| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
docs(skills): migrate execution examples to shell and environment IDs | 1 个月前 | |
feat(idea-tree): add Python tree engine and file persistence | 29 天前 | |
first commit | 1 个月前 | |
feat(skills): 沙箱启动时放入本 Session 可见的整包 skill 改为在模型 loop 启动前，把本轮已选 skill 的完整冻结包写入本次执行专属的 快照根，并在沙箱中以只读 /skills/<skillId> 就位；Agent 不必再调用挂载或 提取工具，直接按普通文件路径读取、按显式 argv 执行捆绑脚本。 - 新增 prepareSkillSandbox：逐文件校验 size 与 SHA-256、以 0444 写入 staging、复核整包 hash、原子 rename 就位，并写入含 skillId/revision/ version/hash 的快照清单；清单一致时短路，不重读 live 磁盘文件。 - Runner 以 --ro-bind 挂 /skills，并把工作区内 .sciencediscovery/ skill-extensions 可写挂到 /skill-extensions 作为自演进预留位（本次只 预留，不实现自演进）；持久 kernel 与 shell 把快照根纳入挂载一致性校验。 - Prompt 为每个 skill 输出 package_path 与 package_hash，加载步骤改为读 包内 SKILL.md；无沙箱的嵌套 Agent 不 stage 包，回落到 read_skill。 - 删除上一版的 materialize_skill_resource 与 readResourceBytes，冻结 snapshot 改为提供整包 readPackageFiles；read_skill / read_skill_resource 语义不变。 - 文档与仓内 bundled skill 区分「启动时放入只读技能包」与「自动执行/安装」， 后者仍然禁止，并禁止全盘搜索包资源。 | 1 个月前 | |
first commit | 1 个月前 | |
feat(idea-tree): add Python tree engine and file persistence | 29 天前 | |
first commit | 1 个月前 | |
refactor(skills): trim evolve-design by 40% and move the custom_script contract out SKILL.md loads whole every time the skill triggers, and at 21.7KB much of it restated what the create_evolve_run tool already carries or told a measured anecdote at length. - Drop the cPuct / priorExponent walkthrough: the tool's parameter descriptions already hold the ranges and the reasoning. The skill keeps when to reach for each and that search is left out by default. - Move the custom_script evaluator contract, the error rule the probe enforces, how the script runs and the "evaluator reads nothing" constraint to references/custom-script.md, read only when that mode is chosen. SKILL.md keeps the one-line rule and points to it. - Cut the mode list and the "do not score a broken copy" passage down to what the tool descriptions do not say, and shorten the measured anecdotes to one clause each, keeping the rule and its reason. The four checkpoints, the sizing numbers, and every rule the probe or schema enforces are unchanged. SKILL.md goes from 21,685 to 12,983 bytes; the reference adds 2,633 on demand. Version 1.0.0 -> 1.1.0 in the frontmatter and in BUILT_IN_VERSIONS. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> | 23 天前 | |
fix(idea-tree): prepare evidence before leaf-only research execution | 29 天前 | |
feat(idea-tree): add Python tree engine and file persistence | 29 天前 | |
docs(skills): migrate execution examples to shell and environment IDs | 1 个月前 | |
first commit | 1 个月前 | |
first commit | 1 个月前 | |
first commit | 1 个月前 | |
first commit | 1 个月前 | |
feat(skills): add reviewable skill authoring workspace | 1 个月前 | |
feat(skills): 沙箱启动时放入本 Session 可见的整包 skill 改为在模型 loop 启动前，把本轮已选 skill 的完整冻结包写入本次执行专属的 快照根，并在沙箱中以只读 /skills/<skillId> 就位；Agent 不必再调用挂载或 提取工具，直接按普通文件路径读取、按显式 argv 执行捆绑脚本。 - 新增 prepareSkillSandbox：逐文件校验 size 与 SHA-256、以 0444 写入 staging、复核整包 hash、原子 rename 就位，并写入含 skillId/revision/ version/hash 的快照清单；清单一致时短路，不重读 live 磁盘文件。 - Runner 以 --ro-bind 挂 /skills，并把工作区内 .sciencediscovery/ skill-extensions 可写挂到 /skill-extensions 作为自演进预留位（本次只 预留，不实现自演进）；持久 kernel 与 shell 把快照根纳入挂载一致性校验。 - Prompt 为每个 skill 输出 package_path 与 package_hash，加载步骤改为读 包内 SKILL.md；无沙箱的嵌套 Agent 不 stage 包，回落到 read_skill。 - 删除上一版的 materialize_skill_resource 与 readResourceBytes，冻结 snapshot 改为提供整包 readPackageFiles；read_skill / read_skill_resource 语义不变。 - 文档与仓内 bundled skill 区分「启动时放入只读技能包」与「自动执行/安装」， 后者仍然禁止，并禁止全盘搜索包资源。 | 1 个月前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 1 个月前 | ||
| 29 天前 | ||
| 1 个月前 | ||
| 1 个月前 | ||
| 1 个月前 | ||
| 29 天前 | ||
| 1 个月前 | ||
| 23 天前 | ||
| 29 天前 | ||
| 29 天前 | ||
| 1 个月前 | ||
| 1 个月前 | ||
| 1 个月前 | ||
| 1 个月前 | ||
| 1 个月前 | ||
| 1 个月前 | ||
| 1 个月前 |