iomgaa
4c135075b3
A sixteen-row matrix over 127 real calls: disable and enable on MiniMax-M3 in both streaming and non-streaming mode, extra_body winning over the profile slot, qwen and deepseek still disabling correctly, a drift sentinel that re-derives every registered capability from live behaviour, and the assembly guard refusing the models that cannot comply. Two judgement criteria had to be corrected by the data they were meant to judge. Output length cannot separate the two regimes at all -- the disabled runs reach 46 tokens when the model narrates its working in the visible answer, and the enabled runs drop to 13 when medium effort barely thinks. reasoning_tokens separates them cleanly in both directions, which is precisely what issue #6 was collected for. A second anchor compares prompt_tokens between the two regimes: the vendor injects a reasoning instruction when thinking is on, so the input side grows, and comparing the two runs relatively avoids hardcoding any vendor number. Provider names are mapped explicitly rather than guessed from the model string; guessing had silently skipped the qwen row behind a "source unavailable" reason that was not true.
87 lines
6.8 KiB
Markdown
87 lines
6.8 KiB
Markdown
# Wiki 变更日志
|
|
|
|
- [2026-07-20 09:55 UTC] Wiki 初始化完成
|
|
- [2026-07-20 09:55 UTC] 重建索引: 2 篇页面
|
|
- [2026-07-20 10:18 UTC] 新增 plan: M1 核心里程碑实现计划 (plan:m1-core-plan)
|
|
- [2026-07-20 10:18 UTC] 新增边: plan:m1-core-plan --implements--> design:m1-core-design
|
|
- [2026-07-20 10:18 UTC] 重建索引: 4 篇页面
|
|
- [2026-07-20 11:11 UTC] 新增 schema: 表结构: llm_calls(遥测 18 字段) (schema:llm-calls)
|
|
- [2026-07-20 11:11 UTC] 新增 metric: 每次调用必录覆盖率(含缓存命中/失败/取消) (metric:call-telemetry-coverage)
|
|
- [2026-07-20 11:11 UTC] 新增边: metric:call-telemetry-coverage --measures--> schema:llm-calls
|
|
- [2026-07-20 11:11 UTC] 新增边: schema:llm-calls --implements--> design:m1-core-design
|
|
- [2026-07-20 11:11 UTC] 重建索引: 6 篇页面
|
|
- [2026-07-21 02:27 UTC] 新增 finding: M2 真实数据压测: 场景矩阵与数据清单 (finding:m2-soak-workload)
|
|
- [2026-07-21 02:27 UTC] 重建索引: 8 篇页面
|
|
- [2026-07-21 02:59 UTC] 新增 design: M2 分布式:Redis 治理后端+背压+Postgres 遥测+pricing+Embedding+压测 harness (design:m2-distributed)
|
|
- [2026-07-21 02:59 UTC] 重建索引: 10 篇页面
|
|
- [2026-07-21 03:46 UTC] 新增 plan: M2 分布式实现计划 (plan:m2-distributed)
|
|
- [2026-07-21 03:46 UTC] 新增边: plan:m2-distributed --implements--> design:m2-distributed
|
|
- [2026-07-21 03:46 UTC] 重建索引: 12 篇页面
|
|
- [2026-07-21 06:00 UTC] 新增 finding: M2 verifier 三项 Important 补齐(不变量接线/网关保护/P3 验收) (finding:m2-verifier-fixes)
|
|
- [2026-07-21 06:00 UTC] 重建索引: 13 篇页面
|
|
- [2026-07-21 11:19 UTC] 新增 finding: P6 混合浸泡首跑基线与记分板三重伪击穿修复 (finding:p6-soak-baseline)
|
|
- [2026-07-21 11:19 UTC] 重建索引: 15 篇页面
|
|
- [2026-07-21 12:26 UTC] 新增 design: M2.5 治理韧性: 半死源隔离与健康感知调度 (design:m25-resilience)
|
|
- [2026-07-21 12:26 UTC] 重建索引: 17 篇页面
|
|
- [2026-07-21 12:30 UTC] 新增 plan: M2.5 治理韧性实现计划 (plan:m25-resilience)
|
|
- [2026-07-21 12:30 UTC] 新增边: plan:m25-resilience --implements--> design:m25-resilience
|
|
- [2026-07-21 12:30 UTC] 重建索引: 19 篇页面
|
|
- [2026-07-21 21:34 UTC] 新增 finding: M2.5 验收: P6 同场景 58.1% → 98.96% (finding:m25-acceptance)
|
|
- [2026-07-21 21:34 UTC] 重建索引: 21 篇页面
|
|
- [2026-07-22 01:37 UTC] 新增 design: M3 OCR 端口族设计 (design:m3-ocr)
|
|
- [2026-07-22 01:37 UTC] 重建索引: 23 篇页面
|
|
- [2026-07-22 02:05 UTC] 新增 metric: OCR 治理调用成功率与错误分类分布 (metric:ocr-call-success)
|
|
- [2026-07-22 02:05 UTC] 新增边: metric:ocr-call-success --measures--> schema:llm-calls
|
|
- [2026-07-22 02:05 UTC] 新增边: schema:llm-calls --implements--> design:m3-ocr
|
|
- [2026-07-22 02:05 UTC] 重建索引: 24 篇页面
|
|
- [2026-07-22 02:09 UTC] 新增 plan: M3 OCR 实现计划 (plan:m3-ocr)
|
|
- [2026-07-22 02:09 UTC] 新增边: plan:m3-ocr --implements--> design:m3-ocr
|
|
- [2026-07-22 02:09 UTC] 重建索引: 26 篇页面
|
|
- [2026-07-22 05:33 UTC] 新增 finding: P7 OCR soak 验收: 99.73% 与 13 不变量全 PASS (finding:p7-ocr-soak)
|
|
- [2026-07-22 05:33 UTC] 重建索引: 28 篇页面
|
|
- [2026-07-22 08:58 UTC] 新增 design: M4 迁移验证设计(GovDoc→CHS,发 v1.0) (design:m4-migration)
|
|
- [2026-07-22 08:58 UTC] 重建索引: 30 篇页面
|
|
- [2026-07-22 09:33 UTC] 新增 plan: M4 迁移实现计划(T0-T14) (plan:m4-migration)
|
|
- [2026-07-22 09:33 UTC] 新增边: plan:m4-migration --implements--> design:m4-migration
|
|
- [2026-07-22 09:33 UTC] 重建索引: 32 篇页面
|
|
- [2026-07-22 14:36 UTC] 新增 finding: M4 迁移验收(GovDoc+CHS) (finding:m4-acceptance)
|
|
- [2026-07-22 14:36 UTC] 重建索引: 34 篇页面
|
|
- [2026-07-30 03:44 UTC] 新增 design: GatewaySettings 跨字段不变量守卫的生效范围 (design:settings-invariant-guards)
|
|
- [2026-07-30 03:44 UTC] 重建索引: 36 篇页面
|
|
- [2026-07-30 04:44 UTC] 新增 design: GatewaySettings 装配校验补齐(第二轮) (design:settings-invariants-round-2)
|
|
- [2026-07-30 04:44 UTC] 重建索引: 38 篇页面
|
|
- [2026-07-30 09:32 UTC] 新增 design: est_tokens 解耦: 拆分限流预扣与遥测用量兜底(issue #2) (design:est-tokens-decoupling)
|
|
- [2026-07-30 09:33 UTC] 重建索引: 40 篇页面
|
|
- [2026-07-30 09:33 UTC] 新增边: design:est-tokens-decoupling --refines--> design:m1-core-design
|
|
- [2026-07-30 09:33 UTC] 重建索引: 40 篇页面
|
|
- [2026-07-30 09:39 UTC] 新增 plan: est_tokens 解耦实施计划 (plan:est-tokens-decoupling)
|
|
- [2026-07-30 09:39 UTC] 新增边: plan:est-tokens-decoupling --implements--> design:est-tokens-decoupling
|
|
- [2026-07-30 09:39 UTC] 重建索引: 42 篇页面
|
|
- [2026-07-31 08:35 UTC] 新增 design: 响应可观测字段扩展(Issue #3) (design:response-observability-fields)
|
|
- [2026-07-31 08:37 UTC] 重建索引: 44 篇页面
|
|
- [2026-07-31 11:10 UTC] 新增 plan: 响应可观测字段扩展实现计划 (plan:response-observability-fields)
|
|
- [2026-07-31 11:10 UTC] 新增边: plan:response-observability-fields --implements--> design:response-observability-fields
|
|
- [2026-07-31 11:10 UTC] 重建索引: 46 篇页面
|
|
- [2026-07-31 11:11 UTC] 重建索引: 46 篇页面
|
|
- [2026-07-31 12:25 UTC] 重建索引: 46 篇页面
|
|
- [2026-07-31 15:57 UTC] 新增 design: 采样参数透传设计(issue #4) (design:sampling-params)
|
|
- [2026-07-31 15:57 UTC] 重建索引: 48 篇页面
|
|
- [2026-07-31 16:00 UTC] 重建索引: 48 篇页面
|
|
- [2026-07-31 16:31 UTC] 重建索引: 48 篇页面
|
|
- [2026-07-31 16:59 UTC] 新增 plan: 采样参数透传实现计划(issue #4) (plan:sampling-params-plan)
|
|
- [2026-07-31 16:59 UTC] 新增边: plan:sampling-params-plan --implements--> design:sampling-params
|
|
- [2026-07-31 16:59 UTC] 重建索引: 50 篇页面
|
|
- [2026-07-31 17:01 UTC] 重建索引: 50 篇页面
|
|
- [2026-08-01 01:58 UTC] 重建索引: 50 篇页面
|
|
- [2026-08-02 09:38 UTC] 重建索引: 52 篇页面
|
|
- [2026-08-02 09:38 UTC] 新增边: finding:2026-08-02-thinking-switch-and-reasoning-tokens --supports--> design:2026-08-02-thinking-capability-design
|
|
- [2026-08-02 09:38 UTC] 新增 finding: 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)
|
|
- [2026-08-02 09:38 UTC] 新增 design: 推理开关能力建模与 reasoning_tokens 采集 issue #5+#6 (design:2026-08-02-thinking-capability-design)
|
|
- [2026-08-02 09:39 UTC] 重建 Query Pack: 29 字符
|
|
- [2026-08-02 09:49 UTC] 重建索引: 53 篇页面
|
|
- [2026-08-02 09:49 UTC] 新增边: plan:2026-08-02-thinking-capability --implements--> design:2026-08-02-thinking-capability-design
|
|
- [2026-08-02 09:49 UTC] 新增 plan: 推理开关能力建模与 reasoning_tokens 采集实施计划 (plan:2026-08-02-thinking-capability)
|
|
- [2026-08-02 09:49 UTC] 重建索引: 53 篇页面
|
|
- [2026-08-02 10:55 UTC] 重建索引: 53 篇页面
|
|
- [2026-08-02 10:55 UTC] 更新 finding: 补 §2.5 输出长度不是有效判别量(e2e 各 15 轮实测)
|