Conversation
记录 160 次固定请求和 16 轮新场景的 217 次真实模型调用，保留原始上下文、候选、用量、失败和独立核验。 比较 A/B/C/D 的资源选择及台词盲评，将自方条件披露与动作过滤的效果分开，更新 Agent 世界 PRD 的实验结论和后继范围。 真实调用结束后补充余额 24/25/26、库存 0/1/2 的确定性测试，Python 24 项通过；运行函数与真实语料保持冻结版本。
Closed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
此前 NPC 在本人资源数值已披露时仍选择不可行交易，台词也出现无依据环境断言。本次增加独立 A/B/C/D 实验适配器及 Unity 入口，分别比较原上下文、事实边界、自方条件和动作过滤；生产默认策略保持原行为。
完成 160 次固定请求与 16 轮重新初始化的双方真实场景，共 217 次 v4-flash 调用、254,299 tokens。固定请求中，已知不足时的不可行动作为 A/B/C/D = 7/15、8/15、2/15、0/15；D 的结果来自程序过滤。可行探针有效继续合作为 15/15、13/15、15/15、15/15，B 的两次失败把 planId 嵌套在 social 内。台词仍有无依据事实，B/C/D 在已交付发言探针中处理相同，不能把分组波动归因于资源规则。
16 轮均通过资产与日程恢复检查；四组各一次充足配置均交付，C/D 在两种不足配置分别拒绝或等待。保留 A 的一次过期候选取消。每场景每组仅一次，不据此估算长期可靠率。
验证：运行前 Python 22 项通过；实验后补齐余额 24/25/26 与库存 0/1/2 边界，Python 24 项通过，运行函数未变。隔离 Unity 完整 PlayMode 175 项通过、4 项显式外部测试跳过；真实实验入口 1 项通过，包含上述 16 轮。完整回归使用基准加相同测试文件，真实场景在干净的 d40fe70 实验检出运行，详细版本依据见报告。
实验报告记录原始失败、两份独立盲评及分歧、未知位置边界与时间戳限制；证据及哈希可核对全部请求与用量。关联：对照验证 NPC 环境上下文与资源条件。
本 PR 基于 codex/research-npc-environment-grounding，保持 Draft、未合并。后续资源策略、协议校验及局部观察玩法在现有后继票据中继续决定。