ms=ttft_ms,
|
||||||
max_inter_token_ms=max_inter_token_ms,
|
max_inter_token_ms=max_inter_token_ms,
|
||||||
cache_hit=cache_hit,
|
cache_hit=cache_hit,
|
||||||
error=error,
|
error=errors.error,
|
||||||
cost=cost,
|
cost=cost,
|
||||||
cached_prompt_tokens=cached_prompt_tokens,
|
cached_prompt_tokens=cached_prompt_tokens,
|
||||||
model_reported=model_reported,
|
model_reported=model_reported,
|
||||||
@@ -457,6 +647,19 @@ class TelemetryEmitter:
|
|||||||
# Postgres 那一路悄悄少一列数据
|
# Postgres 那一路悄悄少一列数据
|
||||||
thinking_observation=_normalize_observation(thinking_observation),
|
thinking_observation=_normalize_observation(thinking_observation),
|
||||||
reasoning_effort=reasoning_effort,
|
reasoning_effort=reasoning_effort,
|
||||||
|
# —— 1.3.5 十列 ——
|
||||||
|
scope=self._scope,
|
||||||
|
# 调用点给定的公开方法四值,**绝不读 `exc.operation`**(设计 §5 I1/I2)
|
||||||
|
operation=operation,
|
||||||
|
# 上下文缺席(库内现场构造的 ChatRequest)→ NULL,**不造 ID**(I5)
|
||||||
|
logical_call_id=None if context is None else context.logical_call_id,
|
||||||
|
event_kind=event_kind,
|
||||||
|
http_status_code=errors.http_status_code,
|
||||||
|
error_type=errors.error_type,
|
||||||
|
cause_type=errors.cause_type,
|
||||||
|
error_body=errors.error_body,
|
||||||
|
attempts=attempts,
|
||||||
|
total_latency_ms=total_latency_ms,
|
||||||
)
|
)
|
||||||
except asyncio.CancelledError:
|
except asyncio.CancelledError:
|
||||||
raise
|
raise
|
||||||
@@ -464,36 +667,69 @@ class TelemetryEmitter:
|
|||||||
logger.warning("遥测记录失败(降级不冒泡): {}", exc)
|
logger.warning("遥测记录失败(降级不冒泡): {}", exc)
|
||||||
|
|
||||||
|
|
||||||
|
async def emit_terminal_once(
|
||||||
|
emitter: TelemetryEmitter | None,
|
||||||
|
*,
|
||||||
|
request: ChatRequest,
|
||||||
|
context: _CallContext,
|
||||||
|
error: PolyGatewayError | str,
|
||||||
|
operation: CallOperation,
|
||||||
|
class_prefixed_error: bool = False,
|
||||||
|
) -> None:
|
||||||
|
"""三个 client 共用的**终态唯一出口**: 去重 + 同步冻结快照 + best effort 写入。
|
||||||
|
|
||||||
|
去重由 `claim_terminal()` 承担(每逻辑调用至多一条终态行);`emitter is None`
|
||||||
|
或已写过 → 直接返回。
|
||||||
|
|
||||||
|
**降级范围包含诊断字段的提取与构建**,不只是写入那一步: `_record` 内的
|
||||||
|
`except Exception` 只兜住落库,而 `_error_fields` / `canonical_sampling_json`
|
||||||
|
在它**之外**求值——下游经公共端口(自实现 `StructuredOutputStrategy` 或
|
||||||
|
transport)构造出的 `ResultInvalidError(validation_errors=(非 str,))` 会让提取期
|
||||||
|
抛 `TypeError` 顶替调用方本该收到的领域异常,错误四分类被击穿且终态行照样丢。
|
||||||
|
故在此整段兜底,与 RetryMW 的 attempt 出口(`retry.py::_emit`)同款写法。
|
||||||
|
终态行按 best effort: 兜底命中时本次逻辑调用**没有**终态行(`claim_terminal()`
|
||||||
|
已消耗,不补写、不重试——重写一遍只会把同一个提取期异常再抛一次)。
|
||||||
|
|
||||||
|
**`CancelledError` 原样传播**(取消优先,不 shield、不开后台任务): 这一次
|
||||||
|
`await` 本身就是新的取消点,外部取消落在它上时调用方会看到 `CancelledError`
|
||||||
|
而非领域错误——与 TelemetryMW 的历史行为同款,已经人类批准(设计 §6/§10)。
|
||||||
|
快照冻结是**同步**动作,故终态行不含它自身的写入耗时。
|
||||||
|
"""
|
||||||
|
if emitter is None or not context.claim_terminal():
|
||||||
|
return
|
||||||
|
try:
|
||||||
|
stats = context.snapshot()
|
||||||
|
await emitter.emit_terminal_failure(
|
||||||
|
request=request,
|
||||||
|
call_id=str(uuid.uuid4()),
|
||||||
|
error=error,
|
||||||
|
operation=operation,
|
||||||
|
stats=stats,
|
||||||
|
class_prefixed_error=class_prefixed_error,
|
||||||
|
)
|
||||||
|
except asyncio.CancelledError:
|
||||||
|
raise
|
||||||
|
except Exception as exc:
|
||||||
|
logger.warning("终态遥测记录失败(降级不冒泡): {}", exc)
|
||||||
|
|
||||||
|
|
||||||
class TelemetryMW:
|
class TelemetryMW:
|
||||||
"""洋葱最外层: 观测尝试层看不见的路径,任何路径都留痕(遥测必录)。"""
|
"""洋葱最外层: 只观测尝试层看不见的**缓存命中**。
|
||||||
|
|
||||||
|
1.3.5 起不再在此写终态失败行: 终态由 `GatewayClient.chat` 的公开边界经
|
||||||
|
`emit_terminal_once` 统一写出。两处同时写会让同一次失败出两条终态行,
|
||||||
|
而下游正是按 `event_kind = 'terminal_failure'` 计失败调用次数的。
|
||||||
|
"""
|
||||||
|
|
||||||
def __init__(
|
def __init__(
|
||||||
self, emitter: TelemetryEmitter, now: Callable[[], float] = time.monotonic
|
self, emitter: TelemetryEmitter, now: Callable[[], float] = time.monotonic
|
||||||
) -> None:
|
) -> None:
|
||||||
self._emitter = emitter
|
self._emitter = emitter
|
||||||
self._now = now
|
# `now` 自 1.3.5 起本类不再读取(终态行迁到公开边界后无耗时可测),但形参保留:
|
||||||
|
# 删它会平白打断 `TelemetryMW(emitter, now=...)` 这一既有装配写法
|
||||||
|
|
||||||
async def __call__(self, request: ChatRequest, call_next: CallNext) -> LLMResponse:
|
async def __call__(self, request: ChatRequest, call_next: CallNext) -> LLMResponse:
|
||||||
started = self._now()
|
|
||||||
try:
|
|
||||||
response = await call_next(request)
|
response = await call_next(request)
|
||||||
except (GatewayUnavailableError, GovernanceBackendError, SourceNotConfiguredError) as exc:
|
|
||||||
await self._emitter.emit_terminal_failure(
|
|
||||||
request=request,
|
|
||||||
call_id=str(uuid.uuid4()),
|
|
||||||
latency_ms=int((self._now() - started) * 1000),
|
|
||||||
error=str(exc),
|
|
||||||
)
|
|
||||||
raise
|
|
||||||
except asyncio.CancelledError:
|
|
||||||
# 尽力而为: 取消也留痕(§5.1 约定④);随后立即重抛
|
|
||||||
await self._emitter.emit_terminal_failure(
|
|
||||||
request=request,
|
|
||||||
call_id=str(uuid.uuid4()),
|
|
||||||
latency_ms=int((self._now() - started) * 1000),
|
|
||||||
error="cancelled",
|
|
||||||
)
|
|
||||||
raise
|
|
||||||
if response.cache_hit:
|
if response.cache_hit:
|
||||||
await self._emitter.emit_cache_hit(request=request, response=response)
|
await self._emitter.emit_cache_hit(request=request, response=response, operation="chat")
|
||||||
return response
|
return response
|
||||||
|
|||||||
+153
-24
@@ -37,15 +37,17 @@ from polygateway.middleware.admission import SourceAdmission, settle_and_release
|
|||||||
from polygateway.middleware.breaker import BreakerGate
|
from polygateway.middleware.breaker import BreakerGate
|
||||||
from polygateway.middleware.ratelimit import QuotaGate
|
from polygateway.middleware.ratelimit import QuotaGate
|
||||||
from polygateway.middleware.retry import StallClock, _failure_reason, backoff_delay
|
from polygateway.middleware.retry import StallClock, _failure_reason, backoff_delay
|
||||||
from polygateway.middleware.telemetry import TelemetryEmitter
|
from polygateway.middleware.telemetry import TelemetryEmitter, emit_terminal_once
|
||||||
from polygateway.ports import OutcomeAwareSelector
|
from polygateway.ports import OutcomeAwareSelector
|
||||||
from polygateway.types import (
|
from polygateway.types import (
|
||||||
|
CallStats,
|
||||||
ChatRequest,
|
ChatRequest,
|
||||||
LLMResponse,
|
LLMResponse,
|
||||||
OcrLayoutResult,
|
OcrLayoutResult,
|
||||||
OcrTextResult,
|
OcrTextResult,
|
||||||
TelemetryStatus,
|
TelemetryStatus,
|
||||||
Usage,
|
Usage,
|
||||||
|
_CallContext,
|
||||||
strip_unsupported_extra_body,
|
strip_unsupported_extra_body,
|
||||||
validate_caller_dimensions,
|
validate_caller_dimensions,
|
||||||
)
|
)
|
||||||
@@ -65,6 +67,7 @@ if TYPE_CHECKING:
|
|||||||
)
|
)
|
||||||
from polygateway.types import (
|
from polygateway.types import (
|
||||||
BackpressurePolicy,
|
BackpressurePolicy,
|
||||||
|
CallOperation,
|
||||||
OcrLayoutTransportResult,
|
OcrLayoutTransportResult,
|
||||||
OcrTextTransportResult,
|
OcrTextTransportResult,
|
||||||
RetryPolicy,
|
RetryPolicy,
|
||||||
@@ -126,7 +129,9 @@ class OcrClient:
|
|||||||
self._breaker = BreakerGate(breaker, scope=self._scope)
|
self._breaker = BreakerGate(breaker, scope=self._scope)
|
||||||
self._transport = transport
|
self._transport = transport
|
||||||
self._retry = retry
|
self._retry = retry
|
||||||
self._emitter = TelemetryEmitter(telemetry, text_cap=text_cap) if telemetry else None
|
self._emitter = (
|
||||||
|
TelemetryEmitter(telemetry, scope=self._scope, text_cap=text_cap) if telemetry else None
|
||||||
|
)
|
||||||
self._telemetry = telemetry
|
self._telemetry = telemetry
|
||||||
# 限流/熔断后端在此之外只以 QuotaGate/BreakerGate 的形态存在,自持一份
|
# 限流/熔断后端在此之外只以 QuotaGate/BreakerGate 的形态存在,自持一份
|
||||||
# 引用才关得到自建的 redis 客户端(设计 §3.4)
|
# 引用才关得到自建的 redis 客户端(设计 §3.4)
|
||||||
@@ -176,8 +181,14 @@ class OcrClient:
|
|||||||
dimension_tenant_id, dimensions = validate_caller_dimensions(
|
dimension_tenant_id, dimensions = validate_caller_dimensions(
|
||||||
tenant_id, meta, origin="recognize_text(tenant_id=..., meta=...)"
|
tenant_id, meta, origin="recognize_text(tenant_id=..., meta=...)"
|
||||||
)
|
)
|
||||||
outcome = await self._call(
|
outcome, call_stats = await self._call(
|
||||||
"text", image, session_id, parent_call_id, dimension_tenant_id, dimensions
|
"text",
|
||||||
|
"recognize_text",
|
||||||
|
image,
|
||||||
|
session_id,
|
||||||
|
parent_call_id,
|
||||||
|
dimension_tenant_id,
|
||||||
|
dimensions,
|
||||||
)
|
)
|
||||||
result = outcome.result
|
result = outcome.result
|
||||||
return OcrTextResult(
|
return OcrTextResult(
|
||||||
@@ -187,6 +198,7 @@ class OcrClient:
|
|||||||
latency_ms=outcome.latency_ms,
|
latency_ms=outcome.latency_ms,
|
||||||
call_id=outcome.call_id,
|
call_id=outcome.call_id,
|
||||||
raw=result.raw,
|
raw=result.raw,
|
||||||
|
call_stats=call_stats,
|
||||||
)
|
)
|
||||||
|
|
||||||
async def parse_layout(
|
async def parse_layout(
|
||||||
@@ -206,8 +218,14 @@ class OcrClient:
|
|||||||
dimension_tenant_id, dimensions = validate_caller_dimensions(
|
dimension_tenant_id, dimensions = validate_caller_dimensions(
|
||||||
tenant_id, meta, origin="parse_layout(tenant_id=..., meta=...)"
|
tenant_id, meta, origin="parse_layout(tenant_id=..., meta=...)"
|
||||||
)
|
)
|
||||||
outcome = await self._call(
|
outcome, call_stats = await self._call(
|
||||||
"layout", image, session_id, parent_call_id, dimension_tenant_id, dimensions
|
"layout",
|
||||||
|
"parse_layout",
|
||||||
|
image,
|
||||||
|
session_id,
|
||||||
|
parent_call_id,
|
||||||
|
dimension_tenant_id,
|
||||||
|
dimensions,
|
||||||
)
|
)
|
||||||
result = outcome.result
|
result = outcome.result
|
||||||
return OcrLayoutResult(
|
return OcrLayoutResult(
|
||||||
@@ -218,6 +236,7 @@ class OcrClient:
|
|||||||
latency_ms=outcome.latency_ms,
|
latency_ms=outcome.latency_ms,
|
||||||
call_id=outcome.call_id,
|
call_id=outcome.call_id,
|
||||||
raw=result.raw,
|
raw=result.raw,
|
||||||
|
call_stats=call_stats,
|
||||||
)
|
)
|
||||||
|
|
||||||
async def check_health(self) -> dict[str, bool]:
|
async def check_health(self) -> dict[str, bool]:
|
||||||
@@ -237,16 +256,60 @@ class OcrClient:
|
|||||||
async def _call(
|
async def _call(
|
||||||
self,
|
self,
|
||||||
kind: _OcrKind,
|
kind: _OcrKind,
|
||||||
|
operation: CallOperation,
|
||||||
image: bytes,
|
image: bytes,
|
||||||
session_id: str | None,
|
session_id: str | None,
|
||||||
parent_call_id: str | None,
|
parent_call_id: str | None,
|
||||||
tenant_id: str | None,
|
tenant_id: str | None,
|
||||||
meta: dict[str, Any],
|
meta: dict[str, Any],
|
||||||
) -> _AttemptOutcome:
|
) -> tuple[_AttemptOutcome, CallStats]:
|
||||||
if not isinstance(image, bytes):
|
if not isinstance(image, bytes):
|
||||||
raise TypeError("image 必须是 bytes(路径读取/批量拼帧留业务侧,D9)")
|
raise TypeError("image 必须是 bytes(路径读取/批量拼帧留业务侧,D9)")
|
||||||
if not image:
|
if not image:
|
||||||
raise ValueError("image 不能为空")
|
raise ValueError("image 不能为空")
|
||||||
|
# M1 例外: `image` 校验在 `_call` 内而非公开方法,故上下文在该校验
|
||||||
|
# **通过之后**创建——这样设计 §3 的"校验在统计边界外"对 OCR 才成立
|
||||||
|
context = _CallContext(now=self._now)
|
||||||
|
try:
|
||||||
|
return await self._run(
|
||||||
|
kind, operation, image, session_id, parent_call_id, tenant_id, meta, context
|
||||||
|
)
|
||||||
|
except PolyGatewayError as exc:
|
||||||
|
await self._emit_terminal(
|
||||||
|
kind, operation, image, session_id, parent_call_id, tenant_id, meta, context, exc
|
||||||
|
)
|
||||||
|
raise
|
||||||
|
except asyncio.CancelledError:
|
||||||
|
# 三条链路同一口径尽力写一条(允许 0 条);取消优先,不 shield
|
||||||
|
await self._emit_terminal(
|
||||||
|
kind,
|
||||||
|
operation,
|
||||||
|
image,
|
||||||
|
session_id,
|
||||||
|
parent_call_id,
|
||||||
|
tenant_id,
|
||||||
|
meta,
|
||||||
|
context,
|
||||||
|
"cancelled",
|
||||||
|
)
|
||||||
|
raise
|
||||||
|
|
||||||
|
async def _run(
|
||||||
|
self,
|
||||||
|
kind: _OcrKind,
|
||||||
|
operation: CallOperation,
|
||||||
|
image: bytes,
|
||||||
|
session_id: str | None,
|
||||||
|
parent_call_id: str | None,
|
||||||
|
tenant_id: str | None,
|
||||||
|
meta: dict[str, Any],
|
||||||
|
context: _CallContext,
|
||||||
|
) -> tuple[_AttemptOutcome, CallStats]:
|
||||||
|
"""选源与重试循环。
|
||||||
|
|
||||||
|
无源的 raise 必须在本方法内(而非循环之前的调用方): 它得被 `_call` 的
|
||||||
|
`try` 包住,否则无源终态行根本写不出来(设计 §3.5)。
|
||||||
|
"""
|
||||||
if not self._sources:
|
if not self._sources:
|
||||||
raise AllSourcesExhausted(scope=self._scope, reason="no_sources", retry_after_s=0.0)
|
raise AllSourcesExhausted(scope=self._scope, reason="no_sources", retry_after_s=0.0)
|
||||||
fails = 0
|
fails = 0
|
||||||
@@ -260,10 +323,19 @@ class OcrClient:
|
|||||||
continue
|
continue
|
||||||
async with clock.attempting():
|
async with clock.attempting():
|
||||||
outcome = await self._attempt(
|
outcome = await self._attempt(
|
||||||
kind, image, *picked, reasons, session_id, parent_call_id, tenant_id, meta
|
kind,
|
||||||
|
operation,
|
||||||
|
image,
|
||||||
|
*picked,
|
||||||
|
reasons,
|
||||||
|
session_id,
|
||||||
|
parent_call_id,
|
||||||
|
tenant_id,
|
||||||
|
meta,
|
||||||
|
context,
|
||||||
)
|
)
|
||||||
if isinstance(outcome, _AttemptOutcome):
|
if isinstance(outcome, _AttemptOutcome):
|
||||||
return outcome
|
return outcome, context.snapshot()
|
||||||
fails += 1
|
fails += 1
|
||||||
if fails >= self._retry.max_attempts:
|
if fails >= self._retry.max_attempts:
|
||||||
raise AllSourcesExhausted(
|
raise AllSourcesExhausted(
|
||||||
@@ -278,6 +350,7 @@ class OcrClient:
|
|||||||
async def _attempt(
|
async def _attempt(
|
||||||
self,
|
self,
|
||||||
kind: _OcrKind,
|
kind: _OcrKind,
|
||||||
|
operation: CallOperation,
|
||||||
image: bytes,
|
image: bytes,
|
||||||
source: SourceConfig,
|
source: SourceConfig,
|
||||||
permit: Permit,
|
permit: Permit,
|
||||||
@@ -287,11 +360,14 @@ class OcrClient:
|
|||||||
parent_call_id: str | None,
|
parent_call_id: str | None,
|
||||||
tenant_id: str | None,
|
tenant_id: str | None,
|
||||||
meta: dict[str, Any],
|
meta: dict[str, Any],
|
||||||
|
context: _CallContext,
|
||||||
) -> _AttemptOutcome | _FailedAttempt:
|
) -> _AttemptOutcome | _FailedAttempt:
|
||||||
call_id = str(uuid.uuid4())
|
call_id = str(uuid.uuid4())
|
||||||
started = self._now()
|
started = self._now()
|
||||||
# 四个 emit 分支(成功/终态拒绝/取消/可重试失败)都必须带调用方维度:
|
# 四个 emit 分支(成功/终态拒绝/取消/可重试失败)都必须带调用方维度:
|
||||||
# 失败行与取消行同样需要租户归属,漏掉任一分支就会写出无归属的行
|
# 失败行与取消行同样需要租户归属,漏掉任一分支就会写出无归属的行
|
||||||
|
# layout 的 POST + ZIP GET 在同一次 `_invoke` 内,故这里只登记 **1** 次
|
||||||
|
context.register_attempt()
|
||||||
try:
|
try:
|
||||||
result = await self._invoke(kind, image, source, call_id)
|
result = await self._invoke(kind, image, source, call_id)
|
||||||
await self._record_quietly(self._breaker.record_success(entry))
|
await self._record_quietly(self._breaker.record_success(entry))
|
||||||
@@ -300,6 +376,7 @@ class OcrClient:
|
|||||||
latency_ms = int((self._now() - started) * 1000)
|
latency_ms = int((self._now() - started) * 1000)
|
||||||
await self._emit(
|
await self._emit(
|
||||||
kind,
|
kind,
|
||||||
|
operation,
|
||||||
image,
|
image,
|
||||||
source,
|
source,
|
||||||
call_id,
|
call_id,
|
||||||
@@ -308,6 +385,7 @@ class OcrClient:
|
|||||||
parent_call_id,
|
parent_call_id,
|
||||||
tenant_id,
|
tenant_id,
|
||||||
meta,
|
meta,
|
||||||
|
context,
|
||||||
result,
|
result,
|
||||||
)
|
)
|
||||||
return _AttemptOutcome(result, source, call_id, latency_ms)
|
return _AttemptOutcome(result, source, call_id, latency_ms)
|
||||||
@@ -315,6 +393,7 @@ class OcrClient:
|
|||||||
await self._gate_on_terminal(exc, entry)
|
await self._gate_on_terminal(exc, entry)
|
||||||
await self._emit(
|
await self._emit(
|
||||||
kind,
|
kind,
|
||||||
|
operation,
|
||||||
image,
|
image,
|
||||||
source,
|
source,
|
||||||
call_id,
|
call_id,
|
||||||
@@ -323,6 +402,7 @@ class OcrClient:
|
|||||||
parent_call_id,
|
parent_call_id,
|
||||||
tenant_id,
|
tenant_id,
|
||||||
meta,
|
meta,
|
||||||
|
context,
|
||||||
error=exc,
|
error=exc,
|
||||||
)
|
)
|
||||||
raise
|
raise
|
||||||
@@ -331,6 +411,7 @@ class OcrClient:
|
|||||||
await self._record_quietly(self._breaker.release_probe(entry))
|
await self._record_quietly(self._breaker.release_probe(entry))
|
||||||
await self._emit(
|
await self._emit(
|
||||||
kind,
|
kind,
|
||||||
|
operation,
|
||||||
image,
|
image,
|
||||||
source,
|
source,
|
||||||
call_id,
|
call_id,
|
||||||
@@ -339,6 +420,7 @@ class OcrClient:
|
|||||||
parent_call_id,
|
parent_call_id,
|
||||||
tenant_id,
|
tenant_id,
|
||||||
meta,
|
meta,
|
||||||
|
context,
|
||||||
error="cancelled",
|
error="cancelled",
|
||||||
)
|
)
|
||||||
raise
|
raise
|
||||||
@@ -350,6 +432,7 @@ class OcrClient:
|
|||||||
self._feed_outcome(source.name, ok=False)
|
self._feed_outcome(source.name, ok=False)
|
||||||
await self._emit(
|
await self._emit(
|
||||||
kind,
|
kind,
|
||||||
|
operation,
|
||||||
image,
|
image,
|
||||||
source,
|
source,
|
||||||
call_id,
|
call_id,
|
||||||
@@ -358,6 +441,7 @@ class OcrClient:
|
|||||||
parent_call_id,
|
parent_call_id,
|
||||||
tenant_id,
|
tenant_id,
|
||||||
meta,
|
meta,
|
||||||
|
context,
|
||||||
error=exc,
|
error=exc,
|
||||||
)
|
)
|
||||||
return _FailedAttempt(exc, immediate=dead)
|
return _FailedAttempt(exc, immediate=dead)
|
||||||
@@ -399,9 +483,60 @@ class OcrClient:
|
|||||||
except (GovernanceBackendError, SourceNotConfiguredError) as exc:
|
except (GovernanceBackendError, SourceNotConfiguredError) as exc:
|
||||||
logger.warning("OCR 治理记账写回降级(不冒泡): {}", exc)
|
logger.warning("OCR 治理记账写回降级(不冒泡): {}", exc)
|
||||||
|
|
||||||
|
def _request_for(
|
||||||
|
self,
|
||||||
|
kind: _OcrKind,
|
||||||
|
image: bytes,
|
||||||
|
session_id: str | None,
|
||||||
|
parent_call_id: str | None,
|
||||||
|
tenant_id: str | None,
|
||||||
|
meta: dict[str, Any],
|
||||||
|
context: _CallContext,
|
||||||
|
) -> ChatRequest:
|
||||||
|
"""OCR 行的现场 ChatRequest: 占位摘要,**图像 bytes 永不入库**。
|
||||||
|
|
||||||
|
尝试行与终态行共用同一个构造点: 占位字面量复制成两份就会漂移。
|
||||||
|
调用方维度与上下文必须显式填回(OCR 不走 chat 洋葱),否则 OCR 行的
|
||||||
|
维度恒为空、`logical_call_id` 恒为 NULL。
|
||||||
|
"""
|
||||||
|
return ChatRequest(
|
||||||
|
messages=[{"role": "user", "content": f"<ocr:{kind} image_bytes={len(image)}>"}],
|
||||||
|
session_id=session_id,
|
||||||
|
parent_call_id=parent_call_id,
|
||||||
|
tenant_id=tenant_id,
|
||||||
|
meta=meta,
|
||||||
|
call_context=context,
|
||||||
|
)
|
||||||
|
|
||||||
|
async def _emit_terminal(
|
||||||
|
self,
|
||||||
|
kind: _OcrKind,
|
||||||
|
operation: CallOperation,
|
||||||
|
image: bytes,
|
||||||
|
session_id: str | None,
|
||||||
|
parent_call_id: str | None,
|
||||||
|
tenant_id: str | None,
|
||||||
|
meta: dict[str, Any],
|
||||||
|
context: _CallContext,
|
||||||
|
error: PolyGatewayError | str,
|
||||||
|
) -> None:
|
||||||
|
"""终态行: 沿用 `<ocr:{kind} image_bytes=…>` 占位,错误文本保留类名前缀。"""
|
||||||
|
await emit_terminal_once(
|
||||||
|
self._emitter,
|
||||||
|
request=self._request_for(
|
||||||
|
kind, image, session_id, parent_call_id, tenant_id, meta, context
|
||||||
|
),
|
||||||
|
context=context,
|
||||||
|
error=error,
|
||||||
|
operation=operation,
|
||||||
|
# metric ocr-call-success 的注册口径是按类名归组,终态行同款保留
|
||||||
|
class_prefixed_error=True,
|
||||||
|
)
|
||||||
|
|
||||||
async def _emit(
|
async def _emit(
|
||||||
self,
|
self,
|
||||||
kind: _OcrKind,
|
kind: _OcrKind,
|
||||||
|
operation: CallOperation,
|
||||||
image: bytes,
|
image: bytes,
|
||||||
source: SourceConfig,
|
source: SourceConfig,
|
||||||
call_id: str,
|
call_id: str,
|
||||||
@@ -410,20 +545,15 @@ class OcrClient:
|
|||||||
parent_call_id: str | None,
|
parent_call_id: str | None,
|
||||||
tenant_id: str | None,
|
tenant_id: str | None,
|
||||||
meta: dict[str, Any],
|
meta: dict[str, Any],
|
||||||
|
context: _CallContext,
|
||||||
result: OcrTextTransportResult | OcrLayoutTransportResult | None = None,
|
result: OcrTextTransportResult | OcrLayoutTransportResult | None = None,
|
||||||
error: object | None = None,
|
error: PolyGatewayError | str | None = None,
|
||||||
) -> None:
|
) -> None:
|
||||||
"""逐尝试遥测(单一 Emitter): messages 占位摘要,图像 bytes 绝不入库。"""
|
"""逐尝试遥测(单一 Emitter): messages 占位摘要,图像 bytes 绝不入库。"""
|
||||||
if self._emitter is None:
|
if self._emitter is None:
|
||||||
return
|
return
|
||||||
# 这个 ChatRequest 只为复用同一个 Emitter 而现场构造(OCR 不走 chat 洋葱),
|
request = self._request_for(
|
||||||
# 故调用方维度必须在这里显式填回,否则 OCR 行的维度恒为空
|
kind, image, session_id, parent_call_id, tenant_id, meta, context
|
||||||
request = ChatRequest(
|
|
||||||
messages=[{"role": "user", "content": f"<ocr:{kind} image_bytes={len(image)}>"}],
|
|
||||||
session_id=session_id,
|
|
||||||
parent_call_id=parent_call_id,
|
|
||||||
tenant_id=tenant_id,
|
|
||||||
meta=meta,
|
|
||||||
)
|
)
|
||||||
latency_ms = int((self._now() - started) * 1000)
|
latency_ms = int((self._now() - started) * 1000)
|
||||||
response = None
|
response = None
|
||||||
@@ -443,20 +573,19 @@ class OcrClient:
|
|||||||
source_name=source.name,
|
source_name=source.name,
|
||||||
usage_source="measured",
|
usage_source="measured",
|
||||||
)
|
)
|
||||||
# 错误带异常类名前缀(metric ocr-call-success 注册口径: 按类名归组)
|
# 错误文本的类名前缀现由出口的显式策略参数承担(设计 §6 I7):
|
||||||
if error is None or isinstance(error, str):
|
# 三处各拼一遍才是下一次漂移的种子,而取消行传的是字符串,不受前缀影响
|
||||||
error_text = error
|
|
||||||
else:
|
|
||||||
error_text = f"{type(error).__name__}: {error}"
|
|
||||||
await self._emitter.emit_attempt(
|
await self._emitter.emit_attempt(
|
||||||
request=request,
|
request=request,
|
||||||
source=source,
|
source=source,
|
||||||
call_id=call_id,
|
call_id=call_id,
|
||||||
latency_ms=latency_ms,
|
latency_ms=latency_ms,
|
||||||
response=response,
|
response=response,
|
||||||
error=error_text,
|
error=error,
|
||||||
# OCR 走 MonkeyOCR 自有端点,没有推理参数可言(理由同 embedding)
|
# OCR 走 MonkeyOCR 自有端点,没有推理参数可言(理由同 embedding)
|
||||||
reasoning_applies=False,
|
reasoning_applies=False,
|
||||||
|
operation=operation,
|
||||||
|
class_prefixed_error=True,
|
||||||
)
|
)
|
||||||
|
|
||||||
@staticmethod
|
@staticmethod
|
||||||
|
|||||||
@@ -271,7 +271,7 @@ class TelemetryStatusProvider(Protocol):
|
|||||||
|
|
||||||
@runtime_checkable
|
@runtime_checkable
|
||||||
class TelemetryRecorder(Protocol):
|
class TelemetryRecorder(Protocol):
|
||||||
"""遥测后端;26 字段冻结(M1 设计 §4.4 + issue #3/#4/#11/#16/#20),唯一调用点是 TelemetryEmitter。
|
"""遥测后端;36 字段冻结(M1 设计 §4.4 + issue #3/#4/#11/#16/#20 + 1.3.5),唯一调用点是 TelemetryEmitter。
|
||||||
|
|
||||||
新增参数不设默认值: 库外无第三方实现者(三项目迁移时删除了各自的同名
|
新增参数不设默认值: 库外无第三方实现者(三项目迁移时删除了各自的同名
|
||||||
Protocol),完整签名的成本为零,而少写一列会被 emitter 的降级吞成 warning。
|
Protocol),完整签名的成本为零,而少写一列会被 emitter 的降级吞成 warning。
|
||||||
@@ -286,6 +286,15 @@ class TelemetryRecorder(Protocol):
|
|||||||
|
|
||||||
recorder 只负责落库,不做任何语义判断,与 `sampling` 列由
|
recorder 只负责落库,不做任何语义判断,与 `sampling` 列由
|
||||||
`canonical_sampling_json()` 在 emitter 侧定型是同一先例。
|
`canonical_sampling_json()` 在 emitter 侧定型是同一先例。
|
||||||
|
|
||||||
|
1.3.5 新增十列同理已在 emitter 侧定型: `operation` 是**公开方法**四值之一
|
||||||
|
(与 `PolyGatewayError.operation` 这个 HTTP 子操作是两个语义);`event_kind` 区分
|
||||||
|
attempt / cache_hit / terminal_failure 三类行;`attempts` 与 `total_latency_ms`
|
||||||
|
只在终态行非空;`error_body` 沿用 transport 侧 `summarize_body` 的上限,
|
||||||
|
**不进 `PGW_TELEMETRY_TEXT_CAP` 的覆盖面**。
|
||||||
|
|
||||||
|
**本签名是装配闸的唯一事实源**: `TelemetryEmitter.__init__` 按它派生参数名做
|
||||||
|
一次 `signature.bind` 形状校验(设计 §7),改本签名即改闸的判据。
|
||||||
"""
|
"""
|
||||||
|
|
||||||
async def record_llm_call(
|
async def record_llm_call(
|
||||||
@@ -317,4 +326,14 @@ class TelemetryRecorder(Protocol):
|
|||||||
meta: str,
|
meta: str,
|
||||||
thinking_observation: str,
|
thinking_observation: str,
|
||||||
reasoning_effort: str | None,
|
reasoning_effort: str | None,
|
||||||
|
scope: str,
|
||||||
|
operation: str,
|
||||||
|
logical_call_id: str | None,
|
||||||
|
event_kind: str,
|
||||||
|
http_status_code: int | None,
|
||||||
|
error_type: str | None,
|
||||||
|
cause_type: str | None,
|
||||||
|
error_body: str | None,
|
||||||
|
attempts: int | None,
|
||||||
|
total_latency_ms: int | None,
|
||||||
) -> None: ...
|
) -> None: ...
|
||||||
|
|||||||
@@ -5,8 +5,8 @@
|
|||||||
多处各存一份必然漂移,而漂移的表现是"下游照打印的 SQL 建完表,库仍报缺列"。
|
多处各存一份必然漂移,而漂移的表现是"下游照打印的 SQL 建完表,库仍报缺列"。
|
||||||
|
|
||||||
**`COLUMNS` 是 INSERT 字段序,不是物理列序**: 数据库自填的 `created_at` 不在其中(它带
|
**`COLUMNS` 是 INSERT 字段序,不是物理列序**: 数据库自填的 `created_at` 不在其中(它带
|
||||||
`DEFAULT now()` / `datetime('now')`,库从不显式写它)。物理表列 = 26 个 INSERT 字段 +
|
`DEFAULT now()` / `datetime('now')`,库从不显式写它)。物理表列 = 36 个 INSERT 字段 +
|
||||||
`created_at` = 27;列数断言一律按物理列数写,两套口径混用是最易错处。
|
`created_at` = 37;列数断言一律按物理列数写,两套口径混用是最易错处。
|
||||||
|
|
||||||
本模块只依赖标准库: `telemetry/` 与 `backends/`、`transports/`、`structured/` 同层且
|
本模块只依赖标准库: `telemetry/` 与 `backends/`、`transports/`、`structured/` 同层且
|
||||||
互不依赖(import-linter 契约执法)。
|
互不依赖(import-linter 契约执法)。
|
||||||
@@ -52,7 +52,17 @@ CREATE TABLE IF NOT EXISTS llm_calls (
|
|||||||
tenant_id TEXT NOT NULL DEFAULT '',
|
tenant_id TEXT NOT NULL DEFAULT '',
|
||||||
meta TEXT NOT NULL DEFAULT '{}',
|
meta TEXT NOT NULL DEFAULT '{}',
|
||||||
thinking_observation TEXT,
|
thinking_observation TEXT,
|
||||||
reasoning_effort TEXT
|
reasoning_effort TEXT,
|
||||||
|
scope TEXT,
|
||||||
|
operation TEXT,
|
||||||
|
logical_call_id TEXT,
|
||||||
|
event_kind TEXT,
|
||||||
|
http_status_code INTEGER,
|
||||||
|
error_type TEXT,
|
||||||
|
cause_type TEXT,
|
||||||
|
error_body TEXT,
|
||||||
|
attempts INTEGER,
|
||||||
|
total_latency_ms INTEGER
|
||||||
);
|
);
|
||||||
"""
|
"""
|
||||||
|
|
||||||
@@ -84,7 +94,17 @@ CREATE TABLE IF NOT EXISTS llm_calls (
|
|||||||
tenant_id TEXT NOT NULL DEFAULT '',
|
tenant_id TEXT NOT NULL DEFAULT '',
|
||||||
meta JSONB NOT NULL DEFAULT '{}'::jsonb,
|
meta JSONB NOT NULL DEFAULT '{}'::jsonb,
|
||||||
thinking_observation TEXT,
|
thinking_observation TEXT,
|
||||||
reasoning_effort TEXT
|
reasoning_effort TEXT,
|
||||||
|
scope TEXT,
|
||||||
|
operation TEXT,
|
||||||
|
logical_call_id TEXT,
|
||||||
|
event_kind TEXT,
|
||||||
|
http_status_code INTEGER,
|
||||||
|
error_type TEXT,
|
||||||
|
cause_type TEXT,
|
||||||
|
error_body TEXT,
|
||||||
|
attempts INTEGER,
|
||||||
|
total_latency_ms INTEGER
|
||||||
);
|
);
|
||||||
"""
|
"""
|
||||||
|
|
||||||
@@ -105,6 +125,18 @@ SQLITE_BACKFILL = (
|
|||||||
# 同样可空,但这里 NULL 表达的是"调用方没表态"(issue #20): 它与 'none'
|
# 同样可空,但这里 NULL 表达的是"调用方没表态"(issue #20): 它与 'none'
|
||||||
# (明确要求不推理)是两回事,折叠成任一档都等于替上游声称了它没说过的事
|
# (明确要求不推理)是两回事,折叠成任一档都等于替上游声称了它没说过的事
|
||||||
("reasoning_effort", "TEXT"),
|
("reasoning_effort", "TEXT"),
|
||||||
|
# 1.3.5 十列: 全部可空且无默认值——旧行的 NULL 表达的是"补列之前根本没记过
|
||||||
|
# 这件事",与任何哨兵值都不是一回事,故不回填(设计 §5)
|
||||||
|
("scope", "TEXT"),
|
||||||
|
("operation", "TEXT"),
|
||||||
|
("logical_call_id", "TEXT"),
|
||||||
|
("event_kind", "TEXT"),
|
||||||
|
("http_status_code", "INTEGER"),
|
||||||
|
("error_type", "TEXT"),
|
||||||
|
("cause_type", "TEXT"),
|
||||||
|
("error_body", "TEXT"),
|
||||||
|
("attempts", "INTEGER"),
|
||||||
|
("total_latency_ms", "INTEGER"),
|
||||||
)
|
)
|
||||||
|
|
||||||
# PG 补列的列定义。语句由此派生成两份文本(见下),使"库内执行的那份"与"打印给
|
# PG 补列的列定义。语句由此派生成两份文本(见下),使"库内执行的那份"与"打印给
|
||||||
@@ -120,6 +152,17 @@ _PG_BACKFILL_DECLS = (
|
|||||||
# 可空,理由同 SQLITE_BACKFILL 同名项
|
# 可空,理由同 SQLITE_BACKFILL 同名项
|
||||||
("thinking_observation", "TEXT"),
|
("thinking_observation", "TEXT"),
|
||||||
("reasoning_effort", "TEXT"),
|
("reasoning_effort", "TEXT"),
|
||||||
|
# 1.3.5 十列,列序与 SQLITE_BACKFILL 逐项对齐(两条路径的物理列序不许分叉)
|
||||||
|
("scope", "TEXT"),
|
||||||
|
("operation", "TEXT"),
|
||||||
|
("logical_call_id", "TEXT"),
|
||||||
|
("event_kind", "TEXT"),
|
||||||
|
("http_status_code", "INTEGER"),
|
||||||
|
("error_type", "TEXT"),
|
||||||
|
("cause_type", "TEXT"),
|
||||||
|
("error_body", "TEXT"),
|
||||||
|
("attempts", "INTEGER"),
|
||||||
|
("total_latency_ms", "INTEGER"),
|
||||||
)
|
)
|
||||||
|
|
||||||
# 新列排在 created_at 之后: 与旧表 ALTER 追加的位置一致(见 SQLITE_BACKFILL 同款注释)。
|
# 新列排在 created_at 之后: 与旧表 ALTER 追加的位置一致(见 SQLITE_BACKFILL 同款注释)。
|
||||||
@@ -158,6 +201,17 @@ COLUMNS = (
|
|||||||
"meta",
|
"meta",
|
||||||
"thinking_observation",
|
"thinking_observation",
|
||||||
"reasoning_effort",
|
"reasoning_effort",
|
||||||
|
# —— 1.3.5 逻辑调用统计与结构化失败诊断(issue #19/#23)——
|
||||||
|
"scope",
|
||||||
|
"operation",
|
||||||
|
"logical_call_id",
|
||||||
|
"event_kind",
|
||||||
|
"http_status_code",
|
||||||
|
"error_type",
|
||||||
|
"cause_type",
|
||||||
|
"error_body",
|
||||||
|
"attempts",
|
||||||
|
"total_latency_ms",
|
||||||
)
|
)
|
||||||
|
|
||||||
_COLUMN_SET = frozenset(COLUMNS)
|
_COLUMN_SET = frozenset(COLUMNS)
|
||||||
|
|||||||
@@ -143,7 +143,7 @@ class SQLiteRecorder:
|
|||||||
logger.warning("SQLite 遥测补列失败(写入将逐行降级): {}", exc)
|
logger.warning("SQLite 遥测补列失败(写入将逐行降级): {}", exc)
|
||||||
|
|
||||||
async def record_llm_call(self, **fields: object) -> None:
|
async def record_llm_call(self, **fields: object) -> None:
|
||||||
"""写一行遥测;字段集合即 26 字段冻结签名(ports.TelemetryRecorder)。
|
"""写一行遥测;字段集合即 36 字段冻结签名(ports.TelemetryRecorder)。
|
||||||
|
|
||||||
取值按 `self._columns`(manual 档可能已被裁剪),与 `self._insert` 的
|
取值按 `self._columns`(manual 档可能已被裁剪),与 `self._insert` 的
|
||||||
占位符同序——两者必须一起改,分开改就是把值写进错位的列。
|
占位符同序——两者必须一起改,分开改就是把值写进错位的列。
|
||||||
|
|||||||
@@ -154,18 +154,28 @@ def _classify(status: int) -> tuple[type[PolyGatewayError], str]:
|
|||||||
|
|
||||||
|
|
||||||
def _status_to_error(
|
def _status_to_error(
|
||||||
source: SourceConfig, status: int, body_text: str, headers: Mapping[str, str]
|
source: SourceConfig,
|
||||||
|
status: int,
|
||||||
|
body_text: str,
|
||||||
|
headers: Mapping[str, str],
|
||||||
|
*,
|
||||||
|
operation: str,
|
||||||
) -> Exception:
|
) -> Exception:
|
||||||
"""非 2xx → 领域错误,**全部分支**携带响应体摘要(issue #10)。
|
"""非 2xx → 领域错误,**全部分支**携带响应体摘要(issue #10)。
|
||||||
|
|
||||||
摘要只算一次,message 与 `body_text` 共用同一份串: 两份不同长度会让"遥测里
|
摘要只算一次,message 与 `body_text` 共用同一份串: 两份不同长度会让"遥测里
|
||||||
看到的"与"下游 catch 到的"对不上,排查时反而多一层困惑。
|
看到的"与"下游 catch 到的"对不上,排查时反而多一层困惑。
|
||||||
|
|
||||||
|
`operation` 是 **HTTP 子操作**词表(`chat` / `embedding` / `ocr_text` / ...),由
|
||||||
|
调用点显式给定。它曾被硬编码成 `"chat"`,而 `embed()` 的非 200 分支也走它
|
||||||
|
——于是现存所有 embedding HTTP 失败的 `exc.operation` 都是错的(1.3.5 设计 §5 I1)。
|
||||||
|
注意它与遥测新列 `operation`(公开方法四值)是**两个语义**,不做自动转换。
|
||||||
"""
|
"""
|
||||||
summary = summarize_body(body_text)
|
summary = summarize_body(body_text)
|
||||||
ctx: dict[str, Any] = {
|
ctx: dict[str, Any] = {
|
||||||
"source_name": source.name,
|
"source_name": source.name,
|
||||||
"status_code": status,
|
"status_code": status,
|
||||||
"operation": "chat",
|
"operation": operation,
|
||||||
"body_text": summary,
|
"body_text": summary,
|
||||||
}
|
}
|
||||||
if status == 429:
|
if status == 429:
|
||||||
@@ -509,7 +519,10 @@ class OpenAICompatTransport:
|
|||||||
except httpx.TransportError as exc:
|
except httpx.TransportError as exc:
|
||||||
raise TransientError(f"{source.name} 网络错误: {exc}", **ctx) from exc
|
raise TransientError(f"{source.name} 网络错误: {exc}", **ctx) from exc
|
||||||
if resp.status_code != 200:
|
if resp.status_code != 200:
|
||||||
raise _status_to_error(source, resp.status_code, resp.text, resp.headers)
|
# 历史误标修正: 本分支属 `embed()`,与上方 ctx 同为 `"embedding"`
|
||||||
|
raise _status_to_error(
|
||||||
|
source, resp.status_code, resp.text, resp.headers, operation="embedding"
|
||||||
|
)
|
||||||
return _parse_embedding_payload(resp, source, len(texts))
|
return _parse_embedding_payload(resp, source, len(texts))
|
||||||
|
|
||||||
async def _complete_stream(
|
async def _complete_stream(
|
||||||
@@ -524,7 +537,9 @@ class OpenAICompatTransport:
|
|||||||
async with client.stream("POST", url, json=payload) as resp:
|
async with client.stream("POST", url, json=payload) as resp:
|
||||||
if resp.status_code != 200:
|
if resp.status_code != 200:
|
||||||
body = (await resp.aread()).decode("utf-8", errors="replace")
|
body = (await resp.aread()).decode("utf-8", errors="replace")
|
||||||
raise _status_to_error(source, resp.status_code, body, resp.headers)
|
raise _status_to_error(
|
||||||
|
source, resp.status_code, body, resp.headers, operation="chat"
|
||||||
|
)
|
||||||
sink: dict[str, Any] = {}
|
sink: dict[str, Any] = {}
|
||||||
guarded = stream_with_liveness_timeouts(
|
guarded = stream_with_liveness_timeouts(
|
||||||
_iter_sse_deltas(resp.aiter_lines(), sink),
|
_iter_sse_deltas(resp.aiter_lines(), sink),
|
||||||
@@ -622,7 +637,9 @@ class OpenAICompatTransport:
|
|||||||
"""非流式快路径(三项目均无,库新增): 单 JSON 响应,仅 total 超时。"""
|
"""非流式快路径(三项目均无,库新增): 单 JSON 响应,仅 total 超时。"""
|
||||||
resp = await client.post(url, json=payload)
|
resp = await client.post(url, json=payload)
|
||||||
if resp.status_code != 200:
|
if resp.status_code != 200:
|
||||||
raise _status_to_error(source, resp.status_code, resp.text, resp.headers)
|
raise _status_to_error(
|
||||||
|
source, resp.status_code, resp.text, resp.headers, operation="chat"
|
||||||
|
)
|
||||||
try:
|
try:
|
||||||
body = resp.json()
|
body = resp.json()
|
||||||
except json.JSONDecodeError as exc:
|
except json.JSONDecodeError as exc:
|
||||||
|
|||||||
+107
-2
@@ -8,11 +8,12 @@ import dataclasses
|
|||||||
import json
|
import json
|
||||||
import math
|
import math
|
||||||
import re
|
import re
|
||||||
from collections.abc import Mapping
|
import uuid
|
||||||
|
from collections.abc import Callable, Mapping
|
||||||
from dataclasses import dataclass, field
|
from dataclasses import dataclass, field
|
||||||
from enum import StrEnum
|
from enum import StrEnum
|
||||||
from types import MappingProxyType
|
from types import MappingProxyType
|
||||||
from typing import Any
|
from typing import Any, Literal
|
||||||
|
|
||||||
from loguru import logger
|
from loguru import logger
|
||||||
|
|
||||||
@@ -274,6 +275,91 @@ class ThinkingObservation(StrEnum):
|
|||||||
UNKNOWN = "unknown"
|
UNKNOWN = "unknown"
|
||||||
|
|
||||||
|
|
||||||
|
CallOperation = Literal["chat", "embed", "recognize_text", "parse_layout"]
|
||||||
|
"""遥测 `operation` 列的值域: **公开方法**四值,由调用点给定。
|
||||||
|
|
||||||
|
与 `PolyGatewayError.operation`(HTTP 子操作,如 `download_result`)是**两个语义**,
|
||||||
|
不做自动转换;链路上任何位置都不得读 `exc.operation` 来填本列(设计 §5 I1/I2)。"""
|
||||||
|
|
||||||
|
CALL_OPERATIONS: tuple[CallOperation, ...] = ("chat", "embed", "recognize_text", "parse_layout")
|
||||||
|
|
||||||
|
EventKind = Literal["attempt", "cache_hit", "terminal_failure"]
|
||||||
|
"""一行遥测描述的事件形态;旧行 NULL,不回填。
|
||||||
|
|
||||||
|
终态行与 attempt 行**不是重复事实**(前者描述逻辑终态,后者描述单次尝试),
|
||||||
|
故禁止按 `error IS NOT NULL` 跨两类直接计失败调用次数(设计 §6/§8)。"""
|
||||||
|
|
||||||
|
EVENT_KINDS: tuple[EventKind, ...] = ("attempt", "cache_hit", "terminal_failure")
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class CallStats:
|
||||||
|
"""一次**公开调用**(而非单次尝试)的统计快照(设计 §3)。
|
||||||
|
|
||||||
|
四种响应各平铺三字段会立刻漂移,故收敛成单一对象并由包根导出。
|
||||||
|
第三方合成响应的 `None` 表示**未知**,不得伪造 0。
|
||||||
|
"""
|
||||||
|
|
||||||
|
logical_call_id: str
|
||||||
|
"""每次公开调用一个 UUID;重试、结构化重问、embedding 分批共享同一个。
|
||||||
|
|
||||||
|
不占用既有 `parent_call_id`(后者是调用方的业务关联,语义不变)。"""
|
||||||
|
|
||||||
|
attempts: int
|
||||||
|
"""准入后实际调用 transport 端口的次数;含免预算 429 与端口本地拒绝。
|
||||||
|
|
||||||
|
**不是 HTTP 请求条数**: OCR layout 的 POST + ZIP GET 在同一次 transport
|
||||||
|
调用内,计 1 次。缓存命中与空输入是合法的零尝试。"""
|
||||||
|
|
||||||
|
total_latency_ms: int
|
||||||
|
"""从输入校验通过到返回/异常传播前的单调时钟快照。
|
||||||
|
|
||||||
|
含缓存 IO、退避等待、准入等待、重问、分批与内联记账。
|
||||||
|
"总耗时减最后一次尝试耗时"**不等于**纯等待(含其他本地工作)。"""
|
||||||
|
|
||||||
|
|
||||||
|
class _CallContext:
|
||||||
|
"""私有可变逻辑调用上下文: 只持计数、单调时钟与终态去重位,不做 I/O。
|
||||||
|
|
||||||
|
**每调用一个实例**的单任务对象: chat 重试、结构化重问、embedding 分批
|
||||||
|
都在同一任务内串行推进,故计数无需锁。**严禁提升为 client 实例属性**
|
||||||
|
——那会让同一 client 的并发调用互相串掉计数与逻辑 ID(库铁律"纯 asyncio 中立"、
|
||||||
|
VT `evolve_llm = llm` 教训的同一形态)。
|
||||||
|
"""
|
||||||
|
|
||||||
|
__slots__ = ("_attempts", "_now", "_started", "_terminal_claimed", "logical_call_id")
|
||||||
|
|
||||||
|
def __init__(self, *, now: Callable[[], float]) -> None:
|
||||||
|
self.logical_call_id = str(uuid.uuid4())
|
||||||
|
self._now = now
|
||||||
|
self._started = now()
|
||||||
|
self._attempts = 0
|
||||||
|
self._terminal_claimed = False
|
||||||
|
|
||||||
|
def register_attempt(self) -> None:
|
||||||
|
"""transport 调用**前**登记一次尝试(含免预算 429 与端口本地拒绝)。
|
||||||
|
|
||||||
|
登记点在调用前而非成功后: 否则失败与取消的尝试会从计数里消失,
|
||||||
|
而那正是诊断时最需要看见的那几次。
|
||||||
|
"""
|
||||||
|
self._attempts += 1
|
||||||
|
|
||||||
|
def snapshot(self) -> CallStats:
|
||||||
|
"""同步冻结当前快照;**绝不 await**,可多次调用。"""
|
||||||
|
return CallStats(
|
||||||
|
logical_call_id=self.logical_call_id,
|
||||||
|
attempts=self._attempts,
|
||||||
|
total_latency_ms=int((self._now() - self._started) * 1000),
|
||||||
|
)
|
||||||
|
|
||||||
|
def claim_terminal(self) -> bool:
|
||||||
|
"""首次 `True`、其后 `False`: 保证每逻辑调用至多写一条终态行。"""
|
||||||
|
if self._terminal_claimed:
|
||||||
|
return False
|
||||||
|
self._terminal_claimed = True
|
||||||
|
return True
|
||||||
|
|
||||||
|
|
||||||
@dataclass(frozen=True)
|
@dataclass(frozen=True)
|
||||||
class LLMResponse:
|
class LLMResponse:
|
||||||
"""一次治理调用的统一响应(与三项目超集兼容,ARCH §5.1)。"""
|
"""一次治理调用的统一响应(与三项目超集兼容,ARCH §5.1)。"""
|
||||||
@@ -336,6 +422,9 @@ class LLMResponse:
|
|||||||
`None` 不是"没推理": 库不表态时也不推定模型自己的默认档——"没看见"不许说成
|
`None` 不是"没推理": 库不表态时也不推定模型自己的默认档——"没看见"不许说成
|
||||||
"发生了"(同 `thinking_observation` 的 `UNKNOWN` 一脉)。"""
|
"发生了"(同 `thinking_observation` 的 `UNKNOWN` 一脉)。"""
|
||||||
|
|
||||||
|
call_stats: CallStats | None = None
|
||||||
|
"""本次**逻辑调用**的统计快照(1.3.5);`None` = 未知,不得读成 0。"""
|
||||||
|
|
||||||
|
|
||||||
@dataclass(frozen=True)
|
@dataclass(frozen=True)
|
||||||
class ChatRequest:
|
class ChatRequest:
|
||||||
@@ -382,6 +471,16 @@ class ChatRequest:
|
|||||||
而档位要经能力表校验、要进缓存 key、要落遥测——混进直通层等于放弃这三样,
|
而档位要经能力表校验、要进缓存 key、要落遥测——混进直通层等于放弃这三样,
|
||||||
正是 issue #20 里下游手写 `extra_body` 绕过全部治理的那条路。"""
|
正是 issue #20 里下游手写 `extra_body` 绕过全部治理的那条路。"""
|
||||||
|
|
||||||
|
# —— 库内部逻辑调用上下文(1.3.5;追加在末尾,不扰动既有字段的位置构造)——
|
||||||
|
call_context: _CallContext | None = field(default=None, compare=False, repr=False)
|
||||||
|
"""库内部逻辑调用上下文;`None` = 库内现场构造的请求,遥测 `logical_call_id` 落 NULL。
|
||||||
|
|
||||||
|
`compare=False, repr=False` 不是洁癖: 进 `compare` 会让两个内容相同的请求因
|
||||||
|
"不是同一次调用"而不相等,进 `repr` 则把库内部件泄进调用方的日志。
|
||||||
|
|
||||||
|
洋葱各层经 `dataclasses.replace` 派生请求时保留**同一引用**(不是拷贝),
|
||||||
|
重试/重问/分批才能共享同一个逻辑 ID 与计数。"""
|
||||||
|
|
||||||
|
|
||||||
@dataclass(frozen=True)
|
@dataclass(frozen=True)
|
||||||
class Usage:
|
class Usage:
|
||||||
@@ -722,6 +821,8 @@ class OcrTextResult:
|
|||||||
latency_ms: int
|
latency_ms: int
|
||||||
call_id: str
|
call_id: str
|
||||||
raw: dict[str, Any]
|
raw: dict[str, Any]
|
||||||
|
call_stats: CallStats | None = None
|
||||||
|
"""本次逻辑调用的统计快照(1.3.5);`None` = 未知。"""
|
||||||
|
|
||||||
|
|
||||||
@dataclass(frozen=True)
|
@dataclass(frozen=True)
|
||||||
@@ -739,6 +840,8 @@ class OcrLayoutResult:
|
|||||||
latency_ms: int
|
latency_ms: int
|
||||||
call_id: str
|
call_id: str
|
||||||
raw: dict[str, Any]
|
raw: dict[str, Any]
|
||||||
|
call_stats: CallStats | None = None
|
||||||
|
"""本次逻辑调用的统计快照(1.3.5);`None` = 未知。"""
|
||||||
|
|
||||||
|
|
||||||
@dataclass(frozen=True)
|
@dataclass(frozen=True)
|
||||||
@@ -783,3 +886,5 @@ class EmbeddingResponse:
|
|||||||
call_id: str
|
call_id: str
|
||||||
source_name: str
|
source_name: str
|
||||||
cost: float | None = None
|
cost: float | None = None
|
||||||
|
call_stats: CallStats | None = None
|
||||||
|
"""本次逻辑调用(含全部分批)的统计快照(1.3.5);`None` = 未知。"""
|
||||||
|
|||||||
@@ -28,7 +28,7 @@ import pytest
|
|||||||
from dotenv import dotenv_values
|
from dotenv import dotenv_values
|
||||||
|
|
||||||
from polygateway.telemetry.postgres import PostgresRecorder
|
from polygateway.telemetry.postgres import PostgresRecorder
|
||||||
from polygateway.telemetry.schema import COLUMNS, telemetry_schema_sql
|
from polygateway.telemetry.schema import COLUMNS, insert_sql, telemetry_schema_sql
|
||||||
|
|
||||||
_EXPECTED_COLUMNS = [
|
_EXPECTED_COLUMNS = [
|
||||||
"call_id",
|
"call_id",
|
||||||
@@ -58,8 +58,31 @@ _EXPECTED_COLUMNS = [
|
|||||||
"meta",
|
"meta",
|
||||||
"thinking_observation",
|
"thinking_observation",
|
||||||
"reasoning_effort",
|
"reasoning_effort",
|
||||||
|
# —— 1.3.5 逻辑调用统计与结构化失败诊断的十列(issue #19/#23)——
|
||||||
|
"scope",
|
||||||
|
"operation",
|
||||||
|
"logical_call_id",
|
||||||
|
"event_kind",
|
||||||
|
"http_status_code",
|
||||||
|
"error_type",
|
||||||
|
"cause_type",
|
||||||
|
"error_body",
|
||||||
|
"attempts",
|
||||||
|
"total_latency_ms",
|
||||||
]
|
]
|
||||||
|
|
||||||
|
# 1.3.5 之前那张表的 27 个物理列(26 个 INSERT 字段 + created_at)。写成固定切片
|
||||||
|
# 而非 `[:-10]`: 后者会随下一次补列静默漂移到另一张表上,而漂移的表现是
|
||||||
|
# "旧表补列"用例悄悄改测了别的形态。
|
||||||
|
_PRE_135_COLUMNS = _EXPECTED_COLUMNS[:27]
|
||||||
|
|
||||||
|
# 1.3.4 版本的 recorder 实际写入的列(物理列去掉库从不显式写的 created_at)
|
||||||
|
_PRE_135_WRITTEN_COLUMNS = [c for c in _PRE_135_COLUMNS if c != "created_at"]
|
||||||
|
|
||||||
|
# 1.3.5 新增的十列,按 `COLUMNS`(即 INSERT 字段序)排列: manual 档告警逐字比对与
|
||||||
|
# "旧行新列为 NULL"两处共用同一份,免得两边各抄一份后各自漂移。
|
||||||
|
_CALL_OBSERVABILITY_COLUMNS = [c for c in COLUMNS if c not in _PRE_135_WRITTEN_COLUMNS]
|
||||||
|
|
||||||
|
|
||||||
def _dsn() -> str | None:
|
def _dsn() -> str | None:
|
||||||
"""读 `.env` 的 DSN 并剥掉 SQLAlchemy 风格的 `+driver` 后缀;未配置返回 None。"""
|
"""读 `.env` 的 DSN 并剥掉 SQLAlchemy 风格的 `+driver` 后缀;未配置返回 None。"""
|
||||||
@@ -92,13 +115,13 @@ async def template_admin_dsn() -> str:
|
|||||||
return value
|
return value
|
||||||
|
|
||||||
|
|
||||||
async def _record_minimal(
|
def _minimal_fields(call_id: str | None = None, **overrides) -> dict[str, object]:
|
||||||
recorder: PostgresRecorder, call_id: str | None = None, **overrides
|
"""一行最小遥测的**完整字段字典**(不写库),供 recorder 写入与旧版本进程模拟共用。
|
||||||
) -> dict[str, object]:
|
|
||||||
"""记一行最小遥测,并**返回实际提交的字段**供调用方逐列比对回读结果。
|
|
||||||
|
|
||||||
返回值不是顺手加的: 逐列断言若在测试里另抄一份期望值,抄错的那一列会以
|
独立出来不是顺手拆的: "新旧进程混写"那条用例要以 1.3.4 的列集直接发 INSERT,
|
||||||
"库写错列位"的形态误报,而漏抄的列则悄悄不被验证。
|
若它另抄一份取值,抄错的那一列会以"库写错列位"的形态误报。
|
||||||
|
|
||||||
|
调用方随后逐列比对回读结果,故返回的就是实际提交的那一份。
|
||||||
"""
|
"""
|
||||||
fields: dict[str, object] = {
|
fields: dict[str, object] = {
|
||||||
"call_id": call_id if call_id is not None else "c1",
|
"call_id": call_id if call_id is not None else "c1",
|
||||||
@@ -130,8 +153,30 @@ async def _record_minimal(
|
|||||||
"thinking_observation": "unknown",
|
"thinking_observation": "unknown",
|
||||||
# 同理: `Effort` 归一成裸 str,不表态则是 None(与 'low' 必须分得开)
|
# 同理: `Effort` 归一成裸 str,不表态则是 None(与 'low' 必须分得开)
|
||||||
"reasoning_effort": None,
|
"reasoning_effort": None,
|
||||||
|
# —— 1.3.5 十列: 默认形态即"一次普通尝试行"(与单测 `_record_minimal` 同款)——
|
||||||
|
"scope": "LLM",
|
||||||
|
"operation": "chat",
|
||||||
|
# 库内现场构造的请求没有上下文 → NULL,不造 ID
|
||||||
|
"logical_call_id": None,
|
||||||
|
"event_kind": "attempt",
|
||||||
|
# 诊断四列只在失败的 attempt 行上非空;成功行不统一填 200
|
||||||
|
"http_status_code": None,
|
||||||
|
"error_type": None,
|
||||||
|
"cause_type": None,
|
||||||
|
"error_body": None,
|
||||||
|
# 逻辑快照两列只属终态行
|
||||||
|
"attempts": None,
|
||||||
|
"total_latency_ms": None,
|
||||||
}
|
}
|
||||||
fields.update(overrides)
|
fields.update(overrides)
|
||||||
|
return fields
|
||||||
|
|
||||||
|
|
||||||
|
async def _record_minimal(
|
||||||
|
recorder: PostgresRecorder, call_id: str | None = None, **overrides
|
||||||
|
) -> dict[str, object]:
|
||||||
|
"""记一行最小遥测,并**返回实际提交的字段**供调用方逐列比对回读结果。"""
|
||||||
|
fields = _minimal_fields(call_id, **overrides)
|
||||||
await recorder.record_llm_call(**fields)
|
await recorder.record_llm_call(**fields)
|
||||||
return fields
|
return fields
|
||||||
|
|
||||||
@@ -167,6 +212,17 @@ async def _fetch(dsn: str, sql: str, *args):
|
|||||||
await conn.close()
|
await conn.close()
|
||||||
|
|
||||||
|
|
||||||
|
async def _execute_args(dsn: str, sql: str, *args) -> None:
|
||||||
|
"""带参数执行单条语句(扩展协议);用于模拟旧版本进程按旧列集发出的 INSERT。"""
|
||||||
|
import asyncpg
|
||||||
|
|
||||||
|
conn = await asyncpg.connect(dsn, timeout=10)
|
||||||
|
try:
|
||||||
|
await conn.execute(sql, *args)
|
||||||
|
finally:
|
||||||
|
await conn.close()
|
||||||
|
|
||||||
|
|
||||||
async def _execute_script(dsn: str, sql: str) -> None:
|
async def _execute_script(dsn: str, sql: str) -> None:
|
||||||
"""整段执行多语句脚本(不带参数,走简单查询协议)——模拟下游把脚本贴进 psql。"""
|
"""整段执行多语句脚本(不带参数,走简单查询协议)——模拟下游把脚本贴进 psql。"""
|
||||||
import asyncpg
|
import asyncpg
|
||||||
@@ -588,14 +644,24 @@ _PRE_TENANT_INSERT = (
|
|||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
# `_PRE_TENANT_DDL` 的物理列(23 个): 由 `_EXPECTED_COLUMNS` 去掉此后新增的四列
|
# `_PRE_TENANT_DDL` 的物理列(23 个): 由 `_EXPECTED_COLUMNS` 去掉此后新增的列
|
||||||
# 派生而非另抄一份——两份常量必然漂移,而漂移的表现是"manual 档没补列"这条断言假绿。
|
# 派生而非另抄一份——两份常量必然漂移,而漂移的表现是"manual 档没补列"这条断言假绿。
|
||||||
# 去掉后的顺序与 DDL 逐字一致(这四列在 DDL 里本就排在末尾)。
|
# 去掉后的顺序与 DDL 逐字一致(这些列在 DDL 里本就排在末尾)。
|
||||||
_PRE_TENANT_COLUMNS = [
|
_PRE_TENANT_ABSENT = (
|
||||||
c
|
"tenant_id",
|
||||||
for c in _EXPECTED_COLUMNS
|
"meta",
|
||||||
if c not in ("tenant_id", "meta", "thinking_observation", "reasoning_effort")
|
"thinking_observation",
|
||||||
]
|
"reasoning_effort",
|
||||||
|
*_CALL_OBSERVABILITY_COLUMNS,
|
||||||
|
)
|
||||||
|
|
||||||
|
_PRE_TENANT_COLUMNS = [c for c in _EXPECTED_COLUMNS if c not in _PRE_TENANT_ABSENT]
|
||||||
|
|
||||||
|
# 这张表缺的 14 个维度,按 `COLUMNS`(即告警的排列序)列出: manual 档告警逐字比对用。
|
||||||
|
# 逐字而非前缀断言,是为了让"将来漏进告警的新列"当场红(设计 §4.2 的纪律)。
|
||||||
|
_PRE_TENANT_MISSING_NOTICE = (
|
||||||
|
f"以下维度不会被记录: {', '.join(c for c in COLUMNS if c in _PRE_TENANT_ABSENT)}。"
|
||||||
|
)
|
||||||
|
|
||||||
# 回读要逐列比对的字段: 物理列去掉库从不显式写的 created_at,恰好 22 个
|
# 回读要逐列比对的字段: 物理列去掉库从不显式写的 created_at,恰好 22 个
|
||||||
_PRE_TENANT_WRITTEN_COLUMNS = [c for c in _PRE_TENANT_COLUMNS if c != "created_at"]
|
_PRE_TENANT_WRITTEN_COLUMNS = [c for c in _PRE_TENANT_COLUMNS if c != "created_at"]
|
||||||
@@ -703,7 +769,7 @@ class TestCallerDimensionsAcceptance:
|
|||||||
"WHERE table_schema = $1 AND table_name = 'llm_calls' ORDER BY ordinal_position",
|
"WHERE table_schema = $1 AND table_name = 'llm_calls' ORDER BY ordinal_position",
|
||||||
schema,
|
schema,
|
||||||
)
|
)
|
||||||
# 22 → 26 个 recorder 字段(加 created_at 共 27 个物理列),且新列追加在末尾
|
# 22 → 36 个 recorder 字段(加 created_at 共 37 个物理列),且新列追加在末尾
|
||||||
assert [r["column_name"] for r in cols] == _EXPECTED_COLUMNS
|
assert [r["column_name"] for r in cols] == _EXPECTED_COLUMNS
|
||||||
rows = await _fetch(
|
rows = await _fetch(
|
||||||
schema_dsn,
|
schema_dsn,
|
||||||
@@ -908,11 +974,8 @@ class TestManualSchemaModeAcceptance:
|
|||||||
assert [m for m in captured_warnings if "补列失败" in m] == []
|
assert [m for m in captured_warnings if "补列失败" in m] == []
|
||||||
notices = [m for m in captured_warnings if "auto_migrate=False" in m]
|
notices = [m for m in captured_warnings if "auto_migrate=False" in m]
|
||||||
assert len(notices) == 1 # 准备期一次讲清,不逐行刷屏
|
assert len(notices) == 1 # 准备期一次讲清,不逐行刷屏
|
||||||
# 逐字钉住四个维度: 前缀断言会让将来漏进告警的新列照样绿
|
# 逐字钉住缺的每一个维度: 前缀断言会让将来漏进告警的新列照样绿
|
||||||
assert (
|
assert _PRE_TENANT_MISSING_NOTICE in notices[0]
|
||||||
"以下维度不会被记录: tenant_id, meta, thinking_observation, reasoning_effort。"
|
|
||||||
in notices[0]
|
|
||||||
)
|
|
||||||
finally:
|
finally:
|
||||||
await recorder.aclose()
|
await recorder.aclose()
|
||||||
|
|
||||||
@@ -938,11 +1001,8 @@ class TestManualSchemaModeAcceptance:
|
|||||||
assert recorder.telemetry_status.degraded is False
|
assert recorder.telemetry_status.degraded is False
|
||||||
notices = [m for m in captured_warnings if "auto_migrate=False" in m]
|
notices = [m for m in captured_warnings if "auto_migrate=False" in m]
|
||||||
assert len(notices) == 1 # 准备期一次,第二行不再重复
|
assert len(notices) == 1 # 准备期一次,第二行不再重复
|
||||||
# 逐字钉住四个维度: 前缀断言会让将来漏进告警的新列照样绿
|
# 逐字钉住缺的每一个维度: 前缀断言会让将来漏进告警的新列照样绿
|
||||||
assert (
|
assert _PRE_TENANT_MISSING_NOTICE in notices[0]
|
||||||
"以下维度不会被记录: tenant_id, meta, thinking_observation, reasoning_effort。"
|
|
||||||
in notices[0]
|
|
||||||
)
|
|
||||||
# 提示里的 SQL 必须可直接粘贴执行,而不是只报个列名
|
# 提示里的 SQL 必须可直接粘贴执行,而不是只报个列名
|
||||||
assert (
|
assert (
|
||||||
"ALTER TABLE llm_calls ADD COLUMN tenant_id TEXT NOT NULL DEFAULT '';" in notices[0]
|
"ALTER TABLE llm_calls ADD COLUMN tenant_id TEXT NOT NULL DEFAULT '';" in notices[0]
|
||||||
@@ -974,6 +1034,283 @@ class TestManualSchemaModeAcceptance:
|
|||||||
await recorder.aclose()
|
await recorder.aclose()
|
||||||
|
|
||||||
|
|
||||||
|
# 1.3.5 之前(1.3.4 发布形态)的表: 26 个 recorder 字段 + created_at = 27 个物理列,
|
||||||
|
# 没有本版新增的任何一列。裸表名: 由 `pg_sandbox` 在沙箱 schema 的 search_path 下执行。
|
||||||
|
_PRE_135_DDL = """
|
||||||
|
CREATE TABLE llm_calls (
|
||||||
|
call_id TEXT PRIMARY KEY,
|
||||||
|
parent_call_id TEXT,
|
||||||
|
session_id TEXT,
|
||||||
|
model TEXT NOT NULL,
|
||||||
|
provider TEXT NOT NULL,
|
||||||
|
source_name TEXT NOT NULL,
|
||||||
|
messages TEXT NOT NULL,
|
||||||
|
response TEXT NOT NULL,
|
||||||
|
thinking TEXT NOT NULL DEFAULT '',
|
||||||
|
prompt_tokens INTEGER NOT NULL,
|
||||||
|
completion_tokens INTEGER NOT NULL,
|
||||||
|
usage_source TEXT NOT NULL,
|
||||||
|
latency_ms INTEGER NOT NULL,
|
||||||
|
ttft_ms DOUBLE PRECISION,
|
||||||
|
max_inter_token_ms DOUBLE PRECISION,
|
||||||
|
cache_hit BOOLEAN NOT NULL DEFAULT FALSE,
|
||||||
|
error TEXT,
|
||||||
|
cost DOUBLE PRECISION,
|
||||||
|
created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
||||||
|
cached_prompt_tokens INTEGER,
|
||||||
|
model_reported TEXT,
|
||||||
|
sampling TEXT,
|
||||||
|
reasoning_tokens INTEGER,
|
||||||
|
tenant_id TEXT NOT NULL DEFAULT '',
|
||||||
|
meta JSONB NOT NULL DEFAULT '{}'::jsonb,
|
||||||
|
thinking_observation TEXT,
|
||||||
|
reasoning_effort TEXT
|
||||||
|
)
|
||||||
|
"""
|
||||||
|
|
||||||
|
# 一行 1.3.5 之前写下的历史数据(只列 NOT NULL 列,与当年 recorder 的写入等价)。
|
||||||
|
# 工厂的 `extra` 逐条裸执行、不接受查询参数,故 call_id 内联成字面量。
|
||||||
|
_PRE_135_INSERT = (
|
||||||
|
"INSERT INTO llm_calls (call_id, model, provider, source_name, messages, response, "
|
||||||
|
"prompt_tokens, completion_tokens, usage_source, latency_ms) "
|
||||||
|
"VALUES ('pre135', 'm', 'p', 's1', '[]', 'old body', 1, 2, 'measured', 10)"
|
||||||
|
)
|
||||||
|
|
||||||
|
# 这张表缺的正是本版十列;manual 档告警要逐字比对的那句。
|
||||||
|
_PRE_135_MISSING_NOTICE = f"以下维度不会被记录: {', '.join(_CALL_OBSERVABILITY_COLUMNS)}。"
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.fixture
|
||||||
|
async def pre_135_schema(pg_sandbox) -> tuple[str, str]:
|
||||||
|
"""一次性沙箱里造一张 **1.3.4 形态的 27 列表**,并留一行本版之前的历史数据。
|
||||||
|
|
||||||
|
共享表 `llm_calls` 一个字节都不碰: 本机那张表升级一次就再也回不到旧形态,
|
||||||
|
指望它还是旧形态的测试第二次跑就会空转(与 `pre_tenant_schema` 同款理由)。
|
||||||
|
"""
|
||||||
|
sandbox = await pg_sandbox(ddl=_PRE_135_DDL, extra=(_PRE_135_INSERT,))
|
||||||
|
return sandbox.dsn, sandbox.schema
|
||||||
|
|
||||||
|
|
||||||
|
class TestCallObservabilityColumnsAcceptance:
|
||||||
|
"""1.3.5(issue #19/#23)的 PG 存储兼容验收: auto 追加 / manual 裁剪 / 旧行 NULL / 混写。
|
||||||
|
|
||||||
|
单元层在 SQLite 上断的是同一族语义,这里断的是**真实 PG 上确实如此**——
|
||||||
|
两端的 DDL、补列语句与列序是两份文本(`SQLITE_BACKFILL` 与 `_PG_BACKFILL_DECLS`),
|
||||||
|
只有真表能证明它们没有分叉。
|
||||||
|
"""
|
||||||
|
|
||||||
|
async def test_pre_135_table_gains_the_ten_columns_and_old_rows_stay_null(self, pre_135_schema):
|
||||||
|
"""27 列旧表 auto 补齐到 37 列,新行两类取值读得回,**历史行十列一律 NULL**。
|
||||||
|
|
||||||
|
旧行不回填是本版的明示决策(设计 §5): NULL 表达的是"补列之前根本没记过
|
||||||
|
这件事",与任何哨兵值都不是一回事。若哪天有人给这十列加了 DEFAULT,历史行
|
||||||
|
会被就地改写成"记过且值为 X",归因查询从此分不清真实缺口——故这条断言的
|
||||||
|
方向是 NULL,不是空串也不是 0。
|
||||||
|
"""
|
||||||
|
schema_dsn, schema = pre_135_schema
|
||||||
|
recorder = _recorder(schema_dsn, auto_migrate=True)
|
||||||
|
try:
|
||||||
|
# attempt 行: 诊断四列非空、逻辑快照两列 NULL
|
||||||
|
await _record_minimal(
|
||||||
|
recorder,
|
||||||
|
call_id="att",
|
||||||
|
scope="LLM",
|
||||||
|
operation="chat",
|
||||||
|
logical_call_id="lcid-1",
|
||||||
|
event_kind="attempt",
|
||||||
|
http_status_code=503,
|
||||||
|
error_type="TransientError",
|
||||||
|
cause_type="ReadTimeout",
|
||||||
|
error_body="upstream said 503",
|
||||||
|
)
|
||||||
|
# 终态行: 逻辑快照两列非空、诊断三列 NULL(不搬最后一次 attempt 的现场)
|
||||||
|
await _record_minimal(
|
||||||
|
recorder,
|
||||||
|
call_id="term",
|
||||||
|
scope="LLM",
|
||||||
|
operation="chat",
|
||||||
|
logical_call_id="lcid-1",
|
||||||
|
event_kind="terminal_failure",
|
||||||
|
error="AllSourcesExhausted: 全部源已耗尽",
|
||||||
|
error_type="AllSourcesExhausted",
|
||||||
|
attempts=3,
|
||||||
|
total_latency_ms=4200,
|
||||||
|
)
|
||||||
|
cols = await _fetch(
|
||||||
|
schema_dsn,
|
||||||
|
"SELECT column_name FROM information_schema.columns "
|
||||||
|
"WHERE table_schema = $1 AND table_name = 'llm_calls' ORDER BY ordinal_position",
|
||||||
|
schema,
|
||||||
|
)
|
||||||
|
# 26 → 36 个 recorder 字段(加 created_at 共 37 个物理列),新列追加在末尾:
|
||||||
|
# 列序与新建库一致才不会让两条升级路径分叉
|
||||||
|
assert [r["column_name"] for r in cols] == _EXPECTED_COLUMNS
|
||||||
|
|
||||||
|
names = ", ".join(_CALL_OBSERVABILITY_COLUMNS)
|
||||||
|
rows = await _fetch(
|
||||||
|
schema_dsn,
|
||||||
|
f"SELECT call_id, {names} FROM llm_calls "
|
||||||
|
"WHERE call_id = ANY($1::text[]) ORDER BY call_id",
|
||||||
|
["att", "pre135", "term"],
|
||||||
|
)
|
||||||
|
by_id = {r["call_id"]: r for r in rows}
|
||||||
|
|
||||||
|
assert dict(by_id["att"]) == {
|
||||||
|
"call_id": "att",
|
||||||
|
"scope": "LLM",
|
||||||
|
"operation": "chat",
|
||||||
|
"logical_call_id": "lcid-1",
|
||||||
|
"event_kind": "attempt",
|
||||||
|
"http_status_code": 503,
|
||||||
|
"error_type": "TransientError",
|
||||||
|
"cause_type": "ReadTimeout",
|
||||||
|
"error_body": "upstream said 503",
|
||||||
|
"attempts": None,
|
||||||
|
"total_latency_ms": None,
|
||||||
|
}
|
||||||
|
assert dict(by_id["term"]) == {
|
||||||
|
"call_id": "term",
|
||||||
|
"scope": "LLM",
|
||||||
|
"operation": "chat",
|
||||||
|
"logical_call_id": "lcid-1",
|
||||||
|
"event_kind": "terminal_failure",
|
||||||
|
"http_status_code": None,
|
||||||
|
"error_type": "AllSourcesExhausted",
|
||||||
|
"cause_type": None,
|
||||||
|
"error_body": None,
|
||||||
|
"attempts": 3,
|
||||||
|
"total_latency_ms": 4200,
|
||||||
|
}
|
||||||
|
# 历史行: 十列逐列 NULL(整体比对,漏掉任一列都红)
|
||||||
|
assert dict(by_id["pre135"]) == {
|
||||||
|
"call_id": "pre135",
|
||||||
|
**dict.fromkeys(_CALL_OBSERVABILITY_COLUMNS),
|
||||||
|
}
|
||||||
|
finally:
|
||||||
|
await recorder.aclose()
|
||||||
|
|
||||||
|
async def test_manual_trims_the_insert_on_a_pre_135_table(
|
||||||
|
self, pre_135_schema, captured_warnings
|
||||||
|
):
|
||||||
|
"""27 列旧表 + manual: 一条 DDL 都不发,写入按现有列裁剪后照样落库。
|
||||||
|
|
||||||
|
与上一条恰成对照: 同一张表、同一份负载,只有 `auto_migrate` 不同,列数就必须是
|
||||||
|
27 与 37 之别。裁剪是关掉 ALTER 的前提——不裁剪的话每行 INSERT 都撞缺列
|
||||||
|
(SQLSTATE 42703)而被整行丢弃,那是把自动补列换成遥测静默全失。
|
||||||
|
"""
|
||||||
|
schema_dsn, schema = pre_135_schema
|
||||||
|
recorder = _recorder(schema_dsn, auto_migrate=False)
|
||||||
|
try:
|
||||||
|
recorded = await _record_minimal(
|
||||||
|
recorder, call_id="man135", scope="LLM", logical_call_id="lcid-x"
|
||||||
|
)
|
||||||
|
cols = await _fetch(
|
||||||
|
schema_dsn,
|
||||||
|
"SELECT column_name FROM information_schema.columns "
|
||||||
|
"WHERE table_schema = $1 AND table_name = 'llm_calls' ORDER BY ordinal_position",
|
||||||
|
schema,
|
||||||
|
)
|
||||||
|
# 表结构逐字不动: 既没多出十列,也没被顺手改了列序
|
||||||
|
assert [r["column_name"] for r in cols] == _PRE_135_COLUMNS
|
||||||
|
|
||||||
|
names = ", ".join(_PRE_135_WRITTEN_COLUMNS)
|
||||||
|
rows = await _fetch(
|
||||||
|
schema_dsn, f"SELECT {names} FROM llm_calls WHERE call_id = $1", "man135"
|
||||||
|
)
|
||||||
|
assert len(rows) == 1 # 裁剪后的 INSERT 真写进去了,不是被 PG 拒收
|
||||||
|
# 其余 26 列逐列与提交值相等: 少写十列最容易引发的错是剩下的值整体错位
|
||||||
|
assert dict(rows[0]) == {c: recorded[c] for c in _PRE_135_WRITTEN_COLUMNS}
|
||||||
|
|
||||||
|
assert [m for m in captured_warnings if "写入失败" in m] == []
|
||||||
|
assert [m for m in captured_warnings if "补列失败" in m] == []
|
||||||
|
assert recorder.telemetry_status.degraded is False
|
||||||
|
notices = [m for m in captured_warnings if "auto_migrate=False" in m]
|
||||||
|
assert len(notices) == 1 # 准备期一次讲清,不逐行刷屏
|
||||||
|
# 逐字钉住十个维度: 前缀断言会让将来漏进告警的新列照样绿
|
||||||
|
assert _PRE_135_MISSING_NOTICE in notices[0]
|
||||||
|
# 提示里的 SQL 必须可直接粘贴执行(首列与末列各验一条,含类型)
|
||||||
|
assert "ALTER TABLE llm_calls ADD COLUMN scope TEXT;" in notices[0]
|
||||||
|
assert "ALTER TABLE llm_calls ADD COLUMN total_latency_ms INTEGER;" in notices[0]
|
||||||
|
finally:
|
||||||
|
await recorder.aclose()
|
||||||
|
|
||||||
|
async def test_old_and_new_writers_share_one_table(self, fresh_schema, captured_warnings):
|
||||||
|
"""滚动升级期的混写: 已补列的表上,旧版本进程按 26 列写、新版本按 36 列写。
|
||||||
|
|
||||||
|
这是升级窗口里必然出现的形态(先升一个 worker,其余仍是 1.3.4),而它的失败
|
||||||
|
方式是静默的: 若新列带了 NOT NULL 或旧列集的 INSERT 被拒,旧 worker 的遥测
|
||||||
|
会整段消失而只留逐行 warning。故这里既断三行都在、也断没有写入失败 warning。
|
||||||
|
|
||||||
|
旧进程用 `insert_sql("postgres", 旧列集)` 而不是另抄一条 SQL: 1.3.4 的
|
||||||
|
recorder 发出的正是同一函数按当年列集拼出的语句,另抄一份只会各自漂移。
|
||||||
|
"""
|
||||||
|
fresh_dsn, schema = fresh_schema
|
||||||
|
recorder = _recorder(fresh_dsn, auto_migrate=True)
|
||||||
|
try:
|
||||||
|
# 新版本进程: 建表(37 列)并写一条带完整新列的终态行
|
||||||
|
await _record_minimal(
|
||||||
|
recorder,
|
||||||
|
call_id="new-1",
|
||||||
|
scope="LLM",
|
||||||
|
operation="chat",
|
||||||
|
logical_call_id="lcid-mix",
|
||||||
|
event_kind="terminal_failure",
|
||||||
|
error_type="AllSourcesExhausted",
|
||||||
|
attempts=2,
|
||||||
|
total_latency_ms=1500,
|
||||||
|
)
|
||||||
|
|
||||||
|
# 旧版本进程: 同一张表,按 1.3.4 的 26 列集写入
|
||||||
|
legacy_fields = _minimal_fields("old-1", response="from a 1.3.4 worker")
|
||||||
|
await _execute_args(
|
||||||
|
fresh_dsn,
|
||||||
|
insert_sql("postgres", _PRE_135_WRITTEN_COLUMNS),
|
||||||
|
*(legacy_fields[c] for c in _PRE_135_WRITTEN_COLUMNS),
|
||||||
|
)
|
||||||
|
|
||||||
|
# 新版本进程继续写: 旧进程的写入不得污染后续(列集是每进程各自探测的)
|
||||||
|
await _record_minimal(
|
||||||
|
recorder, call_id="new-2", scope="LLM", operation="embed", event_kind="attempt"
|
||||||
|
)
|
||||||
|
|
||||||
|
cols = await _fetch(
|
||||||
|
fresh_dsn,
|
||||||
|
"SELECT column_name FROM information_schema.columns "
|
||||||
|
"WHERE table_schema = $1 AND table_name = 'llm_calls' ORDER BY ordinal_position",
|
||||||
|
schema,
|
||||||
|
)
|
||||||
|
assert [r["column_name"] for r in cols] == _EXPECTED_COLUMNS # 旧进程不改表结构
|
||||||
|
|
||||||
|
rows = await _fetch(
|
||||||
|
fresh_dsn,
|
||||||
|
"SELECT call_id, response, scope, operation, event_kind, attempts, "
|
||||||
|
"total_latency_ms FROM llm_calls ORDER BY call_id",
|
||||||
|
)
|
||||||
|
assert [r["call_id"] for r in rows] == ["new-1", "new-2", "old-1"]
|
||||||
|
by_id = {r["call_id"]: r for r in rows}
|
||||||
|
assert by_id["old-1"]["response"] == "from a 1.3.4 worker"
|
||||||
|
# 旧进程写下的行,新列一律 NULL——它没写,也不该被谁替它填
|
||||||
|
assert (by_id["old-1"]["scope"], by_id["old-1"]["event_kind"]) == (None, None)
|
||||||
|
assert (by_id["old-1"]["attempts"], by_id["old-1"]["total_latency_ms"]) == (None, None)
|
||||||
|
assert (by_id["new-1"]["attempts"], by_id["new-1"]["total_latency_ms"]) == (2, 1500)
|
||||||
|
assert by_id["new-2"]["operation"] == "embed"
|
||||||
|
assert [m for m in captured_warnings if "写入失败" in m] == []
|
||||||
|
|
||||||
|
# 下游可见变化的机械化依据: 新口径"计失败调用"按 event_kind 过滤,
|
||||||
|
# 混写期旧行(event_kind 为 NULL)既不会被误计成失败,也不会被误计成成功
|
||||||
|
terminal = await _fetch(
|
||||||
|
fresh_dsn,
|
||||||
|
"SELECT count(*) AS n FROM llm_calls WHERE event_kind = 'terminal_failure'",
|
||||||
|
)
|
||||||
|
assert terminal[0]["n"] == 1
|
||||||
|
unclassified = await _fetch(
|
||||||
|
fresh_dsn, "SELECT count(*) AS n FROM llm_calls WHERE event_kind IS NULL"
|
||||||
|
)
|
||||||
|
assert unclassified[0]["n"] == 1
|
||||||
|
finally:
|
||||||
|
await recorder.aclose()
|
||||||
|
|
||||||
|
|
||||||
_PHYSICAL_COLUMNS_SQL = (
|
_PHYSICAL_COLUMNS_SQL = (
|
||||||
"SELECT column_name FROM information_schema.columns "
|
"SELECT column_name FROM information_schema.columns "
|
||||||
"WHERE table_schema = $1 AND table_name = 'llm_calls' ORDER BY ordinal_position"
|
"WHERE table_schema = $1 AND table_name = 'llm_calls' ORDER BY ordinal_position"
|
||||||
@@ -1000,7 +1337,7 @@ class TestPublishedSchemaScript:
|
|||||||
|
|
||||||
await _execute_script(fresh_dsn, script)
|
await _execute_script(fresh_dsn, script)
|
||||||
actual = [r["column_name"] for r in await _fetch(fresh_dsn, _PHYSICAL_COLUMNS_SQL, schema)]
|
actual = [r["column_name"] for r in await _fetch(fresh_dsn, _PHYSICAL_COLUMNS_SQL, schema)]
|
||||||
# 物理列 = 26 个 INSERT 字段 + 库从不显式写的 created_at;对着库常量比,不另抄一份
|
# 物理列 = 36 个 INSERT 字段 + 库从不显式写的 created_at;对着库常量比,不另抄一份
|
||||||
assert set(actual) == set(COLUMNS) | {"created_at"}
|
assert set(actual) == set(COLUMNS) | {"created_at"}
|
||||||
# 列序也不许漂: 新列必须排在 created_at 之后,否则新建库与 ALTER 升级的列序分叉
|
# 列序也不许漂: 新列必须排在 created_at 之后,否则新建库与 ALTER 升级的列序分叉
|
||||||
assert actual == _EXPECTED_COLUMNS
|
assert actual == _EXPECTED_COLUMNS
|
||||||
|
|||||||
@@ -570,7 +570,7 @@ class TestTelemetryCapDoesNotPoisonTheCacheKey:
|
|||||||
before = build_cache_key("m", messages, "proj", None)
|
before = build_cache_key("m", messages, "proj", None)
|
||||||
|
|
||||||
rec = self._Rows()
|
rec = self._Rows()
|
||||||
await TelemetryEmitter(rec, text_cap=8).emit_attempt(
|
await TelemetryEmitter(rec, text_cap=8, scope="LLM").emit_attempt(
|
||||||
request=ChatRequest(messages=messages),
|
request=ChatRequest(messages=messages),
|
||||||
source=SourceConfig(
|
source=SourceConfig(
|
||||||
name="s1",
|
name="s1",
|
||||||
@@ -585,6 +585,7 @@ class TestTelemetryCapDoesNotPoisonTheCacheKey:
|
|||||||
response=_resp(),
|
response=_resp(),
|
||||||
error=None,
|
error=None,
|
||||||
reasoning_applies=True,
|
reasoning_applies=True,
|
||||||
|
operation="chat",
|
||||||
)
|
)
|
||||||
# 截断确实发生了(否则本用例恒真)
|
# 截断确实发生了(否则本用例恒真)
|
||||||
logged = json.loads(rec.rows[0]["messages"])
|
logged = json.loads(rec.rows[0]["messages"])
|
||||||
@@ -818,3 +819,75 @@ class TestExplicitCacheMigration:
|
|||||||
finally:
|
finally:
|
||||||
for transport in transports:
|
for transport in transports:
|
||||||
await transport.aclose()
|
await transport.aclose()
|
||||||
|
|
||||||
|
|
||||||
|
class TestCallStatsNotPoisoned:
|
||||||
|
"""缓存不得回放历史统计(1.3.5 设计 §3)。
|
||||||
|
|
||||||
|
统计描述**本次**调用;把上次那条存进去再放出来,等于对调用方谎称这次
|
||||||
|
重试了 N 次、耗了 M 毫秒。
|
||||||
|
"""
|
||||||
|
|
||||||
|
async def test_serialized_payload_carries_no_call_stats_key(self):
|
||||||
|
from polygateway.types import CallStats
|
||||||
|
|
||||||
|
backend = InMemoryCache()
|
||||||
|
mw = _mw(backend)
|
||||||
|
stats = CallStats(logical_call_id="lc-1", attempts=3, total_latency_ms=900)
|
||||||
|
terminal = _Terminal(_resp(call_stats=stats))
|
||||||
|
await mw(ChatRequest(messages=_MSGS), terminal)
|
||||||
|
key = build_cache_key("m", _MSGS, "proj", None)
|
||||||
|
stored = json.loads(await backend.get(key))
|
||||||
|
assert "call_stats" not in stored # asdict 会把它摊成 dict,必须显式剔除
|
||||||
|
|
||||||
|
async def test_historic_dict_never_impersonates_call_stats(self):
|
||||||
|
"""旧条目里的 `call_stats` dict 会被 `_RESPONSE_FIELDS` 放行,必须显式覆盖。
|
||||||
|
|
||||||
|
不覆盖就会有一个 dict 冒充 `CallStats` 从公共 API 漏给调用方,
|
||||||
|
`resp.call_stats.attempts` 当场 `AttributeError`。
|
||||||
|
"""
|
||||||
|
backend = InMemoryCache()
|
||||||
|
mw = _mw(backend)
|
||||||
|
key = build_cache_key("m", _MSGS, "proj", None)
|
||||||
|
poisoned = {
|
||||||
|
"content": "legacy",
|
||||||
|
"thinking": "",
|
||||||
|
"model": "m",
|
||||||
|
"provider": "p",
|
||||||
|
"prompt_tokens": 1,
|
||||||
|
"completion_tokens": 2,
|
||||||
|
"latency_ms": 30,
|
||||||
|
"ttft_ms": 5.0,
|
||||||
|
"max_inter_token_ms": 2.0,
|
||||||
|
"cache_hit": False,
|
||||||
|
"call_id": "orig",
|
||||||
|
"source_name": "s1",
|
||||||
|
"usage_source": "measured",
|
||||||
|
"call_stats": {
|
||||||
|
"logical_call_id": "stale-lc",
|
||||||
|
"attempts": 7,
|
||||||
|
"total_latency_ms": 9999,
|
||||||
|
},
|
||||||
|
}
|
||||||
|
await backend.set(key, json.dumps(poisoned), ttl_s=100)
|
||||||
|
terminal = _Terminal(_resp())
|
||||||
|
hit = await mw(ChatRequest(messages=_MSGS), terminal)
|
||||||
|
assert hit.content == "legacy" and terminal.calls == 0 # 真的走了缓存
|
||||||
|
assert hit.call_stats is None # dict 不得冒充 CallStats
|
||||||
|
|
||||||
|
async def test_cache_key_is_unchanged_by_the_new_field(self):
|
||||||
|
"""新增内部字段不得扰动 key 公式,否则存量缓存全量冷启动(黄金值)。"""
|
||||||
|
from polygateway.types import _CallContext
|
||||||
|
|
||||||
|
class _Clock:
|
||||||
|
def __call__(self):
|
||||||
|
return 1000.0
|
||||||
|
|
||||||
|
ctx = _CallContext(now=_Clock())
|
||||||
|
bare = build_cache_key("m", _MSGS, "proj", None)
|
||||||
|
assert bare == build_cache_key("m", _MSGS, "proj", None)
|
||||||
|
# 带上下文的请求与不带的请求必须落在同一个 key 上
|
||||||
|
with_ctx = ChatRequest(messages=_MSGS, call_context=ctx)
|
||||||
|
without = ChatRequest(messages=_MSGS)
|
||||||
|
assert with_ctx.cache_namespace == without.cache_namespace
|
||||||
|
assert digest_messages(with_ctx.messages) == digest_messages(without.messages)
|
||||||
|
|||||||
+356
-1
@@ -13,6 +13,7 @@ from polygateway import (
|
|||||||
GatewayClient,
|
GatewayClient,
|
||||||
GatewaySettings,
|
GatewaySettings,
|
||||||
RequestRejectedError,
|
RequestRejectedError,
|
||||||
|
ResultInvalidError,
|
||||||
gather_bounded,
|
gather_bounded,
|
||||||
)
|
)
|
||||||
from polygateway.backends.memory.breaker import InMemoryGate
|
from polygateway.backends.memory.breaker import InMemoryGate
|
||||||
@@ -25,6 +26,7 @@ from polygateway.transports.openai_compat import OpenAICompatTransport
|
|||||||
from polygateway.types import (
|
from polygateway.types import (
|
||||||
BackpressurePolicy,
|
BackpressurePolicy,
|
||||||
BreakerConfig,
|
BreakerConfig,
|
||||||
|
ChatRequest,
|
||||||
Effort,
|
Effort,
|
||||||
GlobalLimits,
|
GlobalLimits,
|
||||||
RetryPolicy,
|
RetryPolicy,
|
||||||
@@ -846,11 +848,19 @@ _CACHE_ENV = dict(
|
|||||||
|
|
||||||
|
|
||||||
class _Closable:
|
class _Closable:
|
||||||
"""记 close 次数的假组件;所有权纪律的唯一观测点。"""
|
"""记 close 次数的假组件;所有权纪律的唯一观测点。
|
||||||
|
|
||||||
|
带 `record_llm_call(**fields)` 是因为它也被当作注入的 telemetry recorder 用:
|
||||||
|
1.3.5 的装配闸在构造期就会拒掉不满足 `TelemetryRecorder` 的对象
|
||||||
|
(否则下游升级后 100% 丢遥测而调用照常成功)。`**fields` 形态天然兼容。
|
||||||
|
"""
|
||||||
|
|
||||||
def __init__(self):
|
def __init__(self):
|
||||||
self.closed = 0
|
self.closed = 0
|
||||||
|
|
||||||
|
async def record_llm_call(self, **fields):
|
||||||
|
pass
|
||||||
|
|
||||||
async def aclose(self):
|
async def aclose(self):
|
||||||
self.closed += 1
|
self.closed += 1
|
||||||
|
|
||||||
@@ -861,6 +871,9 @@ class _SyncClosable:
|
|||||||
def __init__(self):
|
def __init__(self):
|
||||||
self.closed = 0
|
self.closed = 0
|
||||||
|
|
||||||
|
async def record_llm_call(self, **fields):
|
||||||
|
pass
|
||||||
|
|
||||||
def close(self):
|
def close(self):
|
||||||
self.closed += 1
|
self.closed += 1
|
||||||
|
|
||||||
@@ -1362,3 +1375,345 @@ async def test_synthetic_runtime_protocol_and_legacy_call_signatures():
|
|||||||
assert client._transport._clients == {}
|
assert client._transport._clients == {}
|
||||||
finally:
|
finally:
|
||||||
await client.aclose()
|
await client.aclose()
|
||||||
|
|
||||||
|
|
||||||
|
class _StatsClock:
|
||||||
|
"""确定性单调钟;测试主动推进以断言"哪些区段计入了总耗时"。"""
|
||||||
|
|
||||||
|
def __init__(self, start=1000.0):
|
||||||
|
self.t = start
|
||||||
|
|
||||||
|
def __call__(self):
|
||||||
|
return self.t
|
||||||
|
|
||||||
|
def advance(self, seconds):
|
||||||
|
self.t += seconds
|
||||||
|
|
||||||
|
|
||||||
|
class _TickingCache:
|
||||||
|
"""假缓存后端: 每次 IO 推进注入钟。
|
||||||
|
|
||||||
|
不推进时钟的替身会让"缓存 IO 计入总耗时"的断言退化成恒等于 0 的空转绿
|
||||||
|
(计划 §T1 替身构造要求)。
|
||||||
|
"""
|
||||||
|
|
||||||
|
def __init__(self, clock, tick=0.25):
|
||||||
|
self._clock = clock
|
||||||
|
self._tick = tick
|
||||||
|
self._data = {}
|
||||||
|
|
||||||
|
async def get(self, key):
|
||||||
|
self._clock.advance(self._tick)
|
||||||
|
return self._data.get(key)
|
||||||
|
|
||||||
|
async def set(self, key, value, ttl_s):
|
||||||
|
self._clock.advance(self._tick)
|
||||||
|
self._data[key] = value
|
||||||
|
|
||||||
|
|
||||||
|
class _TickingRecorder:
|
||||||
|
"""假 recorder: 写入时推进注入钟,用于断言内联遥测收尾计入总耗时。"""
|
||||||
|
|
||||||
|
def __init__(self, clock, tick=0.5):
|
||||||
|
self._clock = clock
|
||||||
|
self._tick = tick
|
||||||
|
self.rows = []
|
||||||
|
|
||||||
|
async def record_llm_call(self, **fields):
|
||||||
|
self._clock.advance(self._tick)
|
||||||
|
self.rows.append(fields)
|
||||||
|
|
||||||
|
|
||||||
|
class TestLogicalCallStats:
|
||||||
|
"""一次公开 chat 调用的统计(1.3.5 设计 §3)。"""
|
||||||
|
|
||||||
|
_MSG = [{"role": "user", "content": "hi"}]
|
||||||
|
|
||||||
|
async def test_success_reports_one_attempt(self):
|
||||||
|
async with _client() as client:
|
||||||
|
resp = await client.chat(self._MSG)
|
||||||
|
assert resp.call_stats is not None
|
||||||
|
assert resp.call_stats.attempts == 1
|
||||||
|
assert resp.call_stats.logical_call_id
|
||||||
|
|
||||||
|
async def test_concurrent_calls_do_not_share_counters_or_ids(self):
|
||||||
|
"""同一 client 并发两路必须各自计数与各自 ID(库铁律「纯 asyncio 中立」)。
|
||||||
|
|
||||||
|
上下文若被提升成 client 实例属性,这条就会红——那正是 VT
|
||||||
|
`evolve_llm = llm` 教训的同一形态。
|
||||||
|
"""
|
||||||
|
async with _client() as client:
|
||||||
|
a, b = await asyncio.gather(client.chat(self._MSG), client.chat(self._MSG))
|
||||||
|
assert a.call_stats.logical_call_id != b.call_stats.logical_call_id
|
||||||
|
assert a.call_stats.attempts == b.call_stats.attempts == 1
|
||||||
|
|
||||||
|
async def test_cache_hit_is_zero_attempts_with_a_fresh_logical_id(self):
|
||||||
|
"""命中不产生网关调用 → 0 尝试;且是**新**逻辑调用,不回放历史统计。"""
|
||||||
|
clock = _StatsClock()
|
||||||
|
cache = _TickingCache(clock)
|
||||||
|
async with _client(
|
||||||
|
cache=cache, cache_namespace="proj", cache_ttl_s=600, now=clock
|
||||||
|
) as client:
|
||||||
|
first = await client.chat(self._MSG)
|
||||||
|
second = await client.chat(self._MSG)
|
||||||
|
assert first.cache_hit is False and first.call_stats.attempts == 1
|
||||||
|
assert second.cache_hit is True
|
||||||
|
assert second.call_stats.attempts == 0
|
||||||
|
assert second.call_stats.logical_call_id != first.call_stats.logical_call_id
|
||||||
|
|
||||||
|
async def test_cache_io_counts_into_total_latency(self):
|
||||||
|
"""缓存读写是本次调用真实花掉的时间,必须进总耗时(设计 §3)。"""
|
||||||
|
clock = _StatsClock()
|
||||||
|
cache = _TickingCache(clock, tick=0.25)
|
||||||
|
async with _client(
|
||||||
|
cache=cache, cache_namespace="proj", cache_ttl_s=600, now=clock
|
||||||
|
) as client:
|
||||||
|
hit = (await client.chat(self._MSG), await client.chat(self._MSG))[1]
|
||||||
|
# 命中路径只有一次 get(0.25s),无网关调用
|
||||||
|
assert hit.call_stats.attempts == 0
|
||||||
|
assert hit.call_stats.total_latency_ms == 250
|
||||||
|
|
||||||
|
async def test_inline_telemetry_teardown_counts_into_total_latency(self):
|
||||||
|
"""成功响应的快照含返回前已完成的内联遥测耗时(设计 §6)。"""
|
||||||
|
clock = _StatsClock()
|
||||||
|
recorder = _TickingRecorder(clock, tick=0.5)
|
||||||
|
async with _client(telemetry=recorder, now=clock) as client:
|
||||||
|
resp = await client.chat(self._MSG)
|
||||||
|
assert recorder.rows # 确实写了行,否则本断言空转
|
||||||
|
assert resp.call_stats.total_latency_ms == 500
|
||||||
|
|
||||||
|
async def test_milliseconds_not_seconds(self):
|
||||||
|
"""毫秒/秒不混用: 1.5s 必须是 1500 而不是 1 或 1.5。"""
|
||||||
|
clock = _StatsClock()
|
||||||
|
recorder = _TickingRecorder(clock, tick=1.5)
|
||||||
|
async with _client(telemetry=recorder, now=clock) as client:
|
||||||
|
resp = await client.chat(self._MSG)
|
||||||
|
assert resp.call_stats.total_latency_ms == 1500
|
||||||
|
|
||||||
|
async def test_stats_work_without_any_telemetry(self):
|
||||||
|
"""统计生效与否**不由 telemetry 是否启用决定**(设计 §3.5)。"""
|
||||||
|
async with _client(telemetry=None) as client:
|
||||||
|
resp = await client.chat(self._MSG)
|
||||||
|
assert resp.call_stats is not None and resp.call_stats.attempts == 1
|
||||||
|
|
||||||
|
async def test_failure_exception_carries_no_stats_attribute(self):
|
||||||
|
"""本版**不向异常对象附加统计**(设计 §3.1): 第三方可能复用同一异常实例。"""
|
||||||
|
|
||||||
|
def reject(request):
|
||||||
|
return httpx.Response(400, json={"error": {"message": "bad"}})
|
||||||
|
|
||||||
|
async with _client(handler=reject) as client:
|
||||||
|
with pytest.raises(RequestRejectedError) as exc:
|
||||||
|
await client.chat(self._MSG)
|
||||||
|
assert hasattr(exc.value, "call_stats") is False
|
||||||
|
|
||||||
|
async def test_input_validation_stays_outside_the_stats_boundary(self):
|
||||||
|
"""校验异常保持原行为,发生在统计边界之外(设计 §3)。"""
|
||||||
|
async with _client() as client:
|
||||||
|
with pytest.raises(ValueError, match="meta"):
|
||||||
|
await client.chat(self._MSG, meta={"BAD-KEY": 1})
|
||||||
|
|
||||||
|
|
||||||
|
class TestChatTerminalFailureRows:
|
||||||
|
"""chat 链路的**真实**终态行(1.3.5 设计 §6;补漏而非改口径)。
|
||||||
|
|
||||||
|
这些路径改前一条失败行都没有(结构化耗尽)或只有尝试行,
|
||||||
|
"这次调用到底失败了几次"因此 SQL 答不出来。
|
||||||
|
"""
|
||||||
|
|
||||||
|
_MSG = [{"role": "user", "content": "hi"}]
|
||||||
|
|
||||||
|
def _rows(self, recorder, kind):
|
||||||
|
return [r for r in recorder.rows if r["event_kind"] == kind]
|
||||||
|
|
||||||
|
async def test_structured_exhaustion_writes_the_only_failure_row(self):
|
||||||
|
"""结构化耗尽发生在 transport 成功之后: attempt 行全是成功行,终态是唯一记录。"""
|
||||||
|
from pydantic import BaseModel
|
||||||
|
|
||||||
|
class Answer(BaseModel):
|
||||||
|
answer: int
|
||||||
|
|
||||||
|
recorder = _MemoryRecorder()
|
||||||
|
async with _client(
|
||||||
|
handler=lambda request: _sse("not json at all"),
|
||||||
|
telemetry=recorder,
|
||||||
|
structured_max_retries=1,
|
||||||
|
) as client:
|
||||||
|
with pytest.raises(ResultInvalidError):
|
||||||
|
await client.chat(self._MSG, structured=Answer)
|
||||||
|
attempts = self._rows(recorder, "attempt")
|
||||||
|
terminals = self._rows(recorder, "terminal_failure")
|
||||||
|
assert [a["error"] for a in attempts] == [None, None] # 两次尝试都成功
|
||||||
|
assert len(terminals) == 1
|
||||||
|
row = terminals[0]
|
||||||
|
assert row["error_type"] == "ResultInvalidError"
|
||||||
|
# C2: 有界结构化说明并入 error,且不含 raw_text(正文预算已由 attempt 行承担)
|
||||||
|
assert "validation=" in row["error"] or "repair=" in row["error"]
|
||||||
|
assert len(row["error"]) < 1200
|
||||||
|
|
||||||
|
async def test_retry_exhaustion_writes_exactly_one_terminal_row(self):
|
||||||
|
"""重试耗尽: 逐次 attempt 行之外只能有**一条**终态行。
|
||||||
|
|
||||||
|
终态行的 `attempts` 是整次逻辑调用的真实尝试数——这正是改前 SQL
|
||||||
|
答不出的"这次调用到底重试了几次"。
|
||||||
|
"""
|
||||||
|
recorder = _MemoryRecorder()
|
||||||
|
async with _client(
|
||||||
|
handler=lambda request: httpx.Response(503),
|
||||||
|
telemetry=recorder,
|
||||||
|
retry=RetryPolicy(3, 0.001, 0.01),
|
||||||
|
) as client:
|
||||||
|
with pytest.raises(AllSourcesExhausted):
|
||||||
|
await client.chat(self._MSG)
|
||||||
|
attempts = self._rows(recorder, "attempt")
|
||||||
|
terminals = self._rows(recorder, "terminal_failure")
|
||||||
|
assert len(attempts) == 3
|
||||||
|
assert len(terminals) == 1
|
||||||
|
row = terminals[0]
|
||||||
|
assert row["error_type"] == "AllSourcesExhausted"
|
||||||
|
assert row["attempts"] == 3 # 整次逻辑调用的尝试数
|
||||||
|
assert row["scope"] == "llm" and row["operation"] == "chat"
|
||||||
|
# 终态行的 latency_ms 与 total_latency_ms 同取一份冻结快照
|
||||||
|
assert row["latency_ms"] == row["total_latency_ms"]
|
||||||
|
|
||||||
|
async def test_request_rejected_now_has_both_an_attempt_and_a_terminal_row(self):
|
||||||
|
"""已批准的下游可见变化: 400 密集负载的错误行翻倍,失败计数只能取终态。"""
|
||||||
|
recorder = _MemoryRecorder()
|
||||||
|
async with _client(
|
||||||
|
handler=lambda request: httpx.Response(400, json={"error": {"message": "bad"}}),
|
||||||
|
telemetry=recorder,
|
||||||
|
) as client:
|
||||||
|
with pytest.raises(RequestRejectedError):
|
||||||
|
await client.chat(self._MSG)
|
||||||
|
attempts = self._rows(recorder, "attempt")
|
||||||
|
terminals = self._rows(recorder, "terminal_failure")
|
||||||
|
assert len(attempts) == 1 and attempts[0]["http_status_code"] == 400
|
||||||
|
assert len(terminals) == 1
|
||||||
|
# C1: 终态不搬运最后一次 attempt 的状态码与正文
|
||||||
|
assert terminals[0]["http_status_code"] is None
|
||||||
|
assert terminals[0]["error_body"] is None
|
||||||
|
# 两类行共享同一 logical_call_id,归因查询才连得起来
|
||||||
|
assert attempts[0]["logical_call_id"] == terminals[0]["logical_call_id"]
|
||||||
|
|
||||||
|
async def test_non_domain_exception_writes_no_terminal_row(self):
|
||||||
|
"""编程错原样传播,本版**不承诺**任何统计或终态行,也不偷偷改分类。"""
|
||||||
|
recorder = _MemoryRecorder()
|
||||||
|
|
||||||
|
async def boom(request):
|
||||||
|
raise KeyError("programming error")
|
||||||
|
|
||||||
|
async with _client(telemetry=recorder) as client:
|
||||||
|
client._handler = boom
|
||||||
|
with pytest.raises(KeyError):
|
||||||
|
await client.chat(self._MSG)
|
||||||
|
assert self._rows(recorder, "terminal_failure") == []
|
||||||
|
|
||||||
|
async def test_cancellation_writes_at_most_one_terminal_row(self):
|
||||||
|
"""取消尽力写一条(允许 0),且 `CancelledError` 类型与语义不变。"""
|
||||||
|
recorder = _MemoryRecorder()
|
||||||
|
|
||||||
|
async def hang(request):
|
||||||
|
raise asyncio.CancelledError
|
||||||
|
|
||||||
|
async with _client(telemetry=recorder) as client:
|
||||||
|
client._handler = hang
|
||||||
|
with pytest.raises(asyncio.CancelledError):
|
||||||
|
await client.chat(self._MSG)
|
||||||
|
terminals = self._rows(recorder, "terminal_failure")
|
||||||
|
assert len(terminals) == 1
|
||||||
|
assert terminals[0]["error"] == "cancelled"
|
||||||
|
# 字符串不解析猜诊断
|
||||||
|
assert terminals[0]["error_type"] is None
|
||||||
|
|
||||||
|
async def test_terminal_row_is_written_once_per_logical_call(self):
|
||||||
|
"""`claim_terminal` 去重: 同一次调用即便出口被多次触达也只有一条。"""
|
||||||
|
from polygateway.middleware.telemetry import emit_terminal_once
|
||||||
|
from polygateway.types import _CallContext
|
||||||
|
|
||||||
|
recorder = _MemoryRecorder()
|
||||||
|
async with _client(telemetry=recorder) as client:
|
||||||
|
context = _CallContext(now=client._now)
|
||||||
|
request = ChatRequest(messages=self._MSG, call_context=context)
|
||||||
|
for _ in range(3):
|
||||||
|
await emit_terminal_once(
|
||||||
|
client._emitter,
|
||||||
|
request=request,
|
||||||
|
context=context,
|
||||||
|
error=AllSourcesExhausted(
|
||||||
|
scope="llm", reason="retry_exhausted", retry_after_s=1.0
|
||||||
|
),
|
||||||
|
operation="chat",
|
||||||
|
)
|
||||||
|
assert len(self._rows(recorder, "terminal_failure")) == 1
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.fixture
|
||||||
|
def captured_warnings():
|
||||||
|
"""捕获库发出的 WARNING;loguru 不经标准 logging,pytest 的 caplog 抓不到。
|
||||||
|
|
||||||
|
名字避开裸 `warnings`: 那会遮蔽标准库模块名,本文件将来任何一次
|
||||||
|
`import warnings` 都会与它静默互相顶掉,而报错点离真因很远。
|
||||||
|
"""
|
||||||
|
from loguru import logger
|
||||||
|
|
||||||
|
messages: list[str] = []
|
||||||
|
sink_id = logger.add(messages.append, level="WARNING")
|
||||||
|
yield messages
|
||||||
|
logger.remove(sink_id)
|
||||||
|
|
||||||
|
|
||||||
|
class TestTerminalEmitDegradation:
|
||||||
|
"""终态出口的降级方向: 诊断字段的**提取**同样在降级范围内(铁律"遥测写失败降级不冒泡")。
|
||||||
|
|
||||||
|
改前 `_record` 的 except 只包住写入本身,而错误诊断列在它之外求值——
|
||||||
|
经公共扩展点(自实现 `StructuredOutputStrategy`/transport)构造出的
|
||||||
|
`ResultInvalidError(validation_errors=(非 str,))` 会让提取期抛 `TypeError`
|
||||||
|
顶替调用方本该收到的领域异常,错误四分类当场被击穿。
|
||||||
|
"""
|
||||||
|
|
||||||
|
_MSG = [{"role": "user", "content": "hi"}]
|
||||||
|
|
||||||
|
def _rows(self, recorder, kind):
|
||||||
|
return [r for r in recorder.rows if r["event_kind"] == kind]
|
||||||
|
|
||||||
|
async def test_broken_validation_errors_keep_the_domain_error(self, captured_warnings):
|
||||||
|
"""自实现策略给出非 str 的 `validation_errors`: 领域异常必须原样上抛。"""
|
||||||
|
|
||||||
|
class _BadStrategy:
|
||||||
|
"""公共端口 `StructuredOutputStrategy` 的下游实现(库外没有类型执法)。"""
|
||||||
|
|
||||||
|
def request_overlay(self, schema):
|
||||||
|
return {}
|
||||||
|
|
||||||
|
def parse(self, text):
|
||||||
|
raise ResultInvalidError("模型返回不可解析", validation_errors=(object(),))
|
||||||
|
|
||||||
|
recorder = _MemoryRecorder()
|
||||||
|
async with _client(telemetry=recorder, structured_strategy=_BadStrategy()) as client:
|
||||||
|
with pytest.raises(ResultInvalidError): # 不是 TypeError
|
||||||
|
await client.chat(self._MSG, structured="json")
|
||||||
|
# 降级有声: 静默吞掉等于遥测缺口无人知道
|
||||||
|
assert [m for m in captured_warnings if "终态遥测记录失败" in m]
|
||||||
|
# 尝试行不受影响;终态行按 best effort 允许 0 条,但绝不能重复
|
||||||
|
assert len(self._rows(recorder, "attempt")) == 1
|
||||||
|
assert len(self._rows(recorder, "terminal_failure")) <= 1
|
||||||
|
|
||||||
|
async def test_cancellation_is_never_swallowed_by_the_degradation(self):
|
||||||
|
"""降级不得吞取消: 写入那一次 await 上被取消,`CancelledError` 照常传播。"""
|
||||||
|
from polygateway.middleware.telemetry import emit_terminal_once
|
||||||
|
from polygateway.types import _CallContext
|
||||||
|
|
||||||
|
class _CancellingEmitter:
|
||||||
|
async def emit_terminal_failure(self, **kwargs):
|
||||||
|
raise asyncio.CancelledError
|
||||||
|
|
||||||
|
context = _CallContext(now=asyncio.get_running_loop().time)
|
||||||
|
request = ChatRequest(messages=self._MSG, call_context=context)
|
||||||
|
with pytest.raises(asyncio.CancelledError):
|
||||||
|
await emit_terminal_once(
|
||||||
|
_CancellingEmitter(),
|
||||||
|
request=request,
|
||||||
|
context=context,
|
||||||
|
error=AllSourcesExhausted(scope="llm", reason="retry_exhausted", retry_after_s=1.0),
|
||||||
|
operation="chat",
|
||||||
|
)
|
||||||
|
|||||||
@@ -580,7 +580,12 @@ class TestReasonlessTelemetryContract:
|
|||||||
client, _ = _embed_client([_src(enable_thinking=True)], script, telemetry=recorder)
|
client, _ = _embed_client([_src(enable_thinking=True)], script, telemetry=recorder)
|
||||||
with pytest.raises(AllSourcesExhausted if exhausted else RequestRejectedError):
|
with pytest.raises(AllSourcesExhausted if exhausted else RequestRejectedError):
|
||||||
await client.embed(["text"])
|
await client.embed(["text"])
|
||||||
assert len(recorder.rows) == len(script)
|
# 1.3.5: 逐次 attempt 行之外,本次逻辑调用另有**一条**终态行
|
||||||
|
attempts = [r for r in recorder.rows if r["event_kind"] == "attempt"]
|
||||||
|
terminals = [r for r in recorder.rows if r["event_kind"] == "terminal_failure"]
|
||||||
|
assert len(attempts) == len(script)
|
||||||
|
assert len(terminals) == 1
|
||||||
|
# 推理档在三类行上都必须是 NULL: embed payload 从不带推理参数
|
||||||
assert all(r["error"] and r["reasoning_effort"] is None for r in recorder.rows)
|
assert all(r["error"] and r["reasoning_effort"] is None for r in recorder.rows)
|
||||||
|
|
||||||
async def test_embedding_wire_ignores_reasoning_configuration(self):
|
async def test_embedding_wire_ignores_reasoning_configuration(self):
|
||||||
@@ -600,3 +605,43 @@ class TestReasonlessTelemetryContract:
|
|||||||
assert seen == [{"model": "embed-1", "input": ["text"]}]
|
assert seen == [{"model": "embed-1", "input": ["text"]}]
|
||||||
finally:
|
finally:
|
||||||
await transport.aclose()
|
await transport.aclose()
|
||||||
|
|
||||||
|
|
||||||
|
class TestEmbedLogicalCallStats:
|
||||||
|
"""分批共享同一逻辑调用(1.3.5 设计 §3/§3.5)。"""
|
||||||
|
|
||||||
|
async def test_three_batches_count_three_attempts(self):
|
||||||
|
"""分批是库的实现细节,但每批都真打了一次网关,故计 3 次尝试。"""
|
||||||
|
client, _ = _embed_client([_src()], ["ok", "ok", "ok"], batch_size=2)
|
||||||
|
resp = await client.embed(["a", "bb", "ccc", "dddd", "eeeee"])
|
||||||
|
assert resp.call_stats is not None
|
||||||
|
assert resp.call_stats.attempts == 3
|
||||||
|
|
||||||
|
async def test_separate_calls_get_distinct_logical_ids(self):
|
||||||
|
"""一次公开调用一个 ID: 两次 `embed` 不得共用同一个。
|
||||||
|
|
||||||
|
共用就意味着上下文被提升成了 client 实例属性(库铁律禁止的形态)。
|
||||||
|
"""
|
||||||
|
client, _ = _embed_client([_src()], ["ok"] * 5, batch_size=2)
|
||||||
|
first = await client.embed(["a", "bb", "ccc", "dddd", "eeeee"]) # 3 批
|
||||||
|
second = await client.embed(["x", "y"]) # 1 批
|
||||||
|
assert first.call_stats.attempts == 3 and second.call_stats.attempts == 1
|
||||||
|
assert first.call_stats.logical_call_id != second.call_stats.logical_call_id
|
||||||
|
|
||||||
|
async def test_retry_within_a_batch_is_counted(self):
|
||||||
|
client, _ = _embed_client([_src(), _src(name="e2")], [TransientError("t1"), "ok"])
|
||||||
|
resp = await client.embed(["a"])
|
||||||
|
assert resp.call_stats.attempts == 2
|
||||||
|
|
||||||
|
async def test_empty_input_is_zero_attempts_and_writes_no_telemetry_row(self):
|
||||||
|
"""合法零尝试: 返回真实统计,且**不写任何遥测行**(设计 §3 M2)。
|
||||||
|
|
||||||
|
与 cache_hit 不同——不要按"遥测必录"推断空输入也有台账行。
|
||||||
|
"""
|
||||||
|
rec = _MemoryRecorder()
|
||||||
|
client, _ = _embed_client([_src()], [], telemetry=rec)
|
||||||
|
resp = await client.embed([])
|
||||||
|
assert resp.call_stats is not None
|
||||||
|
assert resp.call_stats.attempts == 0
|
||||||
|
assert resp.call_stats.logical_call_id # 真实 ID,不是空串
|
||||||
|
assert rec.rows == [] # 零遥测行
|
||||||
|
|||||||
@@ -613,5 +613,42 @@ class TestReasonlessTelemetryContract:
|
|||||||
client, _, _ = _client([_src(enable_thinking=True)], script, telemetry=recorder)
|
client, _, _ = _client([_src(enable_thinking=True)], script, telemetry=recorder)
|
||||||
with pytest.raises(AllSourcesExhausted if exhausted else RequestRejectedError):
|
with pytest.raises(AllSourcesExhausted if exhausted else RequestRejectedError):
|
||||||
await getattr(client, method)(b"image")
|
await getattr(client, method)(b"image")
|
||||||
assert len(recorder.rows) == len(script)
|
# 1.3.5: 逐次 attempt 行之外,本次逻辑调用另有**一条**终态行
|
||||||
|
attempts = [r for r in recorder.rows if r["event_kind"] == "attempt"]
|
||||||
|
terminals = [r for r in recorder.rows if r["event_kind"] == "terminal_failure"]
|
||||||
|
assert len(attempts) == len(script)
|
||||||
|
assert len(terminals) == 1
|
||||||
|
# 终态行的 operation 是**公开方法**名,与尝试行一致
|
||||||
|
assert terminals[0]["operation"] == method
|
||||||
assert all(r["error"] and r["reasoning_effort"] is None for r in recorder.rows)
|
assert all(r["error"] and r["reasoning_effort"] is None for r in recorder.rows)
|
||||||
|
|
||||||
|
|
||||||
|
class TestOcrLogicalCallStats:
|
||||||
|
"""OCR 两个公开方法各自拥有一次逻辑调用(1.3.5 设计 §3/§3.5)。"""
|
||||||
|
|
||||||
|
async def test_text_success_counts_one_attempt(self):
|
||||||
|
client, _, _ = _client([_src()], ["text"])
|
||||||
|
r = await client.recognize_text(b"jpg")
|
||||||
|
assert r.call_stats is not None and r.call_stats.attempts == 1
|
||||||
|
|
||||||
|
async def test_layout_two_http_calls_count_as_one_attempt(self):
|
||||||
|
"""POST + ZIP GET 在同一次 transport 调用内,计 **1** 次尝试而非 2。
|
||||||
|
|
||||||
|
`attempts` 的语义是"调用 transport 端口的次数",不是 HTTP 请求条数。
|
||||||
|
"""
|
||||||
|
client, _, _ = _client([_src()], ["layout"])
|
||||||
|
r = await client.parse_layout(b"jpg")
|
||||||
|
assert r.call_stats is not None and r.call_stats.attempts == 1
|
||||||
|
|
||||||
|
async def test_retry_counts_every_attempt(self):
|
||||||
|
client, _, _ = _client([_src(), _src(name="m2")], [TransientError("t1"), "text"])
|
||||||
|
r = await client.recognize_text(b"jpg")
|
||||||
|
assert r.call_stats.attempts == 2
|
||||||
|
|
||||||
|
async def test_input_validation_stays_outside_the_stats_boundary(self):
|
||||||
|
"""`image` 类型/空校验先于上下文创建(M1 例外),保持原异常行为。"""
|
||||||
|
client, _, _ = _client([_src()], [])
|
||||||
|
with pytest.raises(TypeError):
|
||||||
|
await client.recognize_text("not-bytes")
|
||||||
|
with pytest.raises(ValueError):
|
||||||
|
await client.recognize_text(b"")
|
||||||
|
|||||||
@@ -116,7 +116,7 @@ async def _recorded_cost(result, source):
|
|||||||
source_name=source.name,
|
source_name=source.name,
|
||||||
usage_source=result.usage_source,
|
usage_source=result.usage_source,
|
||||||
)
|
)
|
||||||
await TelemetryEmitter(recorder, pricing=_PRICING, text_cap=None).emit_attempt(
|
await TelemetryEmitter(recorder, pricing=_PRICING, text_cap=None, scope="LLM").emit_attempt(
|
||||||
request=ChatRequest(messages=[{"role": "user", "content": "hi"}]),
|
request=ChatRequest(messages=[{"role": "user", "content": "hi"}]),
|
||||||
source=source,
|
source=source,
|
||||||
call_id="cid-1",
|
call_id="cid-1",
|
||||||
@@ -124,6 +124,7 @@ async def _recorded_cost(result, source):
|
|||||||
response=response,
|
response=response,
|
||||||
error=None,
|
error=None,
|
||||||
reasoning_applies=True,
|
reasoning_applies=True,
|
||||||
|
operation="chat",
|
||||||
)
|
)
|
||||||
return recorder.rows[0]["cost"]
|
return recorder.rows[0]["cost"]
|
||||||
|
|
||||||
|
|||||||
@@ -124,6 +124,18 @@ class _DummyRecorder:
|
|||||||
reasoning_tokens,
|
reasoning_tokens,
|
||||||
tenant_id,
|
tenant_id,
|
||||||
meta,
|
meta,
|
||||||
|
thinking_observation,
|
||||||
|
reasoning_effort,
|
||||||
|
scope,
|
||||||
|
operation,
|
||||||
|
logical_call_id,
|
||||||
|
event_kind,
|
||||||
|
http_status_code,
|
||||||
|
error_type,
|
||||||
|
cause_type,
|
||||||
|
error_body,
|
||||||
|
attempts,
|
||||||
|
total_latency_ms,
|
||||||
) -> None: ...
|
) -> None: ...
|
||||||
|
|
||||||
|
|
||||||
@@ -275,8 +287,47 @@ class TestTelemetryRecorderSignature:
|
|||||||
params = inspect.signature(TelemetryRecorder.record_llm_call).parameters
|
params = inspect.signature(TelemetryRecorder.record_llm_call).parameters
|
||||||
assert {"tenant_id", "meta"} <= set(params)
|
assert {"tenant_id", "meta"} <= set(params)
|
||||||
|
|
||||||
|
def test_call_observability_fields_are_declared(self):
|
||||||
|
"""1.3.5 十列进协议(issue #19/#23);字段总数以实测为准不凭记忆。
|
||||||
|
|
||||||
|
本签名同时是装配闸的事实源(`_assert_recorder_shape` 按它派生参数名),
|
||||||
|
故它与实现一旦漂移,下游自定义 recorder 会在装配期就被拒。
|
||||||
|
"""
|
||||||
|
import inspect
|
||||||
|
|
||||||
|
params = inspect.signature(TelemetryRecorder.record_llm_call).parameters
|
||||||
|
assert {
|
||||||
|
"scope",
|
||||||
|
"operation",
|
||||||
|
"logical_call_id",
|
||||||
|
"event_kind",
|
||||||
|
"http_status_code",
|
||||||
|
"error_type",
|
||||||
|
"cause_type",
|
||||||
|
"error_body",
|
||||||
|
"attempts",
|
||||||
|
"total_latency_ms",
|
||||||
|
} <= set(params)
|
||||||
|
assert len(params) - 1 == 36 # 减掉 self
|
||||||
|
|
||||||
@pytest.mark.parametrize(
|
@pytest.mark.parametrize(
|
||||||
"name", ["tenant_id", "meta", "thinking_observation", "reasoning_effort"]
|
"name",
|
||||||
|
[
|
||||||
|
"tenant_id",
|
||||||
|
"meta",
|
||||||
|
"thinking_observation",
|
||||||
|
"reasoning_effort",
|
||||||
|
"scope",
|
||||||
|
"operation",
|
||||||
|
"logical_call_id",
|
||||||
|
"event_kind",
|
||||||
|
"http_status_code",
|
||||||
|
"error_type",
|
||||||
|
"cause_type",
|
||||||
|
"error_body",
|
||||||
|
"attempts",
|
||||||
|
"total_latency_ms",
|
||||||
|
],
|
||||||
)
|
)
|
||||||
def test_caller_dimensions_have_no_default(self, name):
|
def test_caller_dimensions_have_no_default(self, name):
|
||||||
import inspect
|
import inspect
|
||||||
|
|||||||
@@ -169,7 +169,7 @@ def _source(model="qwen-max"):
|
|||||||
class TestEmitterCost:
|
class TestEmitterCost:
|
||||||
async def test_success_row_costed(self):
|
async def test_success_row_costed(self):
|
||||||
rec = _MemoryRecorder()
|
rec = _MemoryRecorder()
|
||||||
emitter = TelemetryEmitter(rec, pricing=_TABLE, text_cap=None)
|
emitter = TelemetryEmitter(rec, pricing=_TABLE, text_cap=None, scope="LLM")
|
||||||
await emitter.emit_attempt(
|
await emitter.emit_attempt(
|
||||||
request=_REQ,
|
request=_REQ,
|
||||||
source=_source(),
|
source=_source(),
|
||||||
@@ -178,18 +178,19 @@ class TestEmitterCost:
|
|||||||
response=_resp(),
|
response=_resp(),
|
||||||
error=None,
|
error=None,
|
||||||
reasoning_applies=True,
|
reasoning_applies=True,
|
||||||
|
operation="chat",
|
||||||
)
|
)
|
||||||
assert rec.rows[0]["cost"] == pytest.approx(7.2)
|
assert rec.rows[0]["cost"] == pytest.approx(7.2)
|
||||||
|
|
||||||
async def test_cache_hit_row_costs_zero(self):
|
async def test_cache_hit_row_costs_zero(self):
|
||||||
rec = _MemoryRecorder()
|
rec = _MemoryRecorder()
|
||||||
emitter = TelemetryEmitter(rec, pricing=_TABLE, text_cap=None)
|
emitter = TelemetryEmitter(rec, pricing=_TABLE, text_cap=None, scope="LLM")
|
||||||
await emitter.emit_cache_hit(request=_REQ, response=_resp(cache_hit=True))
|
await emitter.emit_cache_hit(request=_REQ, response=_resp(cache_hit=True), operation="chat")
|
||||||
assert rec.rows[0]["cost"] == 0.0
|
assert rec.rows[0]["cost"] == 0.0
|
||||||
|
|
||||||
async def test_failure_row_cost_none(self):
|
async def test_failure_row_cost_none(self):
|
||||||
rec = _MemoryRecorder()
|
rec = _MemoryRecorder()
|
||||||
emitter = TelemetryEmitter(rec, pricing=_TABLE, text_cap=None)
|
emitter = TelemetryEmitter(rec, pricing=_TABLE, text_cap=None, scope="LLM")
|
||||||
await emitter.emit_attempt(
|
await emitter.emit_attempt(
|
||||||
request=_REQ,
|
request=_REQ,
|
||||||
source=_source(),
|
source=_source(),
|
||||||
@@ -198,12 +199,13 @@ class TestEmitterCost:
|
|||||||
response=None,
|
response=None,
|
||||||
error="TransientError: boom",
|
error="TransientError: boom",
|
||||||
reasoning_applies=True,
|
reasoning_applies=True,
|
||||||
|
operation="chat",
|
||||||
)
|
)
|
||||||
assert rec.rows[0]["cost"] is None
|
assert rec.rows[0]["cost"] is None
|
||||||
|
|
||||||
async def test_unknown_model_none_without_blocking(self):
|
async def test_unknown_model_none_without_blocking(self):
|
||||||
rec = _MemoryRecorder()
|
rec = _MemoryRecorder()
|
||||||
emitter = TelemetryEmitter(rec, pricing=_TABLE, text_cap=None)
|
emitter = TelemetryEmitter(rec, pricing=_TABLE, text_cap=None, scope="LLM")
|
||||||
await emitter.emit_attempt(
|
await emitter.emit_attempt(
|
||||||
request=_REQ,
|
request=_REQ,
|
||||||
source=_source(model="mystery"),
|
source=_source(model="mystery"),
|
||||||
@@ -212,13 +214,14 @@ class TestEmitterCost:
|
|||||||
response=_resp(model="mystery"),
|
response=_resp(model="mystery"),
|
||||||
error=None,
|
error=None,
|
||||||
reasoning_applies=True,
|
reasoning_applies=True,
|
||||||
|
operation="chat",
|
||||||
)
|
)
|
||||||
assert rec.rows[0]["cost"] is None
|
assert rec.rows[0]["cost"] is None
|
||||||
|
|
||||||
async def test_no_pricing_keeps_none(self):
|
async def test_no_pricing_keeps_none(self):
|
||||||
"""未注入价格表 = M1 现状: cost 恒 None(回归)。"""
|
"""未注入价格表 = M1 现状: cost 恒 None(回归)。"""
|
||||||
rec = _MemoryRecorder()
|
rec = _MemoryRecorder()
|
||||||
emitter = TelemetryEmitter(rec, text_cap=None)
|
emitter = TelemetryEmitter(rec, text_cap=None, scope="LLM")
|
||||||
await emitter.emit_attempt(
|
await emitter.emit_attempt(
|
||||||
request=_REQ,
|
request=_REQ,
|
||||||
source=_source(),
|
source=_source(),
|
||||||
@@ -227,5 +230,6 @@ class TestEmitterCost:
|
|||||||
response=_resp(),
|
response=_resp(),
|
||||||
error=None,
|
error=None,
|
||||||
reasoning_applies=True,
|
reasoning_applies=True,
|
||||||
|
operation="chat",
|
||||||
)
|
)
|
||||||
assert rec.rows[0]["cost"] is None
|
assert rec.rows[0]["cost"] is None
|
||||||
|
|||||||
@@ -5,6 +5,7 @@
|
|||||||
"""
|
"""
|
||||||
|
|
||||||
import asyncio
|
import asyncio
|
||||||
|
import dataclasses
|
||||||
|
|
||||||
import pytest
|
import pytest
|
||||||
|
|
||||||
@@ -776,3 +777,60 @@ class TestRateLimitPushback:
|
|||||||
await mw(_REQ)
|
await mw(_REQ)
|
||||||
assert ei.value.reason == "retry_exhausted"
|
assert ei.value.reason == "retry_exhausted"
|
||||||
assert len(transport.calls) == 3
|
assert len(transport.calls) == 3
|
||||||
|
|
||||||
|
|
||||||
|
class TestLogicalAttemptCounting:
|
||||||
|
"""尝试登记在 transport 调用**之前**(1.3.5 设计 §4)。
|
||||||
|
|
||||||
|
登记点若挪到成功之后,失败与取消的尝试就会从计数里消失——而那正是
|
||||||
|
诊断时最需要看见的几次。
|
||||||
|
"""
|
||||||
|
|
||||||
|
def _ctx(self, clock):
|
||||||
|
from polygateway.types import _CallContext
|
||||||
|
|
||||||
|
return _CallContext(now=clock)
|
||||||
|
|
||||||
|
async def test_single_success_counts_one(self):
|
||||||
|
mw, _, _, _, _, clock = _harness([_src("a")], [_ok()])
|
||||||
|
ctx = self._ctx(clock)
|
||||||
|
await mw(dataclasses.replace(_REQ, call_context=ctx))
|
||||||
|
assert ctx.snapshot().attempts == 1
|
||||||
|
|
||||||
|
async def test_failed_retries_are_counted(self):
|
||||||
|
"""两次可重试失败 + 一次成功 = 3 次尝试,不是 1 次。"""
|
||||||
|
mw, _, _, transport, _, clock = _harness(
|
||||||
|
[_src("a")], [TransientError("t1"), TransientError("t2"), _ok()]
|
||||||
|
)
|
||||||
|
ctx = self._ctx(clock)
|
||||||
|
await mw(dataclasses.replace(_REQ, call_context=ctx))
|
||||||
|
assert ctx.snapshot().attempts == 3 == len(transport.calls)
|
||||||
|
|
||||||
|
async def test_budget_free_429_still_counts_as_an_attempt(self):
|
||||||
|
"""429 免的是重试预算,不是"没发生过"——它确实打到了网关。"""
|
||||||
|
mw, _, _, transport, _, clock = _harness(
|
||||||
|
[_src("a")],
|
||||||
|
[
|
||||||
|
TransientError("t1", status_code=429, retry_after_s=1.0),
|
||||||
|
TransientError("t2", status_code=429, retry_after_s=1.0),
|
||||||
|
_ok(),
|
||||||
|
],
|
||||||
|
)
|
||||||
|
ctx = self._ctx(clock)
|
||||||
|
await mw(dataclasses.replace(_REQ, call_context=ctx))
|
||||||
|
assert ctx.snapshot().attempts == 3 == len(transport.calls)
|
||||||
|
|
||||||
|
async def test_retry_exhausted_counts_every_attempt(self):
|
||||||
|
mw, _, _, transport, _, clock = _harness(
|
||||||
|
[_src("a")], [TransientError(str(i)) for i in range(5)], max_attempts=3
|
||||||
|
)
|
||||||
|
ctx = self._ctx(clock)
|
||||||
|
with pytest.raises(AllSourcesExhausted):
|
||||||
|
await mw(dataclasses.replace(_REQ, call_context=ctx))
|
||||||
|
assert ctx.snapshot().attempts == 3 == len(transport.calls)
|
||||||
|
|
||||||
|
async def test_absent_context_does_not_break_the_call(self):
|
||||||
|
"""库内现场构造的 `ChatRequest` 没有上下文,不得因此报错(设计 §3.5)。"""
|
||||||
|
mw, _, _, _, _, _ = _harness([_src("a")], [_ok()])
|
||||||
|
resp = await mw(_REQ)
|
||||||
|
assert resp.content == "ok" and _REQ.call_context is None
|
||||||
|
|||||||
+609
-81
File diff suppressed because it is too large
Load Diff
@@ -610,3 +610,144 @@ class TestSourceConfigEffortNormalization:
|
|||||||
"""非字符串同样只能是 `ValueError`: 公共入口不许把类型错误漏成 `AttributeError`。"""
|
"""非字符串同样只能是 `ValueError`: 公共入口不许把类型错误漏成 `AttributeError`。"""
|
||||||
with pytest.raises(ValueError, match="推理档位"):
|
with pytest.raises(ValueError, match="推理档位"):
|
||||||
_make_source(reasoning_effort=3)
|
_make_source(reasoning_effort=3)
|
||||||
|
|
||||||
|
|
||||||
|
class TestCallStatsAndContext:
|
||||||
|
"""逻辑调用统计内核(1.3.5 设计 §3/§4)。"""
|
||||||
|
|
||||||
|
def test_call_stats_is_frozen_snapshot(self):
|
||||||
|
from polygateway.types import CallStats
|
||||||
|
|
||||||
|
stats = CallStats(logical_call_id="lc-1", attempts=2, total_latency_ms=15)
|
||||||
|
with pytest.raises(dataclasses.FrozenInstanceError):
|
||||||
|
stats.attempts = 3
|
||||||
|
|
||||||
|
def test_context_counts_attempts_and_freezes_elapsed(self):
|
||||||
|
"""快照是同步冻结的时间切片: 登记两次尝试后耗时按注入钟折算成毫秒。"""
|
||||||
|
from polygateway.types import _CallContext
|
||||||
|
|
||||||
|
clock = _FakeMonotonic()
|
||||||
|
ctx = _CallContext(now=clock)
|
||||||
|
clock.advance(1.5)
|
||||||
|
ctx.register_attempt()
|
||||||
|
ctx.register_attempt()
|
||||||
|
stats = ctx.snapshot()
|
||||||
|
assert stats.attempts == 2
|
||||||
|
assert stats.total_latency_ms == 1500 # 秒→毫秒,不混用单位
|
||||||
|
|
||||||
|
def test_snapshot_is_repeatable_and_tracks_later_time(self):
|
||||||
|
from polygateway.types import _CallContext
|
||||||
|
|
||||||
|
clock = _FakeMonotonic()
|
||||||
|
ctx = _CallContext(now=clock)
|
||||||
|
first = ctx.snapshot()
|
||||||
|
clock.advance(2.0)
|
||||||
|
second = ctx.snapshot()
|
||||||
|
assert first.total_latency_ms == 0 and second.total_latency_ms == 2000
|
||||||
|
assert first.logical_call_id == second.logical_call_id
|
||||||
|
|
||||||
|
def test_each_context_gets_its_own_logical_id(self):
|
||||||
|
from polygateway.types import _CallContext
|
||||||
|
|
||||||
|
clock = _FakeMonotonic()
|
||||||
|
assert _CallContext(now=clock).logical_call_id != _CallContext(now=clock).logical_call_id
|
||||||
|
|
||||||
|
def test_claim_terminal_is_true_once(self):
|
||||||
|
"""终态去重位: 保证每逻辑调用至多写一条终态行(设计 §6 不变量 I3)。"""
|
||||||
|
from polygateway.types import _CallContext
|
||||||
|
|
||||||
|
ctx = _CallContext(now=_FakeMonotonic())
|
||||||
|
assert ctx.claim_terminal() is True
|
||||||
|
assert ctx.claim_terminal() is False
|
||||||
|
|
||||||
|
def test_chat_request_context_does_not_affect_equality_or_repr(self):
|
||||||
|
"""上下文是库内部件: 进 `compare`/`repr` 会污染既有请求语义与日志。"""
|
||||||
|
from polygateway.types import _CallContext
|
||||||
|
|
||||||
|
ctx = _CallContext(now=_FakeMonotonic())
|
||||||
|
bare = ChatRequest(messages=[{"role": "user", "content": "hi"}])
|
||||||
|
with_ctx = dataclasses.replace(bare, call_context=ctx)
|
||||||
|
assert with_ctx.call_context is ctx
|
||||||
|
assert with_ctx == bare
|
||||||
|
assert "call_context" not in repr(with_ctx)
|
||||||
|
|
||||||
|
def test_replace_preserves_the_same_context_reference(self):
|
||||||
|
"""洋葱各层经 `replace` 派生请求,上下文必须是同一实例而非拷贝。"""
|
||||||
|
from polygateway.types import _CallContext
|
||||||
|
|
||||||
|
ctx = _CallContext(now=_FakeMonotonic())
|
||||||
|
req = ChatRequest(messages=[{"role": "user", "content": "hi"}], call_context=ctx)
|
||||||
|
derived = dataclasses.replace(req, stream=False)
|
||||||
|
assert derived.call_context is ctx
|
||||||
|
|
||||||
|
def test_four_responses_default_call_stats_to_none(self):
|
||||||
|
"""第三方合成响应的 `None` 表示未知,不得伪造 0(设计 §3)。"""
|
||||||
|
from polygateway.types import (
|
||||||
|
EmbeddingResponse,
|
||||||
|
OcrLayoutResult,
|
||||||
|
OcrTextResult,
|
||||||
|
)
|
||||||
|
|
||||||
|
llm = LLMResponse(
|
||||||
|
content="c",
|
||||||
|
thinking="",
|
||||||
|
model="m",
|
||||||
|
provider="p",
|
||||||
|
prompt_tokens=1,
|
||||||
|
completion_tokens=1,
|
||||||
|
latency_ms=1,
|
||||||
|
ttft_ms=None,
|
||||||
|
max_inter_token_ms=None,
|
||||||
|
cache_hit=False,
|
||||||
|
call_id="c1",
|
||||||
|
)
|
||||||
|
emb = EmbeddingResponse(
|
||||||
|
vectors=[],
|
||||||
|
dim=0,
|
||||||
|
model="m",
|
||||||
|
provider="p",
|
||||||
|
prompt_tokens=0,
|
||||||
|
usage_source="measured",
|
||||||
|
latency_ms=0,
|
||||||
|
call_id="c2",
|
||||||
|
source_name="s",
|
||||||
|
)
|
||||||
|
text = OcrTextResult(
|
||||||
|
text="", source_name="s", usage=Usage(0, 0), latency_ms=0, call_id="c3", raw={}
|
||||||
|
)
|
||||||
|
layout = OcrLayoutResult(
|
||||||
|
elements=[],
|
||||||
|
page_sizes=[],
|
||||||
|
source_name="s",
|
||||||
|
usage=Usage(0, 0),
|
||||||
|
latency_ms=0,
|
||||||
|
call_id="c4",
|
||||||
|
raw={},
|
||||||
|
)
|
||||||
|
assert (llm.call_stats, emb.call_stats, text.call_stats, layout.call_stats) == (
|
||||||
|
None,
|
||||||
|
None,
|
||||||
|
None,
|
||||||
|
None,
|
||||||
|
)
|
||||||
|
|
||||||
|
def test_call_stats_is_exported_from_package_root(self):
|
||||||
|
"""四份平铺字段会漂移,故统计以单一对象出现在公共 API(设计 §3)。"""
|
||||||
|
import polygateway
|
||||||
|
from polygateway.types import CallStats
|
||||||
|
|
||||||
|
assert polygateway.CallStats is CallStats
|
||||||
|
assert "CallStats" in polygateway.__all__
|
||||||
|
|
||||||
|
|
||||||
|
class _FakeMonotonic:
|
||||||
|
"""确定性单调钟;不复用 contracts 的 FakeClock 以免 unit 反向依赖契约包。"""
|
||||||
|
|
||||||
|
def __init__(self, start: float = 1000.0) -> None:
|
||||||
|
self.t = start
|
||||||
|
|
||||||
|
def __call__(self) -> float:
|
||||||
|
return self.t
|
||||||
|
|
||||||
|
def advance(self, seconds: float) -> None:
|
||||||
|
self.t += seconds
|
||||||
|
|||||||
@@ -35,6 +35,7 @@ from polygateway.types import (
|
|||||||
USAGE_SOURCES,
|
USAGE_SOURCES,
|
||||||
BackpressurePolicy,
|
BackpressurePolicy,
|
||||||
BreakerConfig,
|
BreakerConfig,
|
||||||
|
CallStats,
|
||||||
ChatRequest,
|
ChatRequest,
|
||||||
EmbeddingTransportResult,
|
EmbeddingTransportResult,
|
||||||
GlobalLimits,
|
GlobalLimits,
|
||||||
@@ -44,6 +45,9 @@ from polygateway.types import (
|
|||||||
SourceConfig,
|
SourceConfig,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
# 终态行的快照入参(1.3.5): `emit_terminal_failure` 不再收 `latency_ms`。
|
||||||
|
_MIGRATED_STATS = CallStats(logical_call_id="lcid-mig", attempts=1, total_latency_ms=1)
|
||||||
|
|
||||||
_REQ = ChatRequest(messages=[{"role": "user", "content": "hi"}])
|
_REQ = ChatRequest(messages=[{"role": "user", "content": "hi"}])
|
||||||
_DOMAIN = sorted(USAGE_SOURCES)
|
_DOMAIN = sorted(USAGE_SOURCES)
|
||||||
|
|
||||||
@@ -255,7 +259,7 @@ def _resp(usage_source):
|
|||||||
@pytest.mark.parametrize("emitted", _DOMAIN)
|
@pytest.mark.parametrize("emitted", _DOMAIN)
|
||||||
async def test_emit_attempt_success_stays_in_domain(emitted):
|
async def test_emit_attempt_success_stays_in_domain(emitted):
|
||||||
recorder = _MemoryRecorder()
|
recorder = _MemoryRecorder()
|
||||||
await TelemetryEmitter(recorder, text_cap=None).emit_attempt(
|
await TelemetryEmitter(recorder, text_cap=None, scope="LLM").emit_attempt(
|
||||||
request=_REQ,
|
request=_REQ,
|
||||||
source=_src(),
|
source=_src(),
|
||||||
call_id="cid",
|
call_id="cid",
|
||||||
@@ -263,6 +267,7 @@ async def test_emit_attempt_success_stays_in_domain(emitted):
|
|||||||
response=_resp(emitted),
|
response=_resp(emitted),
|
||||||
error=None,
|
error=None,
|
||||||
reasoning_applies=True,
|
reasoning_applies=True,
|
||||||
|
operation="chat",
|
||||||
)
|
)
|
||||||
assert recorder.rows[0]["usage_source"] in USAGE_SOURCES
|
assert recorder.rows[0]["usage_source"] in USAGE_SOURCES
|
||||||
|
|
||||||
@@ -270,7 +275,7 @@ async def test_emit_attempt_success_stays_in_domain(emitted):
|
|||||||
async def test_emit_attempt_failed_attempt_stays_in_domain():
|
async def test_emit_attempt_failed_attempt_stays_in_domain():
|
||||||
"""失败尝试无 response,`usage_source` 取 emitter 自己的字面量。"""
|
"""失败尝试无 response,`usage_source` 取 emitter 自己的字面量。"""
|
||||||
recorder = _MemoryRecorder()
|
recorder = _MemoryRecorder()
|
||||||
await TelemetryEmitter(recorder, text_cap=None).emit_attempt(
|
await TelemetryEmitter(recorder, text_cap=None, scope="LLM").emit_attempt(
|
||||||
request=_REQ,
|
request=_REQ,
|
||||||
source=_src(),
|
source=_src(),
|
||||||
call_id="cid",
|
call_id="cid",
|
||||||
@@ -278,6 +283,7 @@ async def test_emit_attempt_failed_attempt_stays_in_domain():
|
|||||||
response=None,
|
response=None,
|
||||||
error="boom",
|
error="boom",
|
||||||
reasoning_applies=True,
|
reasoning_applies=True,
|
||||||
|
operation="chat",
|
||||||
)
|
)
|
||||||
assert recorder.rows[0]["usage_source"] in USAGE_SOURCES
|
assert recorder.rows[0]["usage_source"] in USAGE_SOURCES
|
||||||
|
|
||||||
@@ -285,8 +291,10 @@ async def test_emit_attempt_failed_attempt_stays_in_domain():
|
|||||||
@pytest.mark.parametrize("emitted", _DOMAIN)
|
@pytest.mark.parametrize("emitted", _DOMAIN)
|
||||||
async def test_emit_cache_hit_stays_in_domain(emitted):
|
async def test_emit_cache_hit_stays_in_domain(emitted):
|
||||||
recorder = _MemoryRecorder()
|
recorder = _MemoryRecorder()
|
||||||
await TelemetryEmitter(recorder, text_cap=None).emit_cache_hit(
|
await TelemetryEmitter(recorder, text_cap=None, scope="LLM").emit_cache_hit(
|
||||||
request=_REQ, response=_resp(emitted)
|
request=_REQ,
|
||||||
|
response=_resp(emitted),
|
||||||
|
operation="chat",
|
||||||
)
|
)
|
||||||
assert recorder.rows[0]["usage_source"] in USAGE_SOURCES
|
assert recorder.rows[0]["usage_source"] in USAGE_SOURCES
|
||||||
|
|
||||||
@@ -294,7 +302,11 @@ async def test_emit_cache_hit_stays_in_domain(emitted):
|
|||||||
async def test_emit_terminal_failure_stays_in_domain():
|
async def test_emit_terminal_failure_stays_in_domain():
|
||||||
"""终态失败无具体源,`usage_source` 同样取 emitter 字面量。"""
|
"""终态失败无具体源,`usage_source` 同样取 emitter 字面量。"""
|
||||||
recorder = _MemoryRecorder()
|
recorder = _MemoryRecorder()
|
||||||
await TelemetryEmitter(recorder, text_cap=None).emit_terminal_failure(
|
await TelemetryEmitter(recorder, text_cap=None, scope="LLM").emit_terminal_failure(
|
||||||
request=_REQ, call_id="cid", latency_ms=10, error="cancelled"
|
request=_REQ,
|
||||||
|
call_id="cid",
|
||||||
|
error="cancelled",
|
||||||
|
operation="chat",
|
||||||
|
stats=_MIGRATED_STATS,
|
||||||
)
|
)
|
||||||
assert recorder.rows[0]["usage_source"] in USAGE_SOURCES
|
assert recorder.rows[0]["usage_source"] in USAGE_SOURCES
|
||||||
|
|||||||
Reference in New Issue
Block a user