feat: preserve governed OpenAI tool messages in 1.4.0
Add faithful single-choice chat results, tool stream activity, error-frame retries, and isolated protocol caching. Reject empty cached completions with the same value predicate as transport, add regression coverage, and adopt Apache-2.0.
This commit is contained in:
+23
-11
@@ -1,9 +1,8 @@
|
||||
# Research Wiki 索引
|
||||
|
||||
> 自动生成,更新时间:2026-09-09 18:01 UTC
|
||||
|
||||
## design (43)
|
||||
> 自动生成,更新时间:2026-10-01 18:27 UTC
|
||||
|
||||
## design (47)
|
||||
- [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-m2-distributed-design](designs/2026-07-20-m2-distributed-design.md) `design:2026-07-20-m2-distributed-design`
|
||||
@@ -25,6 +24,9 @@
|
||||
- [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`
|
||||
- [2026-09-09-135-call-observability-design](designs/2026-09-09-135-call-observability-design.md) `design:2026-09-09-135-call-observability-design`
|
||||
- [2026-09-09-136-call-budgets-design](designs/2026-09-09-136-call-budgets-design.md) `design:2026-09-09-136-call-budgets-design`
|
||||
- [2026-09-10-24-hedged-requests-design](designs/2026-09-10-24-hedged-requests-design.md) `design:2026-09-10-24-hedged-requests-design`
|
||||
- [2026-09-11-streaming-stall-design](designs/2026-09-11-streaming-stall-design.md) `design:2026-09-11-streaming-stall-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`
|
||||
- [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`
|
||||
@@ -38,6 +40,7 @@
|
||||
- [M2.5 治理韧性: 半死源隔离与健康感知调度](designs/m25-resilience.md) `design:m25-resilience`
|
||||
- [M3 OCR 端口族设计](designs/m3-ocr.md) `design:m3-ocr`
|
||||
- [M4 迁移验证设计(GovDoc→CHS,发 v1.0)](designs/m4-migration.md) `design:m4-migration`
|
||||
- [OpenAI消息保真设计](designs/2026-10-01-issue29-openai-fidelity-design.md) `design:2026-10-01-issue29-openai-fidelity-design`
|
||||
- [stall 判定改为非生产性等待口径](designs/issue8-stall-budget.md) `design:issue8-stall-budget`
|
||||
- [响应可观测字段扩展(Issue #3)](designs/response-observability-fields.md) `design:response-observability-fields`
|
||||
- [建表前先探测,判死只认「确定写不进去」](designs/issue9-telemetry-ddl-probe.md) `design:issue9-telemetry-ddl-probe`
|
||||
@@ -48,18 +51,22 @@
|
||||
- [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`
|
||||
|
||||
## finding (17)
|
||||
|
||||
## finding (22)
|
||||
- [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`
|
||||
- [1.3.5 发布完成与外部验收:合并后门、registry 产物与页面亲查](findings/2026-09-09-135-release-completion.md) `finding:2026-09-09-135-release-completion`
|
||||
- [1.3.6 可选调用期限与取消结算验证记录](findings/2026-09-10-136-call-deadline-validation.md) `finding:2026-09-10-136-call-deadline-validation`
|
||||
- [1.3.8 流式中段沉默:净口径与中段对冲验证报告](findings/2026-09-11-streaming-stall-validation.md) `finding:2026-09-11-streaming-stall-validation`
|
||||
- [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-p6-soak-baseline](findings/2026-07-21-p6-soak-baseline.md) `finding:2026-07-21-p6-soak-baseline`
|
||||
- [2026-07-22-m4-acceptance](findings/2026-07-22-m4-acceptance.md) `finding:2026-07-22-m4-acceptance`
|
||||
- [2026-07-22-p7-ocr-soak](findings/2026-07-22-p7-ocr-soak.md) `finding:2026-07-22-p7-ocr-soak`
|
||||
- [2026-09-11-streaming-stall-hedging-research](findings/2026-09-11-streaming-stall-hedging-research.md) `finding:2026-09-11-streaming-stall-hedging-research`
|
||||
- [2026-10-01-issue29-license-audit](findings/2026-10-01-issue29-license-audit.md) `finding:2026-10-01-issue29-license-audit`
|
||||
- [issue #16/#17 实测: M3 推理正常,失效的是推理的可观测信号](findings/2026-08-25-thinking-observability-regression.md) `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](findings/2026-08-26-issue18-shared-pg-test-isolation.md) `finding:2026-08-26-issue18-shared-pg-test-isolation`
|
||||
- [issue #24 长尾对冲请求与裸生成时间验证报告](findings/2026-09-10-24-hedged-requests-validation.md) `finding:2026-09-10-24-hedged-requests-validation`
|
||||
- [M2 verifier 三项 Important 补齐(不变量接线/网关保护/P3 验收)](findings/m2-verifier-fixes.md) `finding:m2-verifier-fixes`
|
||||
- [M2 真实数据压测: 场景矩阵与数据清单](findings/m2-soak-workload.md) `finding:m2-soak-workload`
|
||||
- [M2.5 验收: P6 同场景 58.1% → 98.96%](findings/m25-acceptance.md) `finding:m25-acceptance`
|
||||
@@ -68,10 +75,11 @@
|
||||
- [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`
|
||||
|
||||
## plan (38)
|
||||
|
||||
## plan (42)
|
||||
- [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`
|
||||
- [1.3.6 可选调用期限与取消结算修复实施计划](plans/2026-09-10-136-call-deadline.md) `plan:2026-09-10-136-call-deadline`
|
||||
- [1.3.8 流式中段沉默:计量口径与对冲实施计划](plans/2026-09-11-streaming-stall.md) `plan:2026-09-11-streaming-stall`
|
||||
- [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`
|
||||
- [2026-07-21-m25-resilience-plan](plans/2026-07-21-m25-resilience-plan.md) `plan:2026-07-21-m25-resilience-plan`
|
||||
@@ -90,12 +98,14 @@
|
||||
- [2026-09-04-reasoning-effort](plans/2026-09-04-reasoning-effort.md) `plan:2026-09-04-reasoning-effort`
|
||||
- [est_tokens 解耦实施计划](plans/est-tokens-decoupling.md) `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](plans/2026-08-26-issue18-pg-test-isolation.md) `plan:2026-08-26-issue18-pg-test-isolation`
|
||||
- [issue #24 长尾对冲请求与裸生成时间实施计划](plans/2026-09-10-24-hedged-requests.md) `plan:2026-09-10-24-hedged-requests`
|
||||
- [issue #8 实施计划: stall 非生产性等待口径](plans/issue8-stall-budget-plan.md) `plan:issue8-stall-budget-plan`
|
||||
- [M1 核心里程碑实现计划](plans/m1-core-plan.md) `plan:m1-core-plan`
|
||||
- [M2 分布式实现计划](plans/m2-distributed.md) `plan:m2-distributed`
|
||||
- [M2.5 治理韧性实现计划](plans/m25-resilience.md) `plan:m25-resilience`
|
||||
- [M3 OCR 实现计划](plans/m3-ocr.md) `plan:m3-ocr`
|
||||
- [M4 迁移实现计划(T0-T14)](plans/m4-migration.md) `plan:m4-migration`
|
||||
- [OpenAI消息保真实现计划](plans/2026-10-01-issue29-openai-fidelity.md) `plan:2026-10-01-issue29-openai-fidelity`
|
||||
- [plan-issue14-admission-wait-policy](plans/plan-issue14-admission-wait-policy.md) `plan:plan-issue14-admission-wait-policy`
|
||||
- [响应可观测字段扩展实现计划](plans/response-observability-fields.md) `plan:response-observability-fields`
|
||||
- [实现计划: HTTP 错误响应体留存(Issue #10)](plans/issue10-error-body-retention-plan.md) `plan:issue10-error-body-retention-plan`
|
||||
@@ -109,15 +119,17 @@
|
||||
- [调用方自定义维度实现计划(issue #11)](plans/issue11-caller-dimensions.md) `plan:issue11-caller-dimensions`
|
||||
- [采样参数透传实现计划(issue #4)](plans/sampling-params-plan.md) `plan:sampling-params-plan`
|
||||
|
||||
## review (1)
|
||||
|
||||
## review (6)
|
||||
- [2026-09-11-138-branch-review](reviews/2026-09-11-138-branch-review.md) `review:2026-09-11-138-branch-review`
|
||||
- [2026-09-11-138-verifier](reviews/2026-09-11-138-verifier.md) `review:2026-09-11-138-verifier`
|
||||
- [2026-09-11-streaming-stall-design-review](reviews/2026-09-11-streaming-stall-design-review.md) `review:2026-09-11-streaming-stall-design-review`
|
||||
- [2026-09-11-streaming-stall-plan-review](reviews/2026-09-11-streaming-stall-plan-review.md) `review:2026-09-11-streaming-stall-plan-review`
|
||||
- [保真缓存审查修复与1.4.0准备](reviews/2026-10-01-issue29-cache-review.md) `review:2026-10-01-issue29-cache-review`
|
||||
- [整分支审查: issue #14 熔断等待档](reviews/issue14-branch-review.md) `review:issue14-branch-review`
|
||||
|
||||
## schema (1)
|
||||
|
||||
- [表结构: llm_calls(遥测 36 字段)](schemas/llm-calls.md) `schema:llm-calls`
|
||||
|
||||
## metric (2)
|
||||
|
||||
- [OCR 治理调用成功率与错误分类分布](metrics/ocr-call-success.md) `metric:ocr-call-success`
|
||||
- [每次调用必录覆盖率(含缓存命中/失败/取消)](metrics/call-telemetry-coverage.md) `metric:call-telemetry-coverage`
|
||||
|
||||
Reference in New Issue
Block a user