e01420178f
The entity pages carry the rejected alternatives and why, so the next reader does not have to reconstruct the argument: minimal patch cannot fill a tier that does not exist, cherry's wire DSL buys four endpoint protocols we do not have, and default_effort lost its only consumer the moment enable_thinking=True became Effort.AUTO.
12 KiB
12 KiB
Research Wiki 索引
自动生成,更新时间:2026-09-05 04:07 UTC
design (41)
- 2026-07-20-m1-core-design
design:2026-07-20-m1-core-design - 2026-07-20-m2-distributed-design
design:2026-07-20-m2-distributed-design - 2026-07-21-m25-resilience-design
design:2026-07-21-m25-resilience-design - 2026-07-21-m3-ocr-design
design:2026-07-21-m3-ocr-design - 2026-07-22-m4-migration-design
design:2026-07-22-m4-migration-design - 2026-07-29-settings-invariant-guards-design
design:2026-07-29-settings-invariant-guards-design - 2026-07-30-est-tokens-decoupling-design
design:2026-07-30-est-tokens-decoupling-design - 2026-07-30-settings-invariants-round-2-design
design:2026-07-30-settings-invariants-round-2-design - 2026-07-31-response-observability-fields-design
design:2026-07-31-response-observability-fields-design - 2026-07-31-sampling-params-design
design:2026-07-31-sampling-params-design - 2026-08-06-governance-backend-error-design
design:2026-08-06-governance-backend-error-design - 2026-08-06-issue8-stall-budget-design
design:2026-08-06-issue8-stall-budget-design - 2026-08-16-issue10-error-body-retention-design
design:2026-08-16-issue10-error-body-retention-design - 2026-08-17-issue11-caller-dimensions-design
design:2026-08-17-issue11-caller-dimensions-design - 2026-08-19-issue12-telemetry-retention-design
design:2026-08-19-issue12-telemetry-retention-design - 2026-08-19-issue13-schema-mode-design
design:2026-08-19-issue13-schema-mode-design - 2026-08-19-issue14-admission-wait-policy-design
design:2026-08-19-issue14-admission-wait-policy-design - 2026-08-24-issue15-telemetry-pool-lifecycle-design
design:2026-08-24-issue15-telemetry-pool-lifecycle-design - 2026-09-04-reasoning-effort-design
design:2026-09-04-reasoning-effort-design - est_tokens 解耦: 拆分限流预扣与遥测用量兜底(issue #2)
design:est-tokens-decoupling - GatewaySettings 装配校验补齐(第二轮)
design:settings-invariants-round-2 - GatewaySettings 跨字段不变量守卫的生效范围
design:settings-invariant-guards - HTTP 错误响应体留存(Issue #10)
design:issue10-error-body-retention - issue #12: 遥测表的正文体量、保留期与访问控制
design:issue12-telemetry-retention - issue #13: 遥测 schema 自动 ALTER 降级为按后端不对称的显式档位
design:issue13-schema-mode - issue #15: 遥测连接池的资源语义与生命周期
design:issue15-telemetry-pool-lifecycle - issue #18: 隔离靠权限强制,目标靠显式声明
design:2026-08-26-issue18-pg-test-isolation - M1 核心里程碑设计:公共签名冻结与治理栈落地
design:m1-core-design - M2 分布式:Redis 治理后端+背压+Postgres 遥测+pricing+Embedding+压测 harness
design:m2-distributed - M2.5 治理韧性: 半死源隔离与健康感知调度
design:m25-resilience - M3 OCR 端口族设计
design:m3-ocr - M4 迁移验证设计(GovDoc→CHS,发 v1.0)
design:m4-migration - stall 判定改为非生产性等待口径
design:issue8-stall-budget - 响应可观测字段扩展(Issue #3)
design:response-observability-fields - 建表前先探测,判死只认「确定写不进去」
design:issue9-telemetry-ddl-probe - 推理可观测性一等化(issue #16 + #17)
design:2026-08-25-thinking-observability-design - 推理开关能力建模与 reasoning_tokens 采集(issue #5 + #6)
design:2026-08-02-thinking-capability-design - 推理档位一等化设计(issue #20 及其一般形式)
design:reasoning-effort - 治理后端故障归位为 scope 级不可用(Issue #7)
design:governance-backend-error - 调用方自定义维度设计(issue #11)
design:issue11-caller-dimensions - 采样参数透传设计(issue #4)
design:sampling-params
finding (14)
- 2026-07-20-m2-soak-workload
finding:2026-07-20-m2-soak-workload - 2026-07-21-m25-acceptance
finding:2026-07-21-m25-acceptance - 2026-07-21-p6-soak-baseline
finding:2026-07-21-p6-soak-baseline - 2026-07-22-m4-acceptance
finding:2026-07-22-m4-acceptance - 2026-07-22-p7-ocr-soak
finding:2026-07-22-p7-ocr-soak - issue #16/#17 实测: M3 推理正常,失效的是推理的可观测信号
finding:2026-08-25-thinking-observability-regression - issue #18 实测: 偶发红的是安全网本身,不是被测脚本
finding:2026-08-26-issue18-shared-pg-test-isolation - M2 verifier 三项 Important 补齐(不变量接线/网关保护/P3 验收)
finding:m2-verifier-fixes - M2 真实数据压测: 场景矩阵与数据清单
finding:m2-soak-workload - M2.5 验收: P6 同场景 58.1% → 98.96%
finding:m25-acceptance - M4 迁移验收(GovDoc+CHS)
finding:m4-acceptance - P6 混合浸泡首跑基线与记分板三重伪击穿修复
finding:p6-soak-baseline - P7 OCR soak 验收: 99.73% 与 13 不变量全 PASS
finding:p7-ocr-soak - 推理开关与 reasoning_tokens: 供应商实测与业界做法
finding:2026-08-02-thinking-switch-and-reasoning-tokens
plan (36)
- 2026-07-20-m1-core-plan
plan:2026-07-20-m1-core-plan - 2026-07-20-m2-distributed-plan
plan:2026-07-20-m2-distributed-plan - 2026-07-21-m25-resilience-plan
plan:2026-07-21-m25-resilience-plan - 2026-07-21-m3-ocr-plan
plan:2026-07-21-m3-ocr-plan - 2026-07-22-m4-migration-plan
plan:2026-07-22-m4-migration-plan - 2026-07-30-est-tokens-decoupling-plan
plan:2026-07-30-est-tokens-decoupling-plan - 2026-07-31-response-observability-fields
plan:2026-07-31-response-observability-fields - 2026-07-31-sampling-params
plan:2026-07-31-sampling-params - 2026-08-06-governance-backend-error-plan
plan:2026-08-06-governance-backend-error-plan - 2026-08-06-issue8-stall-budget
plan:2026-08-06-issue8-stall-budget - 2026-08-16-issue10-error-body-retention
plan:2026-08-16-issue10-error-body-retention - 2026-08-17-issue11-caller-dimensions
plan:2026-08-17-issue11-caller-dimensions - 2026-08-19-issue12-telemetry-retention
plan:2026-08-19-issue12-telemetry-retention - 2026-08-19-issue13-schema-mode
plan:2026-08-19-issue13-schema-mode - 2026-08-24-issue15-telemetry-pool-lifecycle
plan:2026-08-24-issue15-telemetry-pool-lifecycle - 2026-09-04-reasoning-effort
plan:2026-09-04-reasoning-effort - est_tokens 解耦实施计划
plan:est-tokens-decoupling - issue #18 实现计划: 权限边界替代行数快照 + --table 锁死目标
plan:2026-08-26-issue18-pg-test-isolation - issue #8 实施计划: stall 非生产性等待口径
plan:issue8-stall-budget-plan - M1 核心里程碑实现计划
plan:m1-core-plan - M2 分布式实现计划
plan:m2-distributed - M2.5 治理韧性实现计划
plan:m25-resilience - M3 OCR 实现计划
plan:m3-ocr - M4 迁移实现计划(T0-T14)
plan:m4-migration - plan-issue14-admission-wait-policy
plan:plan-issue14-admission-wait-policy - 响应可观测字段扩展实现计划
plan:response-observability-fields - 实现计划: HTTP 错误响应体留存(Issue #10)
plan:issue10-error-body-retention-plan - 实现计划: issue12-telemetry-retention
plan:plan-issue12-telemetry-retention - 实现计划: issue13-schema-mode
plan:plan-issue13-schema-mode - 实现计划: 推理档位一等化
plan:reasoning-effort - 实现计划: 治理后端故障归位为 scope 级不可用(Issue #7)
plan:governance-backend-error - 实现计划: 遥测连接池的资源语义与生命周期(issue #15)
plan:plan-issue15-telemetry-pool-lifecycle - 推理可观测性一等化实现计划(issue #16 + #17,发 1.3.1)
plan:2026-08-25-thinking-observability-plan - 推理开关能力建模与 reasoning_tokens 采集实施计划(issue #5 + #6)
plan:2026-08-02-thinking-capability - 调用方自定义维度实现计划(issue #11)
plan:issue11-caller-dimensions - 采样参数透传实现计划(issue #4)
plan:sampling-params-plan
review (1)
- 整分支审查: issue #14 熔断等待档
review:issue14-branch-review
schema (1)
- 表结构: llm_calls(遥测 25 字段)
schema:llm-calls
metric (2)
- OCR 治理调用成功率与错误分类分布
metric:ocr-call-success - 每次调用必录覆盖率(含缓存命中/失败/取消)
metric:call-telemetry-coverage