Skip to content

feat(benchmark): Round 8——bridge 工具 generic typed schema + 可恢复 domain-error 契约(#100/#102) - #151

Merged
Danceiny merged 2 commits into
feat/session-hotel-train-doctorfrom
issue/100-102-kernel-round8
Sep 5, 2026
Merged

feat(benchmark): Round 8——bridge 工具 generic typed schema + 可恢复 domain-error 契约(#100/#102)#151
Danceiny merged 2 commits into
feat/session-hotel-train-doctorfrom
issue/100-102-kernel-round8

Conversation

@Danceiny

@Danceiny Danceiny commented Sep 4, 2026

Copy link
Copy Markdown
Owner

摘要(Round 8,承 Round 7「下一轮聚焦」)

  1. generic typed schema:gotry_benchmark_environment 参数面 query blob → typed 三字段(action 枚举 tools/call/errors required + tool + arguments additionalProperties:true)——模型可见逐字段契约,与产品面 D-30 同刀法;benchmark child 内普通模型对参数形状不再靠猜。
  2. 可恢复 domain-error 契约:BRIDGE_ERROR_CONTRACT 封闭词表(10 码 × recoverable/remedy)经 action=errors 可拉取——模型失败后机器取回恢复指引,不再吞进 opaque 的 child_runtime_error;失败返回的扁平形状保持不变(benchmark 诊断面依赖不受扰)。
  3. conformance 契约面同刀法更新:tool/call 校验与 system prompt 教学形态从 query blob 改为平铺(e2e 全链验证:bridge 派发→成功结果→terminal 收敛)。

验证

边界

frozen treatment 的可评分终态仍需 founder 侧环境跑批;本 PR 不声称 external closure。issues #100/#102 保持 open(kernel 轨持续推进)。

…-error 契约(issue #100/#102)——gotry_benchmark_environment 参数面 query blob → typed 三字段(action 枚举 tools/call/errors + tool + arguments additionalProperties:true,模型可见逐字段契约,与产品面 D-30 同刀法);新增 BRIDGE_ERROR_CONTRACT 封闭词表(10 码 × recoverable/remedy)经 action=errors 可拉取——模型失败后可机器取回恢复指引,不再吞进 opaque 的 child_runtime_error;失败返回的扁平形状保持不变(benchmark 诊断面依赖);tests:blob 调用点平铺改写 + errors 契约表断言 + 枚举外 action/非对象 arguments 的宿主权 ToolArgsError 断言;bridge tests 绿;tsc 绿
Base automatically changed from issue/112-canary to feat/session-hotel-train-doctor September 5, 2026 05:42
@Danceiny
Danceiny merged commit af7341d into feat/session-hotel-train-doctor Sep 5, 2026
3 checks passed
@Danceiny
Danceiny deleted the issue/100-102-kernel-round8 branch September 5, 2026 05:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant