From 7c2fb0a6fe9d4edc14d61028a18d9f3b08ff0573 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 21 Jul 2026 04:55:56 +0800 Subject: [PATCH] fix: keep Code Mode result cards complete --- ...de-mode-result-card-completeness.i18n.yaml | 6 +++ ...7-20-code-mode-result-card-completeness.md | 37 ++++++++++++++++++ ...0-code-mode-result-card-completeness.zh.md | 37 ++++++++++++++++++ .../feature/2026-06-15-code-mode.md | 2 +- .../snapshots/code-mode-turn/session.jsonl | 10 ++--- .../code-mode-turn/stdout.expected.jsonl | 4 +- .../tests/snapshots/code-mode/session.jsonl | 10 ++--- .../snapshots/code-mode/terminal.expected.txt | 30 ++++++++------- packages/core/tools/src/code-mode.ts | 26 ++----------- packages/core/tools/tests/code-mode.spec.ts | 38 ++++++++++--------- 10 files changed, 133 insertions(+), 67 deletions(-) create mode 100644 .agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.i18n.yaml create mode 100644 .agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.md create mode 100644 .agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.zh.md diff --git a/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.i18n.yaml new file mode 100644 index 0000000000..2466af8f85 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# 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 +2026-07-20-code-mode-result-card-completeness.md: 65aad02713498f5dbeff5ab3886da558326a0003 +2026-07-20-code-mode-result-card-completeness.zh.md: 082e209544d4ea43f75bb979fc3aa490b426952e diff --git a/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.md b/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.md new file mode 100644 index 0000000000..65aad02713 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.md @@ -0,0 +1,37 @@ +# Agent Note: Keep the Code Mode result card complete + +Status: implemented + +English | [中文](2026-07-20-code-mode-result-card-completeness.zh.md) + +## Problem + +The outer `run_code` tool persisted complete rendered content, but its editor presenter ignored that content and rebuilt the card body from a logs-only `presentationMeta` projection. A result-only run appeared correct because an empty presenter body let ACP and TUI fall back to `tool/result.content`. Once the program emitted a log, the presenter supplied non-empty content, that fallback stopped, and the returned value disappeared from the completed card. Failure text and a spill policy's final head/tail preview were vulnerable to the same split ownership. + +Nested Code calls never owned cards, so producing metadata for the outer call solely to reconstruct one incomplete card also obscured the intended one-card boundary. + +## Decision + +The `run_code` output renderer remains the single owner of model-facing outer content. It renders captured logs followed by the return value, the explicit no-output marker, or the failure content produced by the canonical tool pipeline. Post-execute policy and spill may replace that content before it is persisted. + +`run_code.presentResult` now forwards the final `result.content` into one generic result card. It deliberately omits the title so the pending card retains the program text. The existing logs metadata remains in `tool/result` for transcript compatibility, but the presenter no longer treats it as a second content source: `tool/result.content` is the durable, replayable, post-policy projection. + +Nested dispatch remains unchanged. Calls marked by `exec.parent` emit bounded `tool/code-dispatch` diagnostics but no `tool/call` or `tool/result` surface cards, so one outer `run_code` invocation still produces exactly one card. + +## Testing + +Presenter unit coverage pins logs-only, result-only, logs-plus-result, no-output, failure, and spilled-result content. Every case proves stale metadata cannot replace the final content. + +The keyless ACP and TUI Code Mode snapshots execute one outer program that performs two nested bash calls, logs `captured output`, and returns `CODE_ONE+CODE_TWO`. Both surfaces show one completed outer card containing both lines and no nested cards. + +## Alternatives considered + +**Append the return value to logs metadata.** Rejected because metadata would duplicate the renderer, need a second stable formatting contract for every JSON root, and still miss post-policy content replacement or spill previews. + +**Merge presenter metadata with `result.content`.** Rejected because the rendered content already contains the logs; merging would duplicate them and require brittle deduplication. + +**Create one card per nested dispatch.** Rejected because intermediate values are intentionally execution-local and never model-facing. Multiple cards would expose an implementation trace instead of the single Code Mode operation the model and user invoked. + +## Consequences + +ACP and TUI now display the same complete content the model receives and replay persists, including post-policy spill previews. The change adds or removes no event fields and requires no session-format bump. Existing and future replay records remain valid because the presenter ignores logs metadata when choosing card content and reads their durable rendered content. diff --git a/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.zh.md b/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.zh.md new file mode 100644 index 0000000000..082e209544 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.zh.md @@ -0,0 +1,37 @@ +# Agent Note: 保证 Code Mode 结果卡片内容完整 + +Status: implemented + +[English](2026-07-20-code-mode-result-card-completeness.md) | 中文 + +## 问题 + +外层 `run_code` 工具会持久化完整的渲染内容，但编辑器的卡片展示逻辑忽略了这些内容，转而根据仅含日志的 `presentationMeta` 投影重新构建卡片正文。仅有结果的运行看似正确，是因为展示逻辑未提供正文时，ACP 和 TUI 会回退到 `tool/result.content`。只要程序输出一条日志，展示逻辑就会提供非空内容，回退随即停止，返回值便会从完成态卡片中消失。失败文本以及输出落盘策略最终生成的头尾预览，也会受到同一职责拆分的影响。 + +嵌套 Code 调用从不生成自己的卡片。因此，仅仅为了重建这一张不完整卡片而给外层调用生成元数据，还掩盖了每次外层调用只生成一张卡片的预期边界。 + +## 决策 + +`run_code` 输出渲染器继续作为面向模型的外层内容的唯一所有者。它先渲染已捕获的日志，然后渲染返回值、显式的无输出标记，或规范工具流水线生成的失败内容。Post-execute 策略与输出落盘机制可以在内容持久化之前替换它。 + +`run_code.presentResult` 会把最终的 `result.content` 转交给一张通用结果卡片。它有意省略标题，使待完成卡片保留程序文本。现有日志元数据仍保留在 `tool/result` 中，以维持 transcript（文本记录）兼容性；但展示逻辑不再把它视为第二个内容来源：`tool/result.content` 才是持久、可回放且经过 post-policy 处理的投影。 + +嵌套分发保持不变。带有 `exec.parent` 标记的调用会发出有界的 `tool/code-dispatch` 诊断，但不会生成与 `tool/call` 或 `tool/result` 对应的界面卡片，因此一次外层 `run_code` 调用仍然只会生成一张卡片。 + +## 测试 + +展示逻辑的单元测试覆盖仅有日志、仅有结果、日志与结果并存、无输出、失败和结果落盘六种情况。每个用例都证明，陈旧元数据无法替换最终内容。 + +无密钥的 ACP 与 TUI Code Mode 快照会执行一个外层程序：程序进行两次嵌套 bash 调用，记录 `captured output`，并返回 `CODE_ONE+CODE_TWO`。两个界面都只显示一张完成态外层卡片，其中包含这两行内容，且没有嵌套卡片。 + +## 备选方案 + +**把返回值追加到日志元数据：**不予采纳。元数据会与渲染器重复，并且需要为每一种 JSON 根另行维护稳定的格式化契约；post-policy 内容替换或输出落盘预览仍然会被遗漏。 + +**把展示元数据与 `result.content` 合并：**不予采纳。渲染内容已经包含日志；合并会造成重复，还需要依赖脆弱的去重逻辑。 + +**为每次嵌套分发创建一张卡片：**不予采纳。中间值有意只存在于执行期间，永远不面向模型。多张卡片会暴露实现轨迹，而不是模型与用户调用的单次 Code Mode 操作。 + +## 影响 + +ACP 和 TUI 会显示模型接收、回放持久化的同一份完整内容，其中包括 post-policy 输出落盘预览。该变更不增加或删除任何事件字段，也不需要提升会话格式版本。现有及未来的回放记录都保持有效，因为展示逻辑在选择卡片内容时会忽略日志元数据，转而读取记录中的持久化渲染内容。 diff --git a/.agents/notes/implemented/feature/2026-06-15-code-mode.md b/.agents/notes/implemented/feature/2026-06-15-code-mode.md index e51f95d247..4983ddcfaf 100644 --- a/.agents/notes/implemented/feature/2026-06-15-code-mode.md +++ b/.agents/notes/implemented/feature/2026-06-15-code-mode.md @@ -48,7 +48,7 @@ Under `'code'` and `'both'` the registry owns `run_code` as a reserved presentat **Concurrency is serialized.** Each run owns a dispatch queue, so even `Promise.all` executes tool calls in submission order. Settlement abandons queued calls that have not started. Parallelism requires per-tool concurrency-safety metadata. -**Presentation.** `run_code`'s render intent is decided here per the [render-intent Agent Note](../architecture/2026-07-02-tool-render-intent-union.md): `presentCall` → a `generic` card, `kind: 'execute'`, title = the program text, `rawInput` = the same program text; `presentResult` → a `generic` card whose content is the captured output (from `meta`). The program is the title because ACP execute cards reliably render that field while some clients omit body and raw-input content. This is not a `terminal` card: that card's semantics are "a shell command in a working directory", which a program is not. +**Presentation.** `run_code`'s render intent is decided here per the [render-intent Agent Note](../architecture/2026-07-02-tool-render-intent-union.md): `presentCall` → a `generic` card, `kind: 'execute'`, title = the program text, `rawInput` = the same program text; `presentResult` → a `generic` card whose content is the final durable `tool/result.content`, including captured logs plus the returned value, failure, or post-policy spill preview. The existing logs metadata remains replayable but is not a second content source. The program is the title because ACP execute cards reliably render that field while some clients omit body and raw-input content. This is not a `terminal` card: that card's semantics are "a shell command in a working directory", which a program is not. See the [result-card completeness note](../bug-fix/2026-07-20-code-mode-result-card-completeness.md). ### Observability: `tool/code-dispatch` diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl index ec4e1a8d6a..84ebc9605a 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl @@ -89,7 +89,7 @@ {"type":"assistant/chunk","seq":87,"time":1783611772655,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" echo"}}} {"type":"assistant/chunk","seq":88,"time":1783611772655,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"\\\""}}} {"type":"assistant/chunk","seq":89,"time":1783611772684,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" });\\n"}}} -{"type":"assistant/chunk","seq":90,"time":1783611772685,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"return"}}} +{"type":"assistant/chunk","seq":90,"time":1783611772685,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"console.log(\\\"captured output\\\");\\nreturn"}}} {"type":"assistant/chunk","seq":91,"time":1783611772685,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" out"}}} {"type":"assistant/chunk","seq":92,"time":1783611772713,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"1"}}} {"type":"assistant/chunk","seq":93,"time":1783611772714,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":".stdout.text.trim"}}} @@ -105,14 +105,14 @@ {"type":"assistant/chunk","seq":103,"time":1783611772772,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"\""}}} {"type":"assistant/chunk","seq":104,"time":1783611772773,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"}"}}} {"type":"assistant/chunk","seq":105,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants a single run_code program that calls bash twice, then returns the two outputs joined with a plus sign. Let me write this."}}}} -{"type":"assistant/chunk","seq":106,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.stdout.text.trim() + \\\"+\\\" + out2.stdout.text.trim();\"}"}}}} +{"type":"assistant/chunk","seq":106,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nconsole.log(\\\"captured output\\\");\\nreturn out1.stdout.text.trim() + \\\"+\\\" + out2.stdout.text.trim();\"}"}}}} {"type":"assistant/chunk","seq":107,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}}}} {"type":"assistant/chunk","seq":108,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":109,"time":1783611772840,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants a single run_code program that calls bash twice, then returns the two outputs joined with a plus sign. Let me write this."},{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.stdout.text.trim() + \\\"+\\\" + out2.stdout.text.trim();\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} -{"type":"tool/call","seq":110,"time":1783611772840,"data":{"turn":1,"step":1,"callId":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.stdout.text.trim() + \\\"+\\\" + out2.stdout.text.trim();\"}"}} +{"type":"assistant/message","seq":109,"time":1783611772840,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants a single run_code program that calls bash twice, then returns the two outputs joined with a plus sign. Let me write this."},{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nconsole.log(\\\"captured output\\\");\\nreturn out1.stdout.text.trim() + \\\"+\\\" + out2.stdout.text.trim();\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} +{"type":"tool/call","seq":110,"time":1783611772840,"data":{"turn":1,"step":1,"callId":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nconsole.log(\\\"captured output\\\");\\nreturn out1.stdout.text.trim() + \\\"+\\\" + out2.stdout.text.trim();\"}"}} {"type":"tool/code-dispatch","seq":111,"time":1783611772933,"data":{"parentCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","subCallId":"call_00_DRxnM6R1TThfDwcudW0f2050:code:1","name":"bash","arguments":{"command":"echo CODE_ONE","description":"First echo"},"isError":false,"resultSummary":"CODE_ONE\n"}} {"type":"tool/code-dispatch","seq":112,"time":1783611772936,"data":{"parentCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","subCallId":"call_00_DRxnM6R1TThfDwcudW0f2050:code:2","name":"bash","arguments":{"command":"echo CODE_TWO","description":"Second echo"},"isError":false,"resultSummary":"CODE_TWO\n"}} -{"type":"tool/result","seq":113,"time":1783611772937,"data":{"turn":1,"step":1,"callId":"call_00_DRxnM6R1TThfDwcudW0f2050","content":[{"type":"text","text":"CODE_ONE+CODE_TWO"}],"isError":false,"meta":{"logs":[]}},"sourceEventSeqs":[110],"surfaceOp":"append"} +{"type":"tool/result","seq":113,"time":1783611772937,"data":{"turn":1,"step":1,"callId":"call_00_DRxnM6R1TThfDwcudW0f2050","content":[{"type":"text","text":"captured output\nCODE_ONE+CODE_TWO"}],"isError":false,"meta":{"logs":["captured output"]}},"sourceEventSeqs":[110],"surfaceOp":"append"} {"type":"step/end","seq":114,"time":1783611772938,"data":{"turn":1,"step":1}} {"type":"step/start","seq":115,"time":1783611772938,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":116,"time":1783611773376,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl index 855e1b3ca1..ce9167133f 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl @@ -30,8 +30,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" write"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" this"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","title":"const out1 = await tools.bash({ command: \"echo CODE_ONE\", description: \"First echo\" });\nconst out2 = await tools.bash({ command: \"echo CODE_TWO\", description: \"Second echo\" });\nreturn out1.stdout.text.trim() + \"+\" + out2.stdout.text.trim();","kind":"execute","status":"in_progress","rawInput":"const out1 = await tools.bash({ command: \"echo CODE_ONE\", description: \"First echo\" });\nconst out2 = await tools.bash({ command: \"echo CODE_TWO\", description: \"Second echo\" });\nreturn out1.stdout.text.trim() + \"+\" + out2.stdout.text.trim();"}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","status":"completed","content":[{"type":"content","content":{"type":"text","text":"CODE_ONE+CODE_TWO"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","title":"const out1 = await tools.bash({ command: \"echo CODE_ONE\", description: \"First echo\" });\nconst out2 = await tools.bash({ command: \"echo CODE_TWO\", description: \"Second echo\" });\nconsole.log(\"captured output\");\nreturn out1.stdout.text.trim() + \"+\" + out2.stdout.text.trim();","kind":"execute","status":"in_progress","rawInput":"const out1 = await tools.bash({ command: \"echo CODE_ONE\", description: \"First echo\" });\nconst out2 = await tools.bash({ command: \"echo CODE_TWO\", description: \"Second echo\" });\nconsole.log(\"captured output\");\nreturn out1.stdout.text.trim() + \"+\" + out2.stdout.text.trim();"}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","status":"completed","content":[{"type":"content","content":{"type":"text","text":"captured output\nCODE_ONE+CODE_TWO"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" output"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" is"}}}} diff --git a/examples/tui-agent/tests/snapshots/code-mode/session.jsonl b/examples/tui-agent/tests/snapshots/code-mode/session.jsonl index ec4e1a8d6a..84ebc9605a 100644 --- a/examples/tui-agent/tests/snapshots/code-mode/session.jsonl +++ b/examples/tui-agent/tests/snapshots/code-mode/session.jsonl @@ -89,7 +89,7 @@ {"type":"assistant/chunk","seq":87,"time":1783611772655,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" echo"}}} {"type":"assistant/chunk","seq":88,"time":1783611772655,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"\\\""}}} {"type":"assistant/chunk","seq":89,"time":1783611772684,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" });\\n"}}} -{"type":"assistant/chunk","seq":90,"time":1783611772685,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"return"}}} +{"type":"assistant/chunk","seq":90,"time":1783611772685,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"console.log(\\\"captured output\\\");\\nreturn"}}} {"type":"assistant/chunk","seq":91,"time":1783611772685,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" out"}}} {"type":"assistant/chunk","seq":92,"time":1783611772713,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"1"}}} {"type":"assistant/chunk","seq":93,"time":1783611772714,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":".stdout.text.trim"}}} @@ -105,14 +105,14 @@ {"type":"assistant/chunk","seq":103,"time":1783611772772,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"\""}}} {"type":"assistant/chunk","seq":104,"time":1783611772773,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"}"}}} {"type":"assistant/chunk","seq":105,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants a single run_code program that calls bash twice, then returns the two outputs joined with a plus sign. Let me write this."}}}} -{"type":"assistant/chunk","seq":106,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.stdout.text.trim() + \\\"+\\\" + out2.stdout.text.trim();\"}"}}}} +{"type":"assistant/chunk","seq":106,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nconsole.log(\\\"captured output\\\");\\nreturn out1.stdout.text.trim() + \\\"+\\\" + out2.stdout.text.trim();\"}"}}}} {"type":"assistant/chunk","seq":107,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}}}} {"type":"assistant/chunk","seq":108,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":109,"time":1783611772840,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants a single run_code program that calls bash twice, then returns the two outputs joined with a plus sign. Let me write this."},{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.stdout.text.trim() + \\\"+\\\" + out2.stdout.text.trim();\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} -{"type":"tool/call","seq":110,"time":1783611772840,"data":{"turn":1,"step":1,"callId":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.stdout.text.trim() + \\\"+\\\" + out2.stdout.text.trim();\"}"}} +{"type":"assistant/message","seq":109,"time":1783611772840,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants a single run_code program that calls bash twice, then returns the two outputs joined with a plus sign. Let me write this."},{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nconsole.log(\\\"captured output\\\");\\nreturn out1.stdout.text.trim() + \\\"+\\\" + out2.stdout.text.trim();\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} +{"type":"tool/call","seq":110,"time":1783611772840,"data":{"turn":1,"step":1,"callId":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nconsole.log(\\\"captured output\\\");\\nreturn out1.stdout.text.trim() + \\\"+\\\" + out2.stdout.text.trim();\"}"}} {"type":"tool/code-dispatch","seq":111,"time":1783611772933,"data":{"parentCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","subCallId":"call_00_DRxnM6R1TThfDwcudW0f2050:code:1","name":"bash","arguments":{"command":"echo CODE_ONE","description":"First echo"},"isError":false,"resultSummary":"CODE_ONE\n"}} {"type":"tool/code-dispatch","seq":112,"time":1783611772936,"data":{"parentCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","subCallId":"call_00_DRxnM6R1TThfDwcudW0f2050:code:2","name":"bash","arguments":{"command":"echo CODE_TWO","description":"Second echo"},"isError":false,"resultSummary":"CODE_TWO\n"}} -{"type":"tool/result","seq":113,"time":1783611772937,"data":{"turn":1,"step":1,"callId":"call_00_DRxnM6R1TThfDwcudW0f2050","content":[{"type":"text","text":"CODE_ONE+CODE_TWO"}],"isError":false,"meta":{"logs":[]}},"sourceEventSeqs":[110],"surfaceOp":"append"} +{"type":"tool/result","seq":113,"time":1783611772937,"data":{"turn":1,"step":1,"callId":"call_00_DRxnM6R1TThfDwcudW0f2050","content":[{"type":"text","text":"captured output\nCODE_ONE+CODE_TWO"}],"isError":false,"meta":{"logs":["captured output"]}},"sourceEventSeqs":[110],"surfaceOp":"append"} {"type":"step/end","seq":114,"time":1783611772938,"data":{"turn":1,"step":1}} {"type":"step/start","seq":115,"time":1783611772938,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":116,"time":1783611773376,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/tui-agent/tests/snapshots/code-mode/terminal.expected.txt b/examples/tui-agent/tests/snapshots/code-mode/terminal.expected.txt index 2850e0c7d0..7f8998bd43 100644 --- a/examples/tui-agent/tests/snapshots/code-mode/terminal.expected.txt +++ b/examples/tui-agent/tests/snapshots/code-mode/terminal.expected.txt @@ -1,7 +1,7 @@ terminal 100x36 buffer=normal length=36 base=0 viewport=0 lifecycle started=1 stopped=0 progress=inactive title "DSH TUI snapshot" -cursor hidden column=1 viewportRow=29 bufferRow=29 +cursor hidden column=1 viewportRow=30 bufferRow=30 buffer 0| "╭──────────────────────────────────────────────────────────────────────────────────────────────────╮" style 0-99 fg=bright-blue @@ -54,26 +54,28 @@ buffer 19| "▌ const o " style 0-0 fg=green style 2-8 bold -20| "▌ CODE_ONE+CODE_TWO " +20| "▌ captured output " style 0-0 fg=green -21| "▌ " +21| "▌ CODE_ONE+CODE_TWO " style 0-0 fg=green -22| -23| " Reasoning " +22| "▌ " + style 0-0 fg=green +23| +24| " Reasoning " style 1-9 fg=bright-black italic -24| " The output is exactly what the user asked for: CODE_ONE+CODE_TWO " +25| " The output is exactly what the user asked for: CODE_ONE+CODE_TWO " style 1-64 fg=bright-black italic -25| -26| " Assistant " +26| +27| " Assistant " style 1-9 fg=bright-magenta bold -27| " CODE_ONE+CODE_TWO " -28| "────────────────────────────────────────────────────────────────────────────────────────────────────" +28| " CODE_ONE+CODE_TWO " +29| "────────────────────────────────────────────────────────────────────────────────────────────────────" style 0-99 dim -29| " " +30| " " style 1-1 inverse -30| "────────────────────────────────────────────────────────────────────────────────────────────────────" +31| "────────────────────────────────────────────────────────────────────────────────────────────────────" style 0-99 dim -31| "/workspace/project ↑3.1k ↓158 idle reasoning:on tools:compact" +32| "/workspace/project ↑3.1k ↓158 idle reasoning:on tools:compact" style 0-49 dim style 67-99 dim -32-35| +33-35| diff --git a/packages/core/tools/src/code-mode.ts b/packages/core/tools/src/code-mode.ts index c9bda10358..713978b87e 100644 --- a/packages/core/tools/src/code-mode.ts +++ b/packages/core/tools/src/code-mode.ts @@ -107,22 +107,9 @@ function renderValue(value: JsonValue): string { return typeof value === 'string' ? value : JSON.stringify(value, null, 2) } -/** The run_code result's `meta` payload (JSON-serializable; `presentResult` narrows it back). */ -interface RunCodeMeta { - logs: CodeRunResult['logs'] -} - /** Canonical value returned by the outer Code Mode transport. */ type RunCodeOutput = { logs: string[]; result?: JsonValue } -/** Soft-narrow a result `meta` back to {@link RunCodeMeta} (replay may carry older shapes; presentation must not throw). */ -function asRunCodeMeta(meta: unknown): RunCodeMeta | undefined { - if (typeof meta !== 'object' || meta === null) return undefined - const m = meta as Record - if (!Array.isArray(m.logs) || !m.logs.every(log => typeof log === 'string')) return undefined - return m as unknown as RunCodeMeta -} - /** * Build the `run_code` {@link ToolDefinition}: one required `code` parameter, * executed through the dispatch bridge described above. The @@ -293,15 +280,8 @@ export function createRunCodeTool(registry: ToolRegistry, requireRuntime: () => }), // Title omitted on the result: an update replaces only the fields it // carries, so the pending card's program title persists through - // completion; the captured output rides as body content. - presentResult: (_args, result) => { - const meta = asRunCodeMeta(result.meta) - if (!meta) return undefined - const output = meta.logs.join('\n') - return { - card: 'generic', - ...output.length > 0 ? { content: [{ type: 'text' as const, text: output }] } : {}, - } - }, + // completion. The durable final content already includes logs plus the + // return value, failure, or post-policy spill preview. + presentResult: (_args, result) => ({ card: 'generic', content: result.content }), }) } diff --git a/packages/core/tools/tests/code-mode.spec.ts b/packages/core/tools/tests/code-mode.spec.ts index cfff494a62..7f76a0b539 100644 --- a/packages/core/tools/tests/code-mode.spec.ts +++ b/packages/core/tools/tests/code-mode.spec.ts @@ -663,7 +663,7 @@ describe('the run_code dispatch bridge', () => { expect((result.content[0] as { text: string }).text).toContain('requires a code runtime') }) - it('presents the PROGRAM as the execute-card title on both call and result (the one slot execute cards always show)', async () => { + it('presents the program as the execute-card title', async () => { const { ctx } = await setup({ mode: 'code' }) const tool = ctx.tools.get(RUN_CODE_NAME)! // The program IS the title, mirroring how command tools title their cards @@ -676,24 +676,28 @@ describe('the run_code dispatch bridge', () => { kind: 'execute', rawInput: 'return 1', }) - const view = tool.presentResult?.({ code: 'return 1' }, { - content: [{ type: 'text', text: 'model-facing' }], - isError: false, - meta: { logs: ['printed'] }, - }) + }) + + it.each([ + ['logs only', 'printed', false], + ['result only', 'returned', false], + ['logs plus result', 'printed\nreturned', false], + ['no output', '(run_code completed with no output)', false], + ['failure', 'Error: code run failed (output-limit): outer output exceeded 8 bytes', true], + ['spilled result', 'HEAD\n\n(Omitted 100 bytes. Full formatted result stored at: /tmp/run-code.txt.)\n\nTAIL', false], + ] as const)('presents %s from the final post-policy content', async (_name, text, isError) => { + const { ctx } = await setup({ mode: 'code' }) + const tool = ctx.tools.get(RUN_CODE_NAME)! // The result omits the title — an update replaces only provided fields, // so the pending card's program title persists through completion. - expect(view).toEqual({ - card: 'generic', - content: [{ type: 'text', text: 'printed' }], - }) - // No captured output → no content either; everything pending persists. - expect(tool.presentResult?.({ code: 'x' }, { content: [], isError: false, meta: { logs: [] } })) - .toEqual({ card: 'generic' }) - // Replay with an unrecognizable meta falls back to the generic rendering. - expect(tool.presentResult?.({ code: 'x' }, { content: [], isError: false, meta: { logs: [{ text: 'legacy' }], dispatches: 1 } })).toBeUndefined() - expect(tool.presentResult?.({ code: 'x' }, { content: [], isError: false, meta: { other: true } })).toBeUndefined() - expect(tool.presentResult?.({ code: 'x' }, { content: [], isError: false })).toBeUndefined() + const content = [{ type: 'text' as const, text }] + expect(tool.presentResult?.({ code: 'return 1' }, { + content, + isError, + // Stale or unrelated metadata must not replace the authoritative + // post-policy content used by the card. + meta: { logs: ['stale logs-only projection'] }, + })).toEqual({ card: 'generic', content }) }) it('renders non-text sub-result blocks as placeholders and truncates long event summaries', async () => {