test(canary): D-30 普通模型 canary 达标——typed 参数契约迁移验收收口(#112) - #148
Merged
Conversation
…N Schema,强制 tool_choice 量「参数一次成型」;validateJsonSchemaValue 与 defineTool 同款校验;不执行工具零副作用;隔离 stateRoot;达标线 ≥90%,不达标不合入
…canary.ts 运行器:真实 LLM(MiniMax-M2.7)× 投影后工具 JSON Schema × 强制 tool_choice,10 用例 10/10 一次成型 100%(达标线 90%);不执行工具零副作用,隔离 stateRoot;二级观察:无锚点卡时模型裸猜年份由既有时间锚点卡+过去日期闸纠正(非 D-30 缺陷);D-30 全面清偿入 §10.2 存档,§9/roadmap/stage1 同步
… into tmp-refresh-148
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #112
摘要
D-30 的最后一道门(普通模型 canary)通过,typed 参数契约迁移全面验收完成:
ts/scripts/typed-contract-canary.ts运行器(入仓复用,后续任何契约迁移照跑):真实 LLM × 投影后工具 JSON Schema × 强制 tool_choice,量「参数一次成型」;validateJsonSchemaValue 与 defineTool 同款校验;不执行工具零副作用;隔离 stateRoot。验证
合并顺序:建议 #125(若未合)→ 本 PR;内容为验收收口,无生产行为变更。