From 39d65df019cf214c9cdc483c27c709d22a893f86 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Wed, 29 Jul 2026 11:21:06 +0800 Subject: [PATCH] test(snapshot): tokenize the todo-write fixture cwd; correct the sidecar count The fixture committed the generated Linux workspace path instead of the `{{cwd}}` token every other acp recording uses. The normalizer masked it so replay passed, but the next record or refresh would rewrite the file for no reason; refresh is now byte-stable on it. The Agent Note's schema-pin arithmetic predated master's `toolSchemasSource` sharing: seven of the eight sidecars carry the todo schema, and scenarios composing an identical header share one rather than each keeping a copy. --- .../feature/2026-07-26-todo-parallel-in-progress.i18n.yaml | 4 ++-- .../feature/2026-07-26-todo-parallel-in-progress.md | 2 +- .../feature/2026-07-26-todo-parallel-in-progress.zh.md | 2 +- examples/acp-agent/tests/snapshots/todo-write/session.jsonl | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml index 1daf12d8e6..5148b112be 100644 --- a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md -2026-07-26-todo-parallel-in-progress.md: f1fdb9a96e8b689dba71c448924bbad6cb207420 -2026-07-26-todo-parallel-in-progress.zh.md: fe79952652c138c59dd5ab4da316bab97e880fe5 +2026-07-26-todo-parallel-in-progress.md: 61bfe4bdf03441fa2369683060efcbc35493a95f +2026-07-26-todo-parallel-in-progress.zh.md: e4098cd0c3151867c788b15b3226cff866f6c23d diff --git a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md index f1fdb9a96e..61bfe4bdf0 100644 --- a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md +++ b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md @@ -39,4 +39,4 @@ Splitting the count into its own span puts it outside the `.summary` rule, so it ## Consequences -A todo list can now faithfully mirror parallel execution, and every UI renders several active markers at once: the TUI's per-status prefix needed no change, the plan strip's header counts the active items, and the row needed the derivation above. The tool no longer rejects a formerly-invalid snapshot shape, so the change is compatible with every previously valid call; only the error path was removed. The model-facing description changed, which re-recorded the tool-catalog page and every `pinsHeader` scenario's `tool-schemas.expected.json` (ten of them carry the todo schema). Each new pinning scenario master gains carries its own copy of that description, so a branch changing the tool description has to refresh the pins that landed after it branched — `pnpm run test:snapshot:refresh` does it keylessly. The web fixture's todo sample now runs two items `in_progress`, so the assembled web transcript replays a parallel plan and would fail again if either surface returned to single-active derivation. +A todo list can now faithfully mirror parallel execution, and every UI renders several active markers at once: the TUI's per-status prefix needed no change, the plan strip's header counts the active items, and the row needed the derivation above. The tool no longer rejects a formerly-invalid snapshot shape, so the change is compatible with every previously valid call; only the error path was removed. The model-facing description changed, which re-recorded the tool-catalog page and every `tool-schemas.expected.json` sidecar carrying the todo schema (seven of the eight in the tree). Scenarios composing an identical header share one sidecar through `toolSchemasSource` rather than each keeping a copy, so the count tracks distinct header compositions, not scenarios; a branch changing the tool description still has to refresh whichever sidecars landed after it branched — `pnpm run test:snapshot:refresh` does it keylessly. The web fixture's todo sample now runs two items `in_progress`, so the assembled web transcript replays a parallel plan and would fail again if either surface returned to single-active derivation. diff --git a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md index fe79952652..e4098cd0c3 100644 --- a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md +++ b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md @@ -39,4 +39,4 @@ Status: implemented ## 后果 -现在 todo 列表可以忠实反映并行执行，并且每个 UI 都能一次渲染多个活跃标记：TUI 按状态区分的前缀无需改动，计划横条的表头会计数活跃条目，工具行则需要上述推导。工具不再拒绝一种此前无效的快照形状，因此该改动兼容此前所有合法的调用；被移除的只是错误路径。面向模型的描述发生了变化，这重新记录了 tool-catalog 页面以及每个 `pinsHeader` 场景的 `tool-schemas.expected.json`（其中十个带有 todo schema）。master 每新增一个 pin 场景，就会自带一份该描述的副本，因此改动工具描述的分支必须刷新它分叉之后落地的那些 pin —— `pnpm run test:snapshot:refresh` 可以无 key 完成。web fixture 的 todo 样本现在有两个条目处于 `in_progress`，因此组装后的 web transcript 回放的是一个并行计划；若任一展示面退回单活跃项推导，它会再次失败。 +现在 todo 列表可以忠实反映并行执行，并且每个 UI 都能一次渲染多个活跃标记：TUI 按状态区分的前缀无需改动，计划横条的表头会计数活跃条目，工具行则需要上述推导。工具不再拒绝一种此前无效的快照形状，因此该改动兼容此前所有合法的调用；被移除的只是错误路径。面向模型的描述发生了变化，这重新记录了 tool-catalog 页面以及每个带有 todo schema 的 `tool-schemas.expected.json` sidecar（树中八个里有七个）。组合出相同 header 的场景通过 `toolSchemasSource` 共用同一份 sidecar，而非各自保留副本，因此这个数量对应的是不同的 header 组合，而不是场景数；改动工具描述的分支仍须刷新它分叉之后落地的那些 sidecar —— `pnpm run test:snapshot:refresh` 可以无 key 完成。web fixture 的 todo 样本现在有两个条目处于 `in_progress`，因此组装后的 web transcript 回放的是一个并行计划；若任一展示面退回单活跃项推导，它会再次失败。 diff --git a/examples/acp-agent/tests/snapshots/todo-write/session.jsonl b/examples/acp-agent/tests/snapshots/todo-write/session.jsonl index b6724d4768..4bd1f3ff1b 100644 --- a/examples/acp-agent/tests/snapshots/todo-write/session.jsonl +++ b/examples/acp-agent/tests/snapshots/todo-write/session.jsonl @@ -1,4 +1,4 @@ -{"type":"session","version":0,"id":"3f78454d-3fa3-438c-b788-968a644a42e5","createdAt":1785016210496,"cwd":"/tmp/acp-snap-cwd-hVg513","delegationDepth":0} +{"type":"session","version":0,"id":"3f78454d-3fa3-438c-b788-968a644a42e5","createdAt":1785016210496,"cwd":"{{cwd}}","delegationDepth":0} {"type":"turn/start","seq":0,"time":1785016210501,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1785016210502,"data":{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos for work running in parallel: \"read the code\" (in_progress), \"watch the background build\" (in_progress), \"write the fix\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"c54096e4-65eb-41db-8ca7-9fb38a217f1f"},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1785016210504,"data":{"title":"Use the todo_write tool to","messageSeqs":[1],"source":{"kind":"fallback"}}}