diff --git a/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.i18n.yaml b/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.i18n.yaml index b8a21b4fcb..65d14e9aa4 100644 --- a/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.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/2026-08-05-context-form-vocabulary.md -2026-08-05-context-form-vocabulary.md: c111acfec4fa85fe9e25adeb615371d65098f20f -2026-08-05-context-form-vocabulary.zh.md: d4da218c4c6026eb875513c2acbfcd18ced8faa1 +2026-08-05-context-form-vocabulary.md: 618c11b925208d09a62d10101656e3358e327ddb +2026-08-05-context-form-vocabulary.zh.md: 66278b261f23601461c96f08e87ea58766b2bfc2 diff --git a/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.md b/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.md index c111acfec4..618c11b925 100644 --- a/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.md +++ b/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.md @@ -29,6 +29,14 @@ Entries record the published fact **unescaped**. The pseudo-XML escaping belongs That move also relocates catalog **identity**: the republish digest now covers the durable entries rather than the rendered text, so the model-facing framing can no longer decide whether a republish is needed, and the text-slicing that recovered entries from a logged message is gone. A resumed session whose newest catalog predates this change republishes once, which the pre-release stance permits. One case does not self-heal: if that old-format catalog is the only one and the current view has no skills, the plugin sees no published catalog and emits no tombstone, so the model keeps a stale catalog nothing replaces. The pre-release stance ("backends reject old on-disk formats") permits it; it is recorded here rather than left to the optimistic path. +**`snapshot`** — current state that a later snapshot from the same producer supersedes. The runtime-context snapshot, `time-context`, and `tmux-context` declare it. `renderContextSections()` exposes the assembly's named contributions, which `renderContextSnapshot()` already joined for the model, so the body attributes each part to the subsystem that produced it without re-splitting joined prose. The two single-contribution producers record one section each. The cleared runtime-context marker has no contributions left and declares no form. + +**`notice`** — a one-off account of something that just happened. `tool-tasks`, `tool-goal` wrap-up, `plan-mode` switches, and `repeat-tool-guard` reminders declare it with a `summary`, which rides the **collapsed** row: a notice is meant to be read without expanding at all. The summary is bounded where its inputs are caller text (a task's label and status detail have no length of their own). Goal state changes remain domain-owned `goal/change` events rather than model context, so they declare no form. + +**`relay`** — a message another agent addressed to this one. Both subagent-addressed sources declare it; the sender is shown as the opaque session id the source already records, because this client cannot resolve it to a title. + +**`recall`** — material lifted out of another session's log. `session-reference` declares it and needed no new field: its references already record the label, retained and omitted counts, and truncation flag, which the body shows first, because recalled context is bounded on the way in and a card that hid the omitted count would overstate what the model received. + Both readers are **all-or-nothing**: one unreadable entry disqualifies the record rather than being dropped, because a body that replaces the model-facing text must not present a confident but incomplete account of what the model read. The row's form marker reports what actually rendered, not what was declared. The producer side validates the same durable data with the same posture. `catalogHistory` reads `source.entries` out of `agent.session.events`, which on resume or fork is a JSONL/SQLite seed whose validation only guarantees a source object with a non-empty `kind` — no per-kind field is checked. An unreadable catalog is therefore skipped as "not this plugin's record", the posture the replaced content digest had; throwing there would fail every later step of that session at the latest, least diagnosable point. @@ -61,4 +69,5 @@ The tool seam pairs its vocabulary with `presentCall(args)`, a host-side pure fu - A reader can tell what was added without expanding, and reading it no longer means reading escaped JSON. - The durable `MessageSource` now carries a semantic classification beside provenance. The boundary is load-bearing: facts and shape only, never presentation. A producer that wants a better card records better facts. - Catalog identity no longer depends on the model-facing prose, deleting the text-slicing path that could mistake a reworded catalog for a changed one. -- Five forms from the surveyed taxonomy (`snapshot`, `relay`, `recall`, `notice`, and the unclassified remainder) are not declared yet; their producers render opaque until they record the fields their form needs. +- Every shipped producer except the two hook bridges now declares a form. The bridges stay opaque by design: their content is whatever an external program printed, so no shape can be promised for it. Unknown kinds and unreadable records land there too. +- `ContextFormed` is discriminated by `form`, so a producer cannot declare a shape without the facts that shape is presented from — a `notice` without its summary, or a `snapshot` without its sections, fails to compile. diff --git a/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.zh.md b/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.zh.md index d4da218c4c..66278b261f 100644 --- a/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.zh.md +++ b/.agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.zh.md @@ -29,6 +29,14 @@ Status: implemented 这次迁移同时挪动了目录的**身份**：重新发布用的 digest 现在覆盖持久条目而非渲染文本，于是面向模型的包装再也无法左右是否需要重新发布，那段从已记录消息里切出条目的文本切分逻辑也随之删除。若恢复的会话中最新目录早于本次改动，会重新发布一次——发布前阶段的姿态允许这样做。有一种情形不会自愈：当那份旧格式目录是唯一的一份、且当前视图没有任何 skill 时，插件看不到已发布目录，也就不会发出 tombstone，模型手里会留着一份无人替换的过期目录。发布前阶段的姿态（「后端拒绝旧的磁盘格式」）允许这一点；此处如实记录，而不是只写乐观路径。 +**`snapshot`**——会被同一生产方后续快照取代的当前状态。运行时快照、`time-context`、`tmux-context` 声明它。`renderContextSections()` 暴露出装配时的具名贡献——`renderContextSnapshot()` 本来就是把它们拼给模型的——因此内容区能把每一段归属到产生它的子系统，而不必去切分已经拼好的散文。两个单贡献生产方各记录一段。运行时快照的「已清空」标记没有任何贡献可归属，因此不声明形态。 + +**`notice`**——刚刚发生了什么的一次性说明。`tool-tasks`、`tool-goal` 收尾、`plan-mode` 切换与 `repeat-tool-guard` 提醒都带 `summary` 声明它，而该摘要出现在**折叠态**行上：notice 的全部意义就是不展开也能读完。摘要在其输入是调用方文本时自行封顶（任务的 label 与状态 detail 本身没有长度约束）。Goal 状态变更仍是由领域层持有的 `goal/change` 事件，而非模型上下文，因此不声明 form。 + +**`relay`**——另一个 agent 发给本 agent 的消息。两个子 agent 定向来源都声明它；发送方以来源已记录的不透明会话 id 呈现，因为本客户端无法把它解析成标题。 + +**`recall`**——从另一个会话日志搬来的材料。`session-reference` 声明它，且不需要新增字段：其 references 已经记录了标题、保留与省略条数、截断标记，内容区把这些放在最前面——召回上下文在进入时是有界的，隐藏省略条数的卡片会夸大模型实际收到的内容。 + 两个读取器都是**全有或全无**：一条不可读的条目即判定整条记录不可用，而不是把它丢掉——会替换掉面向模型文本的内容区，不得给出自信但残缺的「模型读到了什么」。行上的形态标记报告的是实际渲染出的形态，而非声明的形态。 生产方一侧对同一份持久数据采取同样的姿态。`catalogHistory` 从 `agent.session.events` 读 `source.entries`，而恢复或 fork 时它来自 JSONL／SQLite 种子，种子验证只保证来源是带非空 `kind` 的对象，不校验任何 kind 特有字段。因此不可读的目录被当作「不是本插件的记录」跳过——正是被替换掉的内容 digest 原有的姿态；在那里抛错会让该会话此后每一步都在最晚、最难定位的点失败。 @@ -61,4 +69,5 @@ Status: implemented - 读者不展开就能知道加进来的是什么，展开之后读到的也不再是转义 JSON。 - 持久 `MessageSource` 现在在溯源之外还承载一个语义分类。这条边界是承重的：只放事实与形状，绝不放呈现。想要更好卡片的生产方应当记录更好的事实。 - 目录身份不再依赖面向模型的散文，删掉了那条可能把「改了措辞」误判为「改了内容」的文本切分路径。 -- 已勘定的分类里还有五种形态（`snapshot`、`relay`、`recall`、`notice`，以及未归类的其余部分）尚未声明；在它们的生产方补齐各自形态所需字段之前，一律渲染 opaque。 +- 除两个 hook 桥接外，每个已发布的生产方现在都声明了形态。桥接按设计保持 opaque：其内容是外部程序打印出来的任意文本，无法承诺任何形状。未知 kind 与不可读记录同样落在这里。 +- `ContextFormed` 按 `form` 判别，因此生产方无法在缺少该形态所需事实的情况下声明它——没有 summary 的 `notice`、没有 sections 的 `snapshot`，都会编译失败。 diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index ed615ed377..b3d81d61b9 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -2195,7 +2195,7 @@ async assemble(context: AssembleContext = {}): Promise Types: [AssembleContext](../core-data-structures/system-prompt.md) · [PromptContext](../core-data-structures/system-prompt.md) · [PromptSection](../core-data-structures/system-prompt.md) · [ToolProviderResult](../core-data-structures/system-prompt.md) -Source: [`packages/core/system-prompt/src/index.ts:290`](../../packages/core/system-prompt/src/index.ts) +Source: [`packages/core/system-prompt/src/index.ts:314`](../../packages/core/system-prompt/src/index.ts) ## `ctx.tasks` — `TaskService` (abstract seam) diff --git a/docs/core-data-structures/core.i18n.yaml b/docs/core-data-structures/core.i18n.yaml index dd21127251..6f16b8c573 100644 --- a/docs/core-data-structures/core.i18n.yaml +++ b/docs/core-data-structures/core.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 docs/core-data-structures/core.md -core.md: c908b71a0e1ea0401a9e7ac46ea9f014ece71796 -core.zh.md: 230000a166d73346cdb0dec114503b5904493c1a +core.md: 495651e1f3105afff15f68822568ff71c531da4f +core.zh.md: c895601f39d350811ab1169533287d8f59dba703 diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index c908b71a0e..495651e1f3 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -190,15 +190,54 @@ type ContextForm = | 'instructions' /** A catalog of items available in this session, republished as it changes. */ | 'catalog' + /** Current state, where a later snapshot from the same producer supersedes an earlier one. */ + | 'snapshot' + /** A one-off account of something that just happened; it supersedes nothing. */ + | 'notice' + /** A message another agent addressed to this one. */ + | 'relay' + /** Material lifted out of another session's log, possibly reduced on the way in. */ + | 'recall' ``` ```ts type-equiv -/** Optional producer-declared {@link ContextForm}, mixed into the source shapes that carry one. */ -interface ContextFormed { - readonly form?: ContextForm +/** One named contribution to a `snapshot`-form context, in assembly order. */ +interface ContextSnapshotSection { + /** The contributing subsystem's name. */ + readonly name: string + /** That contribution's model-facing text, exactly as assembled. */ + readonly text: string } ``` +```ts type-equiv +/** + * Producer-declared {@link ContextForm} and the fields that form requires, + * mixed into the source shapes that carry one. + * + * Discriminated by `form` so a producer cannot declare a shape without the + * facts that shape is presented from: a `notice` must record its one-line + * account, a `snapshot` its sections. Omitting `form` stays valid — an + * undeclared context is the documented default. + */ +type ContextFormed = + | { readonly form?: never } + | { readonly form: 'instructions' } + | { readonly form: 'catalog' } + | { + readonly form: 'snapshot' + /** The named contributions this snapshot assembled, in order. */ + readonly sections: readonly ContextSnapshotSection[] + } + | { + readonly form: 'notice' + /** One-line account of what happened, shown without expanding the row. */ + readonly summary: string + } + | { readonly form: 'relay' } + | { readonly form: 'recall' } +``` + ## Streaming Adapters emit a raw **chunk** protocol; the loop logs the chunks (replay fidelity) while feeding the same chunks through a `BlockAssembler` to rebuild blocks and messages. `StreamChunk` is a closed discriminated union over `type` — `block-start`, `text-delta`, `reasoning-delta`, `tool-call-delta`, `block-end`, `usage`, `finish`. diff --git a/docs/core-data-structures/core.zh.md b/docs/core-data-structures/core.zh.md index 230000a166..c895601f39 100644 --- a/docs/core-data-structures/core.zh.md +++ b/docs/core-data-structures/core.zh.md @@ -196,15 +196,54 @@ type ContextForm = | 'instructions' /** A catalog of items available in this session, republished as it changes. */ | 'catalog' + /** Current state, where a later snapshot from the same producer supersedes an earlier one. */ + | 'snapshot' + /** A one-off account of something that just happened; it supersedes nothing. */ + | 'notice' + /** A message another agent addressed to this one. */ + | 'relay' + /** Material lifted out of another session's log, possibly reduced on the way in. */ + | 'recall' ``` ```ts type-equiv -/** Optional producer-declared {@link ContextForm}, mixed into the source shapes that carry one. */ -interface ContextFormed { - readonly form?: ContextForm +/** One named contribution to a `snapshot`-form context, in assembly order. */ +interface ContextSnapshotSection { + /** The contributing subsystem's name. */ + readonly name: string + /** That contribution's model-facing text, exactly as assembled. */ + readonly text: string } ``` +```ts type-equiv +/** + * Producer-declared {@link ContextForm} and the fields that form requires, + * mixed into the source shapes that carry one. + * + * Discriminated by `form` so a producer cannot declare a shape without the + * facts that shape is presented from: a `notice` must record its one-line + * account, a `snapshot` its sections. Omitting `form` stays valid — an + * undeclared context is the documented default. + */ +type ContextFormed = + | { readonly form?: never } + | { readonly form: 'instructions' } + | { readonly form: 'catalog' } + | { + readonly form: 'snapshot' + /** The named contributions this snapshot assembled, in order. */ + readonly sections: readonly ContextSnapshotSection[] + } + | { + readonly form: 'notice' + /** One-line account of what happened, shown without expanding the row. */ + readonly summary: string + } + | { readonly form: 'relay' } + | { readonly form: 'recall' } +``` + ## 流式输出 适配器发出原始**分片**协议；循环记录分片（回放保真度），同时将同一批分片送入 `BlockAssembler` 以重建块和消息。`StreamChunk` 是基于 `type` 的封闭判别联合——`block-start`、`text-delta`、`reasoning-delta`、`tool-call-delta`、`block-end`、`usage`、`finish`。 diff --git a/docs/core-data-structures/subagent.i18n.yaml b/docs/core-data-structures/subagent.i18n.yaml index d5de81fa45..a449388c60 100644 --- a/docs/core-data-structures/subagent.i18n.yaml +++ b/docs/core-data-structures/subagent.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 docs/core-data-structures/subagent.md -subagent.md: c5fbf80ae71f99606dd86e38f06a4511b4ae4c73 -subagent.zh.md: 42c1fa7cb10863c1aa4ae975171b901207c08b85 +subagent.md: 956b47cfa85efe7826fbde47d4405d20a6abed6c +subagent.zh.md: 467fcd35bcde5fd01a2e18efbad862c72d7a4253 diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index c5fbf80ae7..956b47cfa8 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -149,6 +149,8 @@ Final settlement awaits `ctx.sessions.flush(session)` but ignores its participat /** Attribution for a model coordinator's follow-up to one of its children. */ interface CoordinatorMessageSource { readonly kind: 'coordinator' + /** A message another agent addressed to this one (`relay` context form). */ + readonly form: 'relay' /** Session id of the agent whose tool call produced the follow-up. */ readonly senderSessionId: SessionId } @@ -182,6 +184,8 @@ An optional continuable-child setup contribution can install scope-local capabil /** Durable attribution for a continuable child's explicit parent report. */ interface SubagentReportMessageSource { readonly kind: 'subagent-report' + /** A message another agent addressed to this one (`relay` context form). */ + readonly form: 'relay' /** Session id of the reporting child. */ readonly senderSessionId: SessionId } diff --git a/docs/core-data-structures/subagent.zh.md b/docs/core-data-structures/subagent.zh.md index 42c1fa7cb1..467fcd35bc 100644 --- a/docs/core-data-structures/subagent.zh.md +++ b/docs/core-data-structures/subagent.zh.md @@ -149,6 +149,8 @@ Agent 收件箱是唯一的队列。每条继续执行消息都会成为一个 ` /** Attribution for a model coordinator's follow-up to one of its children. */ interface CoordinatorMessageSource { readonly kind: 'coordinator' + /** A message another agent addressed to this one (`relay` context form). */ + readonly form: 'relay' /** Session id of the agent whose tool call produced the follow-up. */ readonly senderSessionId: SessionId } @@ -182,6 +184,8 @@ interface ContinuableStart { /** Durable attribution for a continuable child's explicit parent report. */ interface SubagentReportMessageSource { readonly kind: 'subagent-report' + /** A message another agent addressed to this one (`relay` context form). */ + readonly form: 'relay' /** Session id of the reporting child. */ readonly senderSessionId: SessionId } diff --git a/examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl b/examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl index 5f5b8971ce..f7b0cc84b2 100644 --- a/examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl +++ b/examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":0,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":0,"data":{"content":[{"type":"text","text":"Create a durable two-round goal for the ACP snapshot, inspect it, then report readiness."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":0,"data":{"title":"Create a durable two-round goal","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/goal-snapshots/goal-wrapup/session.expected.jsonl b/examples/acp-agent/tests/goal-snapshots/goal-wrapup/session.expected.jsonl index 60335e83b4..46ca2fe819 100644 --- a/examples/acp-agent/tests/goal-snapshots/goal-wrapup/session.expected.jsonl +++ b/examples/acp-agent/tests/goal-snapshots/goal-wrapup/session.expected.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":0,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":0,"data":{"content":[{"type":"text","text":"Create a durable goal for the wrap-up snapshot, then report readiness."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":0,"data":{"title":"Create a durable goal for","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} @@ -41,11 +41,11 @@ {"type":"tool/call","seq":39,"time":0,"data":{"turn":2,"step":1,"callId":"call_goal_complete","name":"update_goal","arguments":"{\"goal_id\":\"goal-{{sessionId}}\",\"revision\":1,\"action\":\"complete\"}"}} {"type":"goal/change","seq":40,"time":0,"data":{"kind":"goal/change","version":1,"operation":"complete","goal":{"id":"goal-{{sessionId}}","revision":2,"objective":"Finish the ACP goal wrap-up snapshot proof","phase":"complete","maxGoalRounds":2},"roundsStarted":1,"createdAt":0,"updatedAt":0}} {"type":"tool/result","seq":41,"time":0,"data":{"turn":2,"step":1,"message":{"source":{"kind":"tool","callId":"call_goal_complete"},"content":[{"type":"tool-result","toolCallId":"call_goal_complete","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":2,\"objective\":\"Finish the ACP goal wrap-up snapshot proof\",\"phase\":\"complete\",\"roundsStarted\":1,\"maxGoalRounds\":2},\"activation\":\"disarmed\"}"}],"isError":false}],"role":"user","id":"{{sessionId}}"}},"sourceEventSeqs":[39],"surfaceOp":"append"} -{"type":"agent/inbox/spliced","seq":42,"time":0,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"\nObjective: \"Finish the ACP goal wrap-up snapshot proof\"\nThe goal is marked complete and this autonomous run is ending. Write the closing message to the user now: state the outcome, summarize what was done and how it was verified, and point to the concrete results (files, commits, or other artifacts). Report only what earlier rounds and tool results in this session actually establish; when a detail is not in the session, say so instead of inventing it. Note anything the user should review or do next. Address the user directly. Do not call any more tools in this run; further work waits for the user's next instruction.\n"}],"source":{"kind":"plugin","plugin":"tool-goal"},"role":"user","id":"{{sessionId}}"}]}} +{"type":"agent/inbox/spliced","seq":42,"time":0,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"\nObjective: \"Finish the ACP goal wrap-up snapshot proof\"\nThe goal is marked complete and this autonomous run is ending. Write the closing message to the user now: state the outcome, summarize what was done and how it was verified, and point to the concrete results (files, commits, or other artifacts). Report only what earlier rounds and tool results in this session actually establish; when a detail is not in the session, say so instead of inventing it. Note anything the user should review or do next. Address the user directly. Do not call any more tools in this run; further work waits for the user's next instruction.\n"}],"source":{"kind":"plugin","plugin":"tool-goal","form":"notice","summary":"complete: Finish the ACP goal wrap-up snapshot proof"},"role":"user","id":"{{sessionId}}"}]}} {"type":"step/end","seq":43,"time":0,"data":{"turn":2,"step":1}} {"type":"agent/inbox/spliced","seq":44,"time":0,"data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":45,"time":0,"data":{"turn":2,"step":2}} -{"type":"user/message","seq":46,"time":0,"data":{"content":[{"type":"text","text":"\nObjective: \"Finish the ACP goal wrap-up snapshot proof\"\nThe goal is marked complete and this autonomous run is ending. Write the closing message to the user now: state the outcome, summarize what was done and how it was verified, and point to the concrete results (files, commits, or other artifacts). Report only what earlier rounds and tool results in this session actually establish; when a detail is not in the session, say so instead of inventing it. Note anything the user should review or do next. Address the user directly. Do not call any more tools in this run; further work waits for the user's next instruction.\n"}],"source":{"kind":"plugin","plugin":"tool-goal"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} +{"type":"user/message","seq":46,"time":0,"data":{"content":[{"type":"text","text":"\nObjective: \"Finish the ACP goal wrap-up snapshot proof\"\nThe goal is marked complete and this autonomous run is ending. Write the closing message to the user now: state the outcome, summarize what was done and how it was verified, and point to the concrete results (files, commits, or other artifacts). Report only what earlier rounds and tool results in this session actually establish; when a detail is not in the session, say so instead of inventing it. Note anything the user should review or do next. Address the user directly. Do not call any more tools in this run; further work waits for the user's next instruction.\n"}],"source":{"kind":"plugin","plugin":"tool-goal","form":"notice","summary":"complete: Finish the ACP goal wrap-up snapshot proof"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} {"type":"assistant/chunk","seq":47,"time":0,"data":{"turn":2,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":48,"time":0,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":0,"text":"GOAL WRAP-UP: the snapshot objective is achieved and this closing message reaches the user."}}} {"type":"assistant/chunk","seq":49,"time":0,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL WRAP-UP: the snapshot objective is achieved and this closing message reaches the user."}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 7e9f42d6fb..7908f0e71b 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -5,7 +5,7 @@ {"type":"subagent/descriptor","seq":3,"time":1785821418091,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Check direct child"}} {"type":"step/start","seq":4,"time":1785730458555,"data":{"turn":1,"step":1}} {"type":"user/message","seq":5,"time":1785730458555,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"ebe0cfa0-a909-47e0-8294-28ad84a8fe77"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1785730458555,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"f9a2d1b6-8f23-43a5-8702-d413fed40990"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1785730458555,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"f9a2d1b6-8f23-43a5-8702-d413fed40990"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1785730458555,"data":{"title":"Reply with exactly DIRECT_CHILD_OK and","messageSeqs":[5],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785730458555,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":9,"time":1785730458555,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 38c5dfae47..adf877c24b 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -5,7 +5,7 @@ {"type":"subagent/descriptor","seq":3,"time":1785821418270,"data":{"version":2,"mode":"one-shot","provider":"spawn"}} {"type":"step/start","seq":4,"time":1785730458703,"data":{"turn":1,"step":1}} {"type":"user/message","seq":5,"time":1785730458703,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"2ac2cc54-9bce-4cfa-a569-a64f51bc30a7"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1785730458703,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"dfbcd587-db47-4c3d-bbe9-8c031b215fc3"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1785730458703,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"dfbcd587-db47-4c3d-bbe9-8c031b215fc3"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1785730458703,"data":{"title":"Reply with exactly WORKFLOW_CHILD_OK and","messageSeqs":[5],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785730458703,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":9,"time":1785730458703,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index ec5c5756f2..f4169abe78 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821417919,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783957884486,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498801761,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: try a no-op temporary Cordis Plugin named snapshot-marker; use run_code to inspect the live temporary Plugins through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; stop dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"},"role":"user","id":"6e45782a-31be-4ba7-8c4a-7411a2027e36"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730458430,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"9f38e2b8-1d4e-4c90-8896-00aa42307ea7"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730458430,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"9f38e2b8-1d4e-4c90-8896-00aa42307ea7"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730458430,"data":{"title":"Run this advanced flow exactly","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498801765,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730458431,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/bash-spill/session.jsonl b/examples/acp-agent/tests/snapshots/bash-spill/session.jsonl index 075b166442..449db5acb4 100644 --- a/examples/acp-agent/tests/snapshots/bash-spill/session.jsonl +++ b/examples/acp-agent/tests/snapshots/bash-spill/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821368742,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498767672,"data":{"content":[{"type":"text","text":"Use the bash tool to print a large deterministic output, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"4f33bd12-21b5-4ccc-bbd2-4edb0ab6b33b"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730421018,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"ac1209c1-ce77-4622-a7c4-b39225fda7ab"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730421018,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"ac1209c1-ce77-4622-a7c4-b39225fda7ab"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730421018,"data":{"title":"Use the bash tool to","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498767673,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730421019,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/bash-tool-turn/session.jsonl b/examples/acp-agent/tests/snapshots/bash-tool-turn/session.jsonl index 2d49114651..6e4de13d80 100644 --- a/examples/acp-agent/tests/snapshots/bash-tool-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/bash-tool-turn/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821375023,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352050755,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498771360,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo TERMINAL_OK. Then reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"38694db6-921d-41fd-b1fb-3b0c40caf67c"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730424635,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"80474489-442a-4e98-beef-df6cd1e85870"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730424635,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"80474489-442a-4e98-beef-df6cd1e85870"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730424635,"data":{"title":"Use the bash tool to","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498771361,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730424636,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index 9341d8f61a..a1b26a5af4 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821443048,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1785014504370,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498827112,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"},"role":"user","id":"922e078d-9ef7-4017-9c4e-96a34a721503"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730479344,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"d3891fd4-21eb-4869-8a66-498764450bf2"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730479344,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"d3891fd4-21eb-4869-8a66-498764450bf2"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730479344,"data":{"title":"Call the run_code tool (NOT","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498827116,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730479345,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl b/examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl index a6932c5165..a3676dbc3d 100644 --- a/examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl +++ b/examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821402705,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1784437195076,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498792518,"data":{"content":[{"type":"text","text":"Run two shell commands: wait for cancellation, then write skipped.txt."}],"source":{"kind":"user"},"role":"user","id":"6025dc7c-dc38-4a34-b7b1-688102631c75"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730445587,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"bf953438-d1c4-4e00-a06b-7f5e2da1df7a"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730445587,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"bf953438-d1c4-4e00-a06b-7f5e2da1df7a"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730445587,"data":{"title":"Run two shell commands: wait","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498792519,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730445588,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/cancel/session.jsonl b/examples/acp-agent/tests/snapshots/cancel/session.jsonl index f28bb4a224..c6396be679 100644 --- a/examples/acp-agent/tests/snapshots/cancel/session.jsonl +++ b/examples/acp-agent/tests/snapshots/cancel/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821401560,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498791446,"data":{"content":[{"type":"text","text":"Start a long task; this turn will be cancelled mid-stream."}],"source":{"kind":"user"},"role":"user","id":"f74653c2-8793-4004-ab0d-833a8dfd42bf"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730444531,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"2c4c8dc2-5141-4963-adbc-5928729d3bf6"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730444531,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"2c4c8dc2-5141-4963-adbc-5928729d3bf6"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730444531,"data":{"title":"Start a long task; this","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498791447,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730444532,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} 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 81422f7470..24e1525c79 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821440493,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1785014439593,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498824620,"data":{"content":[{"type":"text","text":"Using ONE run_code program: call the bash tool twice — exactly `echo CODE_ONE` then exactly `echo CODE_TWO`. Inside that same program, console.log exactly `captured output`, then return the two outputs joined with a plus sign. Reply with that joined string only and stop."}],"source":{"kind":"user"},"role":"user","id":"8e2d7086-925a-4734-ba89-418940b0ee58"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730477066,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"ea97a8e4-de78-4638-b80a-c24dfeaba555"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730477066,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"ea97a8e4-de78-4638-b80a-c24dfeaba555"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730477066,"data":{"title":"Using ONE run_code program: call","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498824624,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730477067,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl index 3ef5fb3589..6107589cb2 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl @@ -5,7 +5,7 @@ {"type":"step/start","seq":3,"time":1785901435161,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498825917,"data":{"content":[{"type":"text","text":"Using ONE run_code program, call tools.read on nested/task.txt. After the program finishes, answer the workspace handshake question using the newly discovered instructions: What is the Code Mode workspace handshake?"}],"source":{"kind":"user"},"role":"user","id":"3b04578e-7b22-4b44-b4cd-ef9d4d26fe8b"},"surfaceOp":"append"} {"type":"user/message","seq":5,"time":1785901435161,"data":{"content":[{"type":"text","text":"\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nWorkspace snapshot root instruction.\n\n"}],"source":{"kind":"workspace-instructions","form":"instructions","baseline":true,"changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2119a7072358cc727f8d9c4cb7388e905b075fe6"}]},"role":"user","id":"ac92e76e-4861-47a6-87f8-4e9ca904eb24"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1785730478198,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"d6d78330-05c0-4ebd-9e29-595df6440250"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1785730478198,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"d6d78330-05c0-4ebd-9e29-595df6440250"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1785730478198,"data":{"title":"Using ONE run_code program, call","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785498825920,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":9,"time":1785730478199,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl index c14513774f..12a88365a6 100644 --- a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl +++ b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821419616,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1784449176720,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498803419,"data":{"content":[{"type":"text","text":"Inspect the exact tools service API and tools/pre-execute event with cordis_inspect, then reply with exactly CORDIS_INSPECT_JSDOC_OK."}],"source":{"kind":"user"},"role":"user","id":"3a6e7222-9340-429e-bec7-c30fcd063c70"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730459873,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"f9a387d6-bd6f-4613-9c11-5768017feb5c"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730459873,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"f9a387d6-bd6f-4613-9c11-5768017feb5c"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730459873,"data":{"title":"Inspect the exact tools service","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498803423,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730459874,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} @@ -15,7 +15,7 @@ {"type":"assistant/chunk","seq":13,"time":1785730459883,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":14,"time":1785730459883,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"6b62bed7-113a-4d2e-a6aa-b935a1063ee2"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[9,10,11,12,13],"surfaceOp":"append"} {"type":"tool/call","seq":15,"time":1785730459883,"data":{"turn":1,"step":1,"callId":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}} -{"type":"tool/result","seq":16,"time":1785730459904,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"inspect-tools-api"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly inbox: Inbox;\n readonly status: AgentStatus;\n readonly ctx: Context;\n cancel(cause: AgentCancelCause, options?: CancelOptions): void;\n whenIdle(): Promise;\n runMaintenance(task: (signal: AbortSignal) => Promise): Promise;\n send(message: UserMessage, target: InboxTarget, wakeup: boolean): void;\n followup(message: UserMessage): void;\n steer(message: UserMessage): void;\n inject(message: UserMessage): void;\n }\n export type AgentCancelCause = {\n readonly kind: 'user';\n } | {\n readonly kind: 'parent';\n } | {\n readonly kind: 'hook';\n readonly reason: string;\n } | {\n readonly kind: 'disposed';\n };\n export interface AgentOptions {\n provider?: string;\n model?: string;\n maxTokens?: number;\n }\n export type AgentStatus = 'idle' | 'running';\n export interface AssistantMessage extends Message {\n readonly role: 'assistant';\n readonly source: ModelMessageSource;\n }\n export interface AssistantProvenance {\n provider: string;\n model: string;\n replayState?: unknown;\n }\n export type Branded = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export interface CancelOptions {\n keepInbox?: boolean | undefined;\n }\n export interface ContentBlockMap {\n 'text': TextBlock;\n 'reasoning': ReasoningBlock;\n 'tool-call': ToolCallBlock;\n 'tool-result': ToolResultBlock;\n }\n export type ContentBlockType = keyof ContentBlockMap;\n export type ContextForm = 'instructions' | 'catalog';\n export interface ContextFormed {\n readonly form?: ContextForm;\n }\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface EpochHeader {\n config: LlmCallConfig;\n adapterDefaults?: LlmCallConfigAdapterDefaults;\n system?: string;\n tools?: ToolSchema[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export type FinishReason = FinishReasonMap[keyof FinishReasonMap];\n export interface FinishReasonMap {\n 'stop': {\n kind: 'stop';\n };\n 'tool-calls': {\n kind: 'tool-calls';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n 'aborted': {\n kind: 'aborted';\n failure: LlmFailure;\n };\n 'error': {\n kind: 'error';\n failure: LlmFailure;\n };\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export class Inbox {\n constructor(private readonly session: Session, private readonly notifications: InboxNotifications);\n get nextTurn(): readonly UserMessage[];\n get nextStep(): readonly UserMessage[];\n get hasPending(): boolean;\n clear(): void;\n claim(target: InboxTarget, turn: number): UserMessage[];\n append(target: InboxTarget, message: UserMessage): void;\n prepend(target: InboxTarget, message: UserMessage): void;\n replace(messageId: MessageId, newMessage: UserMessage): boolean;\n remove(messageId: MessageId): boolean;\n splice(target: InboxTarget, start: number, deleteCount: number, inserted: UserMessage[]): UserMessage[];\n }\n export interface InboxNotifications {\n inserted(message: UserMessage): void;\n discarded(message: UserMessage): void;\n claimed(message: UserMessage, turn: number): void;\n }\n export type InboxTarget = 'next-turn' | 'next-step';\n export interface JsonSchemaNode {\n type?: JsonSchemaType;\n oneOf?: JsonSchemaNode[];\n properties?: Record;\n required?: string[];\n additionalProperties?: boolean;\n items?: JsonSchemaNode;\n enum?: JsonSchemaScalar[];\n const?: JsonSchemaScalar;\n description?: string;\n title?: string;\n default?: JsonValue;\n examples?: JsonValue;\n }\n export type JsonSchemaScalar = string | number | boolean | null;\n export type JsonSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null';\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export interface LlmCallConfig {\n provider: string;\n model: string;\n reasoningEffort?: ReasoningEffortId;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n }\n export interface LlmCallConfigAdapterDefaults {\n reasoningEffort?: true;\n maxTokens?: true;\n }\n export interface LlmFailure {\n readonly message: string;\n readonly code: string;\n readonly status?: number;\n readonly providerRetryAfterMs?: number;\n readonly requestId?: ProviderRequestId;\n }\n export interface Message {\n readonly id: MessageId;\n readonly role: 'system' | 'user' | 'assistant';\n readonly content: ContentBlock[];\n readonly source: MessageSource;\n }\n export type MessageId = Branded<'MessageId'>;\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n } & ContextFormed;\n model: ModelMessageSource;\n tool: ToolMessageSource;\n }\n export interface ModelMessageSource extends AssistantProvenance {\n kind: 'model';\n }\n export type ProviderRequestId = Branded<'ProviderRequestId'>;\n export interface ReadFileLine {\n number: number;\n text: string;\n }\n export interface ReadResultView {\n card: 'read';\n title?: string;\n path: string;\n offset: number;\n lines: ReadFileLine[];\n totalLines: number;\n lang?: string;\n content?: ContentBlock[];\n }\n export interface ReasoningBlock {\n type: 'reasoning';\n text: string;\n }\n export type ReasoningEffortId = Branded<'ReasoningEffortId'>;\n export interface RequestContext {\n provider: string;\n model: string;\n contextWindow?: number;\n }\n export type RequestHeaderReason = 'initial' | 'resume' | 'change';\n export type ScopeKey = object;\n export interface SearchFileMatches {\n path: string;\n matches: SearchLineMatch[];\n }\n export interface SearchLineMatch {\n lineNumber: number;\n line: string;\n }\n export interface SearchMatchesResultView {\n card: 'search';\n shape: 'matches';\n title?: string;\n files: SearchFileMatches[];\n truncated: boolean;\n total: number;\n }\n export interface SearchPathsResultView {\n card: 'search';\n shape: 'paths';\n title?: string;\n paths: string[];\n truncated: boolean;\n total: number;\n }\n export type SearchResultView = SearchMatchesResultView | SearchPathsResultView;\n export class Session {\n get surface(): SessionSurface;\n readonly header: SessionHeader;\n get id(): SessionId;\n readonly firstLiveSeq: number;\n static create(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader): Session;\n static fromRestore(id: SessionId, seed: readonly SessionEvent[], header: SessionHeader): Session;\n get events(): readonly SessionEvent[];\n get seq(): number;\n append(type: T, data: SessionEventMap[T], ...opts: T extends SurfaceEventType ? [\n opts: SurfaceIntent\n ] : [\n ]): SessionEvent;\n requestHeader(): EpochHeader | undefined;\n requestContext(): RequestContext | undefined;\n deriveMessages(): Message[];\n deriveEventMessage(event: SessionEvent): Message | null;\n }\n export type SessionEvent = {\n [K in SessionEventType]: {\n type: K;\n seq: number;\n time: number;\n data: SessionEventMap[K];\n } & (K extends SurfaceEventType ? {\n sourceEventSeqs?: number[];\n surfaceOp?: SurfaceOp;\n } : object);\n }[T];\n export interface SessionEventMap {\n 'turn/start': {\n turn: number;\n };\n 'turn/end': {\n turn: number;\n reason: TurnEndReason;\n };\n 'step/start': {\n turn: number;\n step: number;\n };\n 'step/end': {\n turn: number;\n step: number;\n };\n 'user/message': UserMessage;\n 'assistant/chunk': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n 'assistant/message': {\n turn: number;\n step: number;\n message: AssistantMessage;\n usage?: TokenUsage;\n };\n 'tool/call': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n 'tool/result': {\n turn: number;\n step: number;\n message: ToolResultMessage;\n error?: {\n name: string;\n code: string;\n };\n meta?: JsonValue;\n };\n 'todo/write': {\n todos: TodoItem[];\n };\n 'request/header': {\n header: EpochHeader;\n reason: RequestHeaderReason;\n };\n 'request/context': RequestContext;\n 'session/end-seed': Record;\n }\n export type SessionEventType = keyof SessionEventMap;\n export interface SessionHeader {\n readonly version: number;\n readonly id: SessionId;\n readonly createdAt: number;\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n readonly origin?: 'subagent';\n readonly delegationDepth?: number;\n }\n export type SessionId = Branded<'SessionId'>;\n export interface SessionSurface {\n readonly nodes: readonly number[];\n readonly replaceGeneration: number;\n }\n export type StreamChunk = {\n type: 'block-start';\n index: number;\n blockType: ContentBlockType;\n } | {\n type: 'text-delta';\n index: number;\n text: string;\n } | {\n type: 'reasoning-delta';\n index: number;\n text: string;\n } | {\n type: 'tool-call-delta';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n } | {\n type: 'block-end';\n index: number;\n block: ContentBlock;\n } | {\n type: 'usage';\n usage: TokenUsage;\n } | {\n type: 'finish';\n reason: FinishReason;\n replayState?: unknown;\n };\n export type SurfaceEventType = 'user/message' | 'assistant/message' | 'tool/result';\n export interface SurfaceIntent {\n surfaceOp: SurfaceOp;\n sourceEventSeqs?: number[];\n }\n export type SurfaceOp = 'append' | {\n op: 'replace';\n start: number;\n end: number;\n };\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export interface TodoItem {\n content: string;\n status: 'pending' | 'in_progress' | 'completed';\n }\n export interface TokenUsage {\n inputTokens: number;\n outputTokens: number;\n cacheReadTokens?: number;\n cacheWriteTokens?: number;\n reasoningTokens?: number;\n }\n export interface ToolCallBlock {\n type: 'tool-call';\n id: CallId;\n name: string;\n arguments: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise;\n finalizeContent?(exec: Readonly, result: Readonly): ContentBlock[] | undefined;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionFailure {\n readonly isError: true;\n readonly error: ToolFailure;\n readonly value?: never;\n readonly content: ContentBlock[];\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: never;\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n readonly signal: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure;\n export interface ToolExecutionSuccess {\n readonly isError: false;\n readonly value: JsonValue;\n readonly content: ContentBlock[];\n readonly error?: never;\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: true;\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export interface ToolFailure {\n message: string;\n info?: ToolErrorInfo;\n }\n export type ToolGuard = (execution: Readonly) => string | undefined;\n export interface ToolMessageSource {\n kind: 'tool';\n callId: CallId;\n }\n export interface ToolOutputDefinition {\n readonly schema: JsonSchemaNode;\n render(args: unknown, value: JsonValue): ContentBlock[];\n presentationMeta?(args: unknown, value: JsonValue): JsonValue;\n }\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: JsonValue;\n }\n export interface ToolResultBlock {\n type: 'tool-result';\n toolCallId: CallId;\n content: ContentBlock[];\n isError?: boolean;\n }\n export interface ToolResultMessage extends Message {\n readonly role: 'user';\n readonly content: [\n ToolResultBlock\n ];\n readonly source: ToolMessageSource;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView | SearchResultView | ReadResultView | WebResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: UserMessage): void;\n concludeTurn(): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record;\n }\n export type TurnEndCancelCause = AgentCancelCause | {\n readonly kind: 'legacy';\n };\n export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap];\n export interface TurnEndReasonMap {\n completed: {\n kind: 'completed';\n };\n aborted: {\n kind: 'aborted';\n reason: TurnEndCancelCause;\n };\n blocked: {\n kind: 'blocked';\n };\n error: {\n kind: 'error';\n error: LlmFailure;\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n interrupted: {\n kind: 'interrupted';\n };\n }\n export interface UserMessage extends Message {\n readonly role: 'user';\n }\n export interface WebFetchResultView {\n card: 'web';\n kind: 'fetch';\n title?: string;\n url: string;\n statusCode: number;\n truncated: boolean;\n }\n export type WebResultView = WebSearchResultView | WebFetchResultView;\n export interface WebSearchResultView {\n card: 'web';\n kind: 'search';\n title?: string;\n sources: WebSource[];\n answer?: string;\n truncated: boolean;\n }\n export interface WebSource {\n url: string;\n title?: string;\n snippet?: string;\n publishedAt?: string;\n }"}],"isError":false}],"role":"user","id":"847bf2e6-59da-4621-946d-06932a78f0ce"}},"sourceEventSeqs":[15],"surfaceOp":"append"} +{"type":"tool/result","seq":16,"time":1785730459904,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"inspect-tools-api"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly inbox: Inbox;\n readonly status: AgentStatus;\n readonly ctx: Context;\n cancel(cause: AgentCancelCause, options?: CancelOptions): void;\n whenIdle(): Promise;\n runMaintenance(task: (signal: AbortSignal) => Promise): Promise;\n send(message: UserMessage, target: InboxTarget, wakeup: boolean): void;\n followup(message: UserMessage): void;\n steer(message: UserMessage): void;\n inject(message: UserMessage): void;\n }\n export type AgentCancelCause = {\n readonly kind: 'user';\n } | {\n readonly kind: 'parent';\n } | {\n readonly kind: 'hook';\n readonly reason: string;\n } | {\n readonly kind: 'disposed';\n };\n export interface AgentOptions {\n provider?: string;\n model?: string;\n maxTokens?: number;\n }\n export type AgentStatus = 'idle' | 'running';\n export interface AssistantMessage extends Message {\n readonly role: 'assistant';\n readonly source: ModelMessageSource;\n }\n export interface AssistantProvenance {\n provider: string;\n model: string;\n replayState?: unknown;\n }\n export type Branded = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export interface CancelOptions {\n keepInbox?: boolean | undefined;\n }\n export interface ContentBlockMap {\n 'text': TextBlock;\n 'reasoning': ReasoningBlock;\n 'tool-call': ToolCallBlock;\n 'tool-result': ToolResultBlock;\n }\n export type ContentBlockType = keyof ContentBlockMap;\n export type ContextFormed = {\n readonly form?: never;\n } | {\n readonly form: 'instructions';\n } | {\n readonly form: 'catalog';\n } | {\n readonly form: 'snapshot';\n readonly sections: readonly ContextSnapshotSection[];\n } | {\n readonly form: 'notice';\n readonly summary: string;\n } | {\n readonly form: 'relay';\n } | {\n readonly form: 'recall';\n };\n export interface ContextSnapshotSection {\n readonly name: string;\n readonly text: string;\n }\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface EpochHeader {\n config: LlmCallConfig;\n adapterDefaults?: LlmCallConfigAdapterDefaults;\n system?: string;\n tools?: ToolSchema[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export type FinishReason = FinishReasonMap[keyof FinishReasonMap];\n export interface FinishReasonMap {\n 'stop': {\n kind: 'stop';\n };\n 'tool-calls': {\n kind: 'tool-calls';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n 'aborted': {\n kind: 'aborted';\n failure: LlmFailure;\n };\n 'error': {\n kind: 'error';\n failure: LlmFailure;\n };\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export class Inbox {\n constructor(private readonly session: Session, private readonly notifications: InboxNotifications);\n get nextTurn(): readonly UserMessage[];\n get nextStep(): readonly UserMessage[];\n get hasPending(): boolean;\n clear(): void;\n claim(target: InboxTarget, turn: number): UserMessage[];\n append(target: InboxTarget, message: UserMessage): void;\n prepend(target: InboxTarget, message: UserMessage): void;\n replace(messageId: MessageId, newMessage: UserMessage): boolean;\n remove(messageId: MessageId): boolean;\n splice(target: InboxTarget, start: number, deleteCount: number, inserted: UserMessage[]): UserMessage[];\n }\n export interface InboxNotifications {\n inserted(message: UserMessage): void;\n discarded(message: UserMessage): void;\n claimed(message: UserMessage, turn: number): void;\n }\n export type InboxTarget = 'next-turn' | 'next-step';\n export interface JsonSchemaNode {\n type?: JsonSchemaType;\n oneOf?: JsonSchemaNode[];\n properties?: Record;\n required?: string[];\n additionalProperties?: boolean;\n items?: JsonSchemaNode;\n enum?: JsonSchemaScalar[];\n const?: JsonSchemaScalar;\n description?: string;\n title?: string;\n default?: JsonValue;\n examples?: JsonValue;\n }\n export type JsonSchemaScalar = string | number | boolean | null;\n export type JsonSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null';\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export interface LlmCallConfig {\n provider: string;\n model: string;\n reasoningEffort?: ReasoningEffortId;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n }\n export interface LlmCallConfigAdapterDefaults {\n reasoningEffort?: true;\n maxTokens?: true;\n }\n export interface LlmFailure {\n readonly message: string;\n readonly code: string;\n readonly status?: number;\n readonly providerRetryAfterMs?: number;\n readonly requestId?: ProviderRequestId;\n }\n export interface Message {\n readonly id: MessageId;\n readonly role: 'system' | 'user' | 'assistant';\n readonly content: ContentBlock[];\n readonly source: MessageSource;\n }\n export type MessageId = Branded<'MessageId'>;\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n } & ContextFormed;\n model: ModelMessageSource;\n tool: ToolMessageSource;\n }\n export interface ModelMessageSource extends AssistantProvenance {\n kind: 'model';\n }\n export type ProviderRequestId = Branded<'ProviderRequestId'>;\n export interface ReadFileLine {\n number: number;\n text: string;\n }\n export interface ReadResultView {\n card: 'read';\n title?: string;\n path: string;\n offset: number;\n lines: ReadFileLine[];\n totalLines: number;\n lang?: string;\n content?: ContentBlock[];\n }\n export interface ReasoningBlock {\n type: 'reasoning';\n text: string;\n }\n export type ReasoningEffortId = Branded<'ReasoningEffortId'>;\n export interface RequestContext {\n provider: string;\n model: string;\n contextWindow?: number;\n }\n export type RequestHeaderReason = 'initial' | 'resume' | 'change';\n export type ScopeKey = object;\n export interface SearchFileMatches {\n path: string;\n matches: SearchLineMatch[];\n }\n export interface SearchLineMatch {\n lineNumber: number;\n line: string;\n }\n export interface SearchMatchesResultView {\n card: 'search';\n shape: 'matches';\n title?: string;\n files: SearchFileMatches[];\n truncated: boolean;\n total: number;\n }\n export interface SearchPathsResultView {\n card: 'search';\n shape: 'paths';\n title?: string;\n paths: string[];\n truncated: boolean;\n total: number;\n }\n export type SearchResultView = SearchMatchesResultView | SearchPathsResultView;\n export class Session {\n get surface(): SessionSurface;\n readonly header: SessionHeader;\n get id(): SessionId;\n readonly firstLiveSeq: number;\n static create(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader): Session;\n static fromRestore(id: SessionId, seed: readonly SessionEvent[], header: SessionHeader): Session;\n get events(): readonly SessionEvent[];\n get seq(): number;\n append(type: T, data: SessionEventMap[T], ...opts: T extends SurfaceEventType ? [\n opts: SurfaceIntent\n ] : [\n ]): SessionEvent;\n requestHeader(): EpochHeader | undefined;\n requestContext(): RequestContext | undefined;\n deriveMessages(): Message[];\n deriveEventMessage(event: SessionEvent): Message | null;\n }\n export type SessionEvent = {\n [K in SessionEventType]: {\n type: K;\n seq: number;\n time: number;\n data: SessionEventMap[K];\n } & (K extends SurfaceEventType ? {\n sourceEventSeqs?: number[];\n surfaceOp?: SurfaceOp;\n } : object);\n }[T];\n export interface SessionEventMap {\n 'turn/start': {\n turn: number;\n };\n 'turn/end': {\n turn: number;\n reason: TurnEndReason;\n };\n 'step/start': {\n turn: number;\n step: number;\n };\n 'step/end': {\n turn: number;\n step: number;\n };\n 'user/message': UserMessage;\n 'assistant/chunk': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n 'assistant/message': {\n turn: number;\n step: number;\n message: AssistantMessage;\n usage?: TokenUsage;\n };\n 'tool/call': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n 'tool/result': {\n turn: number;\n step: number;\n message: ToolResultMessage;\n error?: {\n name: string;\n code: string;\n };\n meta?: JsonValue;\n };\n 'todo/write': {\n todos: TodoItem[];\n };\n 'request/header': {\n header: EpochHeader;\n reason: RequestHeaderReason;\n };\n 'request/context': RequestContext;\n 'session/end-seed': Record;\n }\n export type SessionEventType = keyof SessionEventMap;\n export interface SessionHeader {\n readonly version: number;\n readonly id: SessionId;\n readonly createdAt: number;\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n readonly origin?: 'subagent';\n readonly delegationDepth?: number;\n }\n export type SessionId = Branded<'SessionId'>;\n export interface SessionSurface {\n readonly nodes: readonly number[];\n readonly replaceGeneration: number;\n }\n export type StreamChunk = {\n type: 'block-start';\n index: number;\n blockType: ContentBlockType;\n } | {\n type: 'text-delta';\n index: number;\n text: string;\n } | {\n type: 'reasoning-delta';\n index: number;\n text: string;\n } | {\n type: 'tool-call-delta';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n } | {\n type: 'block-end';\n index: number;\n block: ContentBlock;\n } | {\n type: 'usage';\n usage: TokenUsage;\n } | {\n type: 'finish';\n reason: FinishReason;\n replayState?: unknown;\n };\n export type SurfaceEventType = 'user/message' | 'assistant/message' | 'tool/result';\n export interface SurfaceIntent {\n surfaceOp: SurfaceOp;\n sourceEventSeqs?: number[];\n }\n export type SurfaceOp = 'append' | {\n op: 'replace';\n start: number;\n end: number;\n };\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export interface TodoItem {\n content: string;\n status: 'pending' | 'in_progress' | 'completed';\n }\n export interface TokenUsage {\n inputTokens: number;\n outputTokens: number;\n cacheReadTokens?: number;\n cacheWriteTokens?: number;\n reasoningTokens?: number;\n }\n export interface ToolCallBlock {\n type: 'tool-call';\n id: CallId;\n name: string;\n arguments: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise;\n finalizeContent?(exec: Readonly, result: Readonly): ContentBlock[] | undefined;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionFailure {\n readonly isError: true;\n readonly error: ToolFailure;\n readonly value?: never;\n readonly content: ContentBlock[];\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: never;\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n readonly signal: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure;\n export interface ToolExecutionSuccess {\n readonly isError: false;\n readonly value: JsonValue;\n readonly content: ContentBlock[];\n readonly error?: never;\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: true;\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export interface ToolFailure {\n message: string;\n info?: ToolErrorInfo;\n }\n export type ToolGuard = (execution: Readonly) => string | undefined;\n export interface ToolMessageSource {\n kind: 'tool';\n callId: CallId;\n }\n export interface ToolOutputDefinition {\n readonly schema: JsonSchemaNode;\n render(args: unknown, value: JsonValue): ContentBlock[];\n presentationMeta?(args: unknown, value: JsonValue): JsonValue;\n }\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: JsonValue;\n }\n export interface ToolResultBlock {\n type: 'tool-result';\n toolCallId: CallId;\n content: ContentBlock[];\n isError?: boolean;\n }\n export interface ToolResultMessage extends Message {\n readonly role: 'user';\n readonly content: [\n ToolResultBlock\n ];\n readonly source: ToolMessageSource;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView | SearchResultView | ReadResultView | WebResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: UserMessage): void;\n concludeTurn(): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record;\n }\n export type TurnEndCancelCause = AgentCancelCause | {\n readonly kind: 'legacy';\n };\n export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap];\n export interface TurnEndReasonMap {\n completed: {\n kind: 'completed';\n };\n aborted: {\n kind: 'aborted';\n reason: TurnEndCancelCause;\n };\n blocked: {\n kind: 'blocked';\n };\n error: {\n kind: 'error';\n error: LlmFailure;\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n interrupted: {\n kind: 'interrupted';\n };\n }\n export interface UserMessage extends Message {\n readonly role: 'user';\n }\n export interface WebFetchResultView {\n card: 'web';\n kind: 'fetch';\n title?: string;\n url: string;\n statusCode: number;\n truncated: boolean;\n }\n export type WebResultView = WebSearchResultView | WebFetchResultView;\n export interface WebSearchResultView {\n card: 'web';\n kind: 'search';\n title?: string;\n sources: WebSource[];\n answer?: string;\n truncated: boolean;\n }\n export interface WebSource {\n url: string;\n title?: string;\n snippet?: string;\n publishedAt?: string;\n }"}],"isError":false}],"role":"user","id":"847bf2e6-59da-4621-946d-06932a78f0ce"}},"sourceEventSeqs":[15],"surfaceOp":"append"} {"type":"step/end","seq":17,"time":1785730459904,"data":{"turn":1,"step":1}} {"type":"step/start","seq":18,"time":1785730459916,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":19,"time":1784449176734,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl b/examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl index 741fb4d797..b619d352e5 100644 --- a/examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl +++ b/examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821397720,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498788095,"data":{"content":[{"type":"text","text":"This prompt first receives an empty completion, then a retried reply."}],"source":{"kind":"user"},"role":"user","id":"04a4b0d6-8873-4ec0-bed5-75de910b556f"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730441191,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"1bbd9bae-e790-4b83-8425-2f042dd37908"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730441191,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"1bbd9bae-e790-4b83-8425-2f042dd37908"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730441191,"data":{"title":"This prompt first receives an","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498788096,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730441192,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/error-finish/session.jsonl b/examples/acp-agent/tests/snapshots/error-finish/session.jsonl index 12afe1fa3e..fdcb57aabd 100644 --- a/examples/acp-agent/tests/snapshots/error-finish/session.jsonl +++ b/examples/acp-agent/tests/snapshots/error-finish/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821396359,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785499006415,"data":{"content":[{"type":"text","text":"This prompt triggers a recorded provider error."}],"source":{"kind":"user"},"role":"user","id":"87677683-56b7-458b-b512-6db73c570e08"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730686099,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"b3b9d048-3992-458f-aad5-b738e4a7d815"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730686099,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"b3b9d048-3992-458f-aad5-b738e4a7d815"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730686099,"data":{"title":"This prompt triggers a recorded","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785499006416,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730686100,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl index 591cd7e4d6..77a4a39b8d 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821444447,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1784821261726,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498828313,"data":{"content":[{"type":"text","text":"The sandbox already denied writing /tmp/dsh-escalated.txt earlier (it is outside this workspace). Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt, with sandbox_permissions set to danger-full-access and the justification 'the user asked to write a file outside the workspace'. Do not run it without sandbox_permissions first. I will approve the permission prompt. After the result, reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"c8597dbb-3765-4c91-9315-2a5704ab60de"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730480503,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"b945fb82-1839-405c-9859-f2d4630a1801"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730480503,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"b945fb82-1839-405c-9859-f2d4630a1801"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730480503,"data":{"title":"The sandbox already denied writing","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498828315,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730480504,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl index 4f05bbfbcf..96b51253d9 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821445663,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1784821263267,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498829488,"data":{"content":[{"type":"text","text":"The sandbox already denied writing /tmp/dsh-escalated.txt earlier (it is outside this workspace). Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt, with sandbox_permissions set to danger-full-access and the justification 'the user asked to write a file outside the workspace'. Do not run it without sandbox_permissions first. I will reject the permission prompt; after the rejection, do not retry and do not work around it — explain in one short sentence and stop."}],"source":{"kind":"user"},"role":"user","id":"e1326897-4139-437b-959c-3b25e46e60ec"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730481594,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"016923c3-51c4-45ba-8a54-4d9d309c0d8e"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730481594,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"016923c3-51c4-45ba-8a54-4d9d309c0d8e"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730481594,"data":{"title":"The sandbox already denied writing","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498829489,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730481595,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl index 18125bea36..cfcdfee68c 100644 --- a/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821389289,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352084742,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498781491,"data":{"content":[{"type":"text","text":"First use the read tool to read config.txt in the current directory. Then use the edit tool (NOT bash) to replace the literal text DEBUG with RELEASE in that file. Then reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"b900992d-cb68-45e3-bdf1-366e2529f6c0"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730434501,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"79d38e8e-c85a-434a-9638-490dea3c8ea8"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730434501,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"79d38e8e-c85a-434a-9638-490dea3c8ea8"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730434501,"data":{"title":"First use the read tool","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498781493,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730434502,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl b/examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl index b5feb459d3..6f69260bad 100644 --- a/examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821446846,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1784821264855,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498830644,"data":{"content":[{"type":"text","text":"Use the write tool (NOT bash) to create escalated.md in the current directory containing exactly the single line: escalated. An equivalent write was denied earlier, so make this one single write call with sandbox_permissions set to danger-full-access and the justification 'the user asked to escalate this write'. Do not call write without sandbox_permissions first. I will approve the permission prompt. After the result, reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"c2a0f1a3-11ce-4d84-bff4-49213573cb37"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730482654,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"54411374-45a0-468c-b524-e5f4d0314e40"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730482654,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"54411374-45a0-468c-b524-e5f4d0314e40"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730482654,"data":{"title":"Use the write tool (NOT","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498830646,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730482655,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl index 112a2b6cab..270cd287f4 100644 --- a/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821393932,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783611702550,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498784863,"data":{"content":[{"type":"text","text":"Do NOT use the read tool and do NOT use bash or shell commands. Immediately use the edit tool to replace the literal text blue with green in settings.txt in the current directory. Do not read the file first. After the tool result, reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"065530a1-5d85-4adb-9458-6511300b63bc"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730437873,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"35df0186-19a8-46d5-bdee-344a776db520"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730437873,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"35df0186-19a8-46d5-bdee-344a776db520"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730437873,"data":{"title":"Do NOT use the read","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498784864,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730437874,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl index ea8e65620c..f9c19a18d3 100644 --- a/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821392334,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352099840,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498783725,"data":{"content":[{"type":"text","text":"Use the read tool (NOT bash) with offset 5 and limit 4 to read lines 5 through 8 of big.txt in the current directory. Then reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"a6db8c80-6239-490e-8ee4-1e2074d73a19"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730436765,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"d5453309-c7da-4071-b46f-5441ca4a828b"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730436765,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"d5453309-c7da-4071-b46f-5441ca4a828b"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730436765,"data":{"title":"Use the read tool (NOT","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498783727,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730436766,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/fs-read/session.jsonl b/examples/acp-agent/tests/snapshots/fs-read/session.jsonl index 0373748f2c..9bab6eb99e 100644 --- a/examples/acp-agent/tests/snapshots/fs-read/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821386137,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352072470,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498779296,"data":{"content":[{"type":"text","text":"Use the read tool (NOT bash) to read the file greeting.txt in the current directory, then reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"3b9f093c-8fed-49d1-8252-7e6560033ebd"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730432294,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"d2b5abf5-ff22-4268-bac3-b6338c6e2f02"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730432294,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"d2b5abf5-ff22-4268-bac3-b6338c6e2f02"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730432294,"data":{"title":"Use the read tool (NOT","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498779297,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730432295,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl index 67c4a6c2be..52310b746b 100644 --- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821390865,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352092223,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498782618,"data":{"content":[{"type":"text","text":"First use the read tool to read data.txt in the current directory. Then use the write tool (NOT bash) to replace its entire contents with exactly the single line: replaced. Then reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"e1697ae3-3d38-4492-9dad-5115f056934a"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730435638,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"3d35609b-3d69-4790-8078-c79eff29bbd8"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730435638,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"3d35609b-3d69-4790-8078-c79eff29bbd8"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730435638,"data":{"title":"First use the read tool","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498782619,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730435639,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/fs-write/session.jsonl b/examples/acp-agent/tests/snapshots/fs-write/session.jsonl index 48a3c835c9..461d8999fe 100644 --- a/examples/acp-agent/tests/snapshots/fs-write/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821387697,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352078756,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498780381,"data":{"content":[{"type":"text","text":"Use the write tool (NOT bash) to create a file named notes.txt in the current directory containing exactly the single line: hello world. Then reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"8316fddb-e888-4ba9-b280-2d2bb8717633"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730433386,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"b54d8375-2277-4551-bd0b-06b40d1ad59a"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730433386,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"b54d8375-2277-4551-bd0b-06b40d1ad59a"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730433386,"data":{"title":"Use the write tool (NOT","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498780382,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730433387,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-invalid-matcher/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-invalid-matcher/session.jsonl index 11409c2a03..bc5f42573a 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-invalid-matcher/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-invalid-matcher/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821424016,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783600629542,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498807263,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"},"role":"user","id":"a56c3c26-071d-407c-8900-d84de1222c0c"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730463095,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"fe569552-1e83-41d2-a240-55df5da79bc9"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730463095,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"fe569552-1e83-41d2-a240-55df5da79bc9"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730463095,"data":{"title":"Reply with exactly the word:","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498807265,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730463096,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl index c8c3b91c7d..79bfe25837 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821430451,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783962504152,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498813609,"data":{"content":[{"type":"text","text":"Call the bash tool to run exactly: echo HELLO. If the first tool result is rejected, retry that command once. Quote the final tool result verbatim and stop."}],"source":{"kind":"user"},"role":"user","id":"ff685d2f-c629-45a2-a6b1-9aba6679e804"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730468551,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"30410f7f-af50-4d13-898a-6fc04927fd93"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730468551,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"30410f7f-af50-4d13-898a-6fc04927fd93"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730468551,"data":{"title":"Call the bash tool to","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498813611,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730468552,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl index 597b1eaa28..3de51d6886 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821431674,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352196664,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498815008,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"},"role":"user","id":"f13c12f8-c187-4bae-bab7-a63d04e66f38"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730469687,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"6bba4af4-6406-410c-b730-541278dcdbd7"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730469687,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"6bba4af4-6406-410c-b730-541278dcdbd7"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730469687,"data":{"title":"Use the bash tool to","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498815010,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730469688,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl index 1ee79964b0..e917d074d7 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821429300,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352171527,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498812202,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"},"role":"user","id":"8b8672e5-2bff-458d-b482-51b703f61dcb"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730467496,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"9d525efc-a44b-4217-a882-d29d8feb042f"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730467496,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"9d525efc-a44b-4217-a882-d29d8feb042f"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730467496,"data":{"title":"Use the bash tool to","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498812203,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730467497,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl index 880eb36f8c..b3aac9fb00 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821428131,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352165198,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498810766,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"},"role":"user","id":"8b449df9-9149-4e05-8464-5fccbbbf06ba"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730466373,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"37e3a9e3-c9f8-431f-8af2-aa16d270e534"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730466373,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"37e3a9e3-c9f8-431f-8af2-aa16d270e534"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730466373,"data":{"title":"Use the bash tool to","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498810768,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730466374,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl index e2a05b7d1d..b03b6b7b4e 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl @@ -6,7 +6,7 @@ {"type":"hook/result","seq":4,"time":1785821426920,"data":{"turn":1,"point":"UserPromptSubmit","handlerId":"claude:UserPromptSubmit:1","decision":"pass","exitCode":0,"durationMs":4.92145800000003}} {"type":"step/start","seq":5,"time":1785821426949,"data":{"turn":1,"step":1}} {"type":"user/message","seq":6,"time":1785730465275,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"},"role":"user","id":"c403acd5-efa4-4c8c-948f-211f3b23c93f"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":1785821426950,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"2514657a-056c-46a8-ac90-c0169b42f048"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":1785821426950,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"2514657a-056c-46a8-ac90-c0169b42f048"},"surfaceOp":"append"} {"type":"user/message","seq":8,"time":1785821426950,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-claude"},"role":"user","id":"8006cbd3-a233-4d35-a61b-1a9e0c6b4545"},"surfaceOp":"append"} {"type":"session/title","seq":9,"time":1785821426950,"data":{"title":"What is my favorite color?","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":10,"time":1785821426951,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl index 96fe89d332..f2e54f6499 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821432845,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1784522140648,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498816483,"data":{"content":[{"type":"text","text":"Reply with the single word FIRST and stop."}],"source":{"kind":"user"},"role":"user","id":"4f322d30-9425-4c61-afbb-ee5432ba6552"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730470752,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"b3914542-4c81-4699-b07e-863d2ef3a818"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730470752,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"b3914542-4c81-4699-b07e-863d2ef3a818"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730470752,"data":{"title":"Reply with the single word","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498816486,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730470753,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-invalid-matcher/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-invalid-matcher/session.jsonl index a161045ea5..374ae19eb3 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-invalid-matcher/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-invalid-matcher/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821425396,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783600629542,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498808410,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"},"role":"user","id":"14d17f1b-63f3-478a-8859-2c0d8cbbf38d"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730464165,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"a4958955-419b-49bf-848b-d404c24e0061"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730464165,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"a4958955-419b-49bf-848b-d404c24e0061"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730464165,"data":{"title":"Reply with exactly the word:","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498808411,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730464166,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl index 2903c7a247..cd72379fa4 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821436674,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783986962240,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498820704,"data":{"content":[{"type":"text","text":"Call the bash tool exactly once to run: echo HELLO. Whatever tool result comes back, quote it verbatim and stop without calling another tool."}],"source":{"kind":"user"},"role":"user","id":"3c6acf4d-845a-44e9-9fde-0ff9611f1b89"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730473886,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"90fd41ec-8404-4c36-8c80-9eec3dda86a7"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730473886,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"90fd41ec-8404-4c36-8c80-9eec3dda86a7"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730473886,"data":{"title":"Call the bash tool exactly","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498820706,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730473887,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl index 2813196245..085aca05da 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821437930,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352228443,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498822136,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"},"role":"user","id":"428246ac-6aee-4609-9ff4-5c5f5755fb61"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730474943,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"442c4504-a8f1-4e47-9314-e3d2badd93df"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730474943,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"442c4504-a8f1-4e47-9314-e3d2badd93df"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730474943,"data":{"title":"Use the bash tool to","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498822138,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730474944,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl index a329513cee..eb521c4df8 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821435310,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352214607,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498819368,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"},"role":"user","id":"83299ced-cede-4e39-a425-4b58915f8c06"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730472832,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"a01d2417-d639-4920-ae79-bd3aa6b5c3bb"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730472832,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"a01d2417-d639-4920-ae79-bd3aa6b5c3bb"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730472832,"data":{"title":"Use the bash tool to","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498819371,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730472833,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl index b2a6d287da..e046950b21 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl @@ -6,7 +6,7 @@ {"type":"hook/result","seq":4,"time":1785821434017,"data":{"turn":1,"point":"UserPromptSubmit","handlerId":"codex:UserPromptSubmit:1","decision":"pass","exitCode":0,"durationMs":3.7565839999999753}} {"type":"step/start","seq":5,"time":1785821434044,"data":{"turn":1,"step":1}} {"type":"user/message","seq":6,"time":1785730471801,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"},"role":"user","id":"8d3df251-9583-4ddb-9ead-a50df35bbac6"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":1785821434044,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"e5f01e9b-c7c7-4f33-b3aa-b949ad404d98"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":1785821434044,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"e5f01e9b-c7c7-4f33-b3aa-b949ad404d98"},"surfaceOp":"append"} {"type":"user/message","seq":8,"time":1785821434044,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-codex"},"role":"user","id":"7c3bd47e-8613-4853-bf55-769ece5c609e"},"surfaceOp":"append"} {"type":"session/title","seq":9,"time":1785821434044,"data":{"title":"What is my favorite color?","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":10,"time":1785821434045,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl index b28ab2e081..11f329a53b 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821439141,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1784522152399,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498823368,"data":{"content":[{"type":"text","text":"Reply with the single word FIRST and stop."}],"source":{"kind":"user"},"role":"user","id":"26dda5a7-298f-4809-96ba-e8be4381afa5"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730476001,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"af67bfc1-182f-4dc5-bbb4-093463938e34"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730476001,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"af67bfc1-182f-4dc5-bbb4-093463938e34"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730476001,"data":{"title":"Reply with the single word","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498823370,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730476002,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/lsp-definition/session.jsonl b/examples/acp-agent/tests/snapshots/lsp-definition/session.jsonl index 9f48213a1c..471b14d87e 100644 --- a/examples/acp-agent/tests/snapshots/lsp-definition/session.jsonl +++ b/examples/acp-agent/tests/snapshots/lsp-definition/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821380423,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498775018,"data":{"content":[{"type":"text","text":"Use the lsp tool exactly once to find the definition at subject.ts line 1 character 7, then reply with exactly DONE."}],"source":{"kind":"user"},"role":"user","id":"d50783a4-e1dd-4d27-8aaf-fa854ffa5560"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730428059,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"63d79744-f179-4840-8278-b1ec07d25158"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730428059,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"63d79744-f179-4840-8278-b1ec07d25158"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730428059,"data":{"title":"Use the lsp tool exactly","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498775021,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730428060,"data":{"provider":"deepseek-official","model":"deepseek-v4-pro"}} diff --git a/examples/acp-agent/tests/snapshots/missing-sandbox-runner/session.jsonl b/examples/acp-agent/tests/snapshots/missing-sandbox-runner/session.jsonl index cf1475057f..f9e30bb24d 100644 --- a/examples/acp-agent/tests/snapshots/missing-sandbox-runner/session.jsonl +++ b/examples/acp-agent/tests/snapshots/missing-sandbox-runner/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785916902430,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1785916902458,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785916902458,"data":{"content":[{"type":"text","text":"Run true once with bash in the foreground. After that fails, run true with bash in the background, read task bash-1 with task_output and wait=true, then reply with exactly RUNNER_FAILURES_SURFACED and stop."}],"source":{"kind":"user"},"role":"user","id":"2d2f8e7a-f08a-464d-8e94-048d1d95717e"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785916902459,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns.\n\nApproval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"de3778e7-e47a-4d34-a004-ecf43da3c9db"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785916902459,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns.\n\nApproval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."},{"name":"approval:policy","text":"Approval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"de3778e7-e47a-4d34-a004-ecf43da3c9db"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785916902459,"data":{"title":"Run true once with bash","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785916902460,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785916902460,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} @@ -27,7 +27,7 @@ {"type":"tool/call","seq":25,"time":1785916902500,"data":{"turn":1,"step":2,"callId":"missing-runner-background","name":"bash","arguments":"{\"command\":\"true\",\"description\":\"Exercise missing sandbox runner in background\",\"run_in_background\":true}"}} {"type":"tool/result","seq":26,"time":1785916902508,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"missing-runner-background"},"content":[{"type":"tool-result","toolCallId":"missing-runner-background","content":[{"type":"text","text":"started background task bash-1"}],"isError":false}],"role":"user","id":"a40cf397-5842-4c09-a6b8-f831eb84827c"}},"sourceEventSeqs":[25],"surfaceOp":"append"} {"type":"step/end","seq":27,"time":1785916902508,"data":{"turn":1,"step":2}} -{"type":"agent/inbox/spliced","seq":28,"time":1785916902508,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"background task bash-1 (bash: true) finished [status: killed, killed before exit]. Read its output with task_output."}],"source":{"kind":"plugin","plugin":"tool-tasks"},"role":"user","id":"989e3c2b-5b21-4694-83d5-6cddac55ce0e"}]}} +{"type":"agent/inbox/spliced","seq":28,"time":1785916902508,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"background task bash-1 (bash: true) finished [status: killed, killed before exit]. Read its output with task_output."}],"source":{"kind":"plugin","plugin":"tool-tasks","form":"notice","summary":"bash true [status: killed, killed before exit]"},"role":"user","id":"989e3c2b-5b21-4694-83d5-6cddac55ce0e"}]}} {"type":"step/start","seq":29,"time":1785916902519,"data":{"turn":1,"step":3}} {"type":"assistant/chunk","seq":30,"time":1785825343607,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":31,"time":1785825343607,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"missing-runner-output","name":"task_output","argumentsDelta":"{\"task_id\":\"bash-1\",\"wait\":true}"}}} @@ -40,7 +40,7 @@ {"type":"step/end","seq":38,"time":1785916902532,"data":{"turn":1,"step":3}} {"type":"agent/inbox/spliced","seq":39,"time":1785916902532,"data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":40,"time":1785916902542,"data":{"turn":1,"step":4}} -{"type":"user/message","seq":41,"time":1785916902542,"data":{"content":[{"type":"text","text":"background task bash-1 (bash: true) finished [status: killed, killed before exit]. Read its output with task_output."}],"source":{"kind":"plugin","plugin":"tool-tasks"},"role":"user","id":"989e3c2b-5b21-4694-83d5-6cddac55ce0e"},"surfaceOp":"append"} +{"type":"user/message","seq":41,"time":1785916902542,"data":{"content":[{"type":"text","text":"background task bash-1 (bash: true) finished [status: killed, killed before exit]. Read its output with task_output."}],"source":{"kind":"plugin","plugin":"tool-tasks","form":"notice","summary":"bash true [status: killed, killed before exit]"},"role":"user","id":"989e3c2b-5b21-4694-83d5-6cddac55ce0e"},"surfaceOp":"append"} {"type":"assistant/chunk","seq":42,"time":1785825343627,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":43,"time":1785825343628,"data":{"turn":1,"step":4,"chunk":{"type":"text-delta","index":0,"text":"RUNNER_FAILURES_SURFACED"}}} {"type":"assistant/chunk","seq":44,"time":1785916902550,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"RUNNER_FAILURES_SURFACED"}}}} diff --git a/examples/acp-agent/tests/snapshots/multi-turn/session.jsonl b/examples/acp-agent/tests/snapshots/multi-turn/session.jsonl index 6392fbf640..46aac90caa 100644 --- a/examples/acp-agent/tests/snapshots/multi-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/multi-turn/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821395167,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352113767,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498786007,"data":{"content":[{"type":"text","text":"Reply with exactly the word: ONE. No tools."}],"source":{"kind":"user"},"role":"user","id":"4d8893f0-f22d-4e43-ac31-f5e7afbda565"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730439011,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"92ebc873-c6cf-4d0f-a30c-7ae0739d1007"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730439011,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"92ebc873-c6cf-4d0f-a30c-7ae0739d1007"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730439011,"data":{"title":"Reply with exactly the word:","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498786009,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730439012,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/packed-chunks/session.jsonl b/examples/acp-agent/tests/snapshots/packed-chunks/session.jsonl index 4d951eebf9..d334ef777e 100644 --- a/examples/acp-agent/tests/snapshots/packed-chunks/session.jsonl +++ b/examples/acp-agent/tests/snapshots/packed-chunks/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821364567,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352165198,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498765364,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"},"role":"user","id":"a207bd9d-9312-46ed-baaf-7a07a6f08ae8"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730418683,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"1c954f81-4e70-4e28-bf11-5f8424f09391"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730418683,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"1c954f81-4e70-4e28-bf11-5f8424f09391"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730418683,"data":{"title":"Use the bash tool to","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498765365,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730418684,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl b/examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl index 251fcaf938..295fe91ed9 100644 --- a/examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl +++ b/examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821366930,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498766502,"data":{"content":[{"type":"text","text":"Use the read tool twice in the same assistant message: read a.txt and b.txt. Then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"e306a97e-4da2-4b50-bec4-90ede1237df4"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730419890,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"02b21476-4349-49c1-a1b8-91d80c27ef0d"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730419890,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"02b21476-4349-49c1-a1b8-91d80c27ef0d"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730419890,"data":{"title":"Use the read tool twice","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498766504,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730419891,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/partial-landlock-child-failure/session.jsonl b/examples/acp-agent/tests/snapshots/partial-landlock-child-failure/session.jsonl index 14ce6b3590..7b73001a01 100644 --- a/examples/acp-agent/tests/snapshots/partial-landlock-child-failure/session.jsonl +++ b/examples/acp-agent/tests/snapshots/partial-landlock-child-failure/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785916901383,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1785916901409,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785916901409,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: false. Then reply with exactly CHILD_EXIT_PRESERVED and stop."}],"source":{"kind":"user"},"role":"user","id":"8a81cb32-8acc-4929-bb63-ec02adea20df"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785916901409,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns.\n\nApproval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"b3b13d6d-dcef-47cb-bbb3-26229c44792c"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785916901409,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns.\n\nApproval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."},{"name":"approval:policy","text":"Approval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"b3b13d6d-dcef-47cb-bbb3-26229c44792c"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785916901409,"data":{"title":"Use the bash tool to","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785916901410,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785916901410,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/pty-tools/session.jsonl b/examples/acp-agent/tests/snapshots/pty-tools/session.jsonl index 8e5a8a2601..f9d4ed2242 100644 --- a/examples/acp-agent/tests/snapshots/pty-tools/session.jsonl +++ b/examples/acp-agent/tests/snapshots/pty-tools/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821373074,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498770152,"data":{"content":[{"type":"text","text":"Exercise the six PTY tools in order, including one missing-session signal error, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"96ac9845-3961-4010-8ee5-d9e5aff18b42"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730423409,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"f7ef1bc0-f4ec-4d3e-b198-399ee1cec46f"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730423409,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"f7ef1bc0-f4ec-4d3e-b198-399ee1cec46f"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730423409,"data":{"title":"Exercise the six PTY tools","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498770153,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730423410,"data":{"provider":"deepseek-official","model":"deepseek-v4-pro"}} diff --git a/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl b/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl index 64bdcbd4fb..800e6f9b01 100644 --- a/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl +++ b/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821399027,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498789151,"data":{"content":[{"type":"text","text":"Write the todo list 'watch the kettle boil' five times in a row without changing it, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"f92afb51-ac61-47d2-b0fb-ee55cc744838"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730442276,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"f9ec98a9-17c2-418e-9982-b8b3e2f8a17d"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730442276,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"f9ec98a9-17c2-418e-9982-b8b3e2f8a17d"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730442276,"data":{"title":"Write the todo list 'watch","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498789152,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730442277,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} @@ -39,11 +39,11 @@ {"type":"tool/call","seq":37,"time":1785730442328,"data":{"turn":1,"step":3,"callId":"call_3","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":38,"time":1785730442335,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":39,"time":1785730442335,"data":{"turn":1,"step":3,"message":{"source":{"kind":"tool","callId":"call_3"},"content":[{"type":"tool-result","toolCallId":"call_3","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false}],"role":"user","id":"779c894c-9e9f-4c8e-a073-36d32b421b0f"}},"sourceEventSeqs":[37],"surfaceOp":"append"} -{"type":"agent/inbox/spliced","seq":40,"time":1785730442335,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"You are repeating the exact same tool call with identical arguments. Carefully analyze the previous result before calling again: if the task is not complete, try a different approach or different arguments instead of repeating the call."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard"},"role":"user","id":"1dee8d17-2cdd-4f76-8330-709191cf8cbb"}]}} +{"type":"agent/inbox/spliced","seq":40,"time":1785730442335,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"You are repeating the exact same tool call with identical arguments. Carefully analyze the previous result before calling again: if the task is not complete, try a different approach or different arguments instead of repeating the call."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard","form":"notice","summary":"todo_write × 3"},"role":"user","id":"1dee8d17-2cdd-4f76-8330-709191cf8cbb"}]}} {"type":"step/end","seq":41,"time":1785730442335,"data":{"turn":1,"step":3}} {"type":"agent/inbox/spliced","seq":42,"time":1785730442335,"data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":43,"time":1785730442344,"data":{"turn":1,"step":4}} -{"type":"user/message","seq":44,"time":1785730442344,"data":{"content":[{"type":"text","text":"You are repeating the exact same tool call with identical arguments. Carefully analyze the previous result before calling again: if the task is not complete, try a different approach or different arguments instead of repeating the call."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard"},"role":"user","id":"1dee8d17-2cdd-4f76-8330-709191cf8cbb"},"surfaceOp":"append"} +{"type":"user/message","seq":44,"time":1785730442344,"data":{"content":[{"type":"text","text":"You are repeating the exact same tool call with identical arguments. Carefully analyze the previous result before calling again: if the task is not complete, try a different approach or different arguments instead of repeating the call."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard","form":"notice","summary":"todo_write × 3"},"role":"user","id":"1dee8d17-2cdd-4f76-8330-709191cf8cbb"},"surfaceOp":"append"} {"type":"assistant/chunk","seq":45,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":46,"time":1785498789219,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"call_4","name":"todo_write","argumentsDelta":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}} {"type":"assistant/chunk","seq":47,"time":1785498789219,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_4","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}}} @@ -64,11 +64,11 @@ {"type":"tool/call","seq":62,"time":1785730442368,"data":{"turn":1,"step":5,"callId":"call_5","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":63,"time":1785730442376,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":64,"time":1785730442376,"data":{"turn":1,"step":5,"message":{"source":{"kind":"tool","callId":"call_5"},"content":[{"type":"tool-result","toolCallId":"call_5","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false}],"role":"user","id":"fa3d2366-ffd8-4f75-833d-e4193c7c9749"}},"sourceEventSeqs":[62],"surfaceOp":"append"} -{"type":"agent/inbox/spliced","seq":65,"time":1785730442376,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"Repeated tool call detected:\n- tool: todo_write\n- consecutive_calls: 5\n- arguments: {\"todos\":[{\"content\":\"watch the kettle boil\",\"status\":\"in_progress\"}]}\nThe repeated calls are not making progress. Do not call this tool with these exact arguments again. Inspect the latest result and choose a different action, different arguments, or finish the task if enough evidence has been gathered."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard"},"role":"user","id":"4ca50ec2-4e31-43c2-bc10-f4bdaa678127"}]}} +{"type":"agent/inbox/spliced","seq":65,"time":1785730442376,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"Repeated tool call detected:\n- tool: todo_write\n- consecutive_calls: 5\n- arguments: {\"todos\":[{\"content\":\"watch the kettle boil\",\"status\":\"in_progress\"}]}\nThe repeated calls are not making progress. Do not call this tool with these exact arguments again. Inspect the latest result and choose a different action, different arguments, or finish the task if enough evidence has been gathered."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard","form":"notice","summary":"todo_write × 5"},"role":"user","id":"4ca50ec2-4e31-43c2-bc10-f4bdaa678127"}]}} {"type":"step/end","seq":66,"time":1785730442376,"data":{"turn":1,"step":5}} {"type":"agent/inbox/spliced","seq":67,"time":1785730442376,"data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":68,"time":1785730442384,"data":{"turn":1,"step":6}} -{"type":"user/message","seq":69,"time":1785730442384,"data":{"content":[{"type":"text","text":"Repeated tool call detected:\n- tool: todo_write\n- consecutive_calls: 5\n- arguments: {\"todos\":[{\"content\":\"watch the kettle boil\",\"status\":\"in_progress\"}]}\nThe repeated calls are not making progress. Do not call this tool with these exact arguments again. Inspect the latest result and choose a different action, different arguments, or finish the task if enough evidence has been gathered."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard"},"role":"user","id":"4ca50ec2-4e31-43c2-bc10-f4bdaa678127"},"surfaceOp":"append"} +{"type":"user/message","seq":69,"time":1785730442384,"data":{"content":[{"type":"text","text":"Repeated tool call detected:\n- tool: todo_write\n- consecutive_calls: 5\n- arguments: {\"todos\":[{\"content\":\"watch the kettle boil\",\"status\":\"in_progress\"}]}\nThe repeated calls are not making progress. Do not call this tool with these exact arguments again. Inspect the latest result and choose a different action, different arguments, or finish the task if enough evidence has been gathered."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard","form":"notice","summary":"todo_write × 5"},"role":"user","id":"4ca50ec2-4e31-43c2-bc10-f4bdaa678127"},"surfaceOp":"append"} {"type":"assistant/chunk","seq":70,"time":1785498789257,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":71,"time":1785498789257,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"DONE."}}} {"type":"assistant/chunk","seq":72,"time":1785498789257,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE."}}}} diff --git a/examples/acp-agent/tests/snapshots/session-query-spill/session.jsonl b/examples/acp-agent/tests/snapshots/session-query-spill/session.jsonl index b5b7d42671..9ba17ca2ee 100644 --- a/examples/acp-agent/tests/snapshots/session-query-spill/session.jsonl +++ b/examples/acp-agent/tests/snapshots/session-query-spill/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821371103,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498768995,"data":{"content":[{"type":"text","text":"Read request event 5 with session_event_read, verify the complete spill was retained, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"05ed182c-4c88-4019-912e-518ed6e431ba"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730422266,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"82025f74-4ec2-4ac7-a90b-5eb18f184abb"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730422266,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"82025f74-4ec2-4ac7-a90b-5eb18f184abb"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730422266,"data":{"title":"Read request event 5 with","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498768997,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730422267,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} @@ -15,7 +15,7 @@ {"type":"assistant/chunk","seq":13,"time":1785730422276,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":14,"time":1785730422276,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_session_query_spill","name":"session_event_read","arguments":"{\"seq\":5}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"a4ee27a4-32b2-40d1-aeac-6a8bc8fcc2de"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[9,10,11,12,13],"surfaceOp":"append"} {"type":"tool/call","seq":15,"time":1785730422276,"data":{"turn":1,"step":1,"callId":"call_session_query_spill","name":"session_event_read","arguments":"{\"seq\":5}"}} -{"type":"tool/result","seq":16,"time":1785730422286,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_session_query_spill"},"content":[{"type":"tool-result","toolCallId":"call_session_query_spill","content":[{"type":"text","text":"Session {{sessionId}} — Read request event 5 with\nTarget event seq 5:\n```json\n{\n \"type\": \"user/message\",\n \"seq\": 5,\n \"time\": 1785821371147,\n \"data\": {\n \"content\": [\n {\n \"type\": \"text\",\n \"text\": \"Current runtime context. This snapshot supersedes ically — do not request sandbox escalation (do not set `sandbox_permissions`).\"\n }\n ],\n \"source\": {\n \"kind\": \"plugin\",\n \"plugin\": \"@deepseek-ai/dsh-system-prompt\"\n },\n \"role\": \"user\",\n \"id\": \"82025f74-4ec2-4ac7-a90b-5eb18f184abb\"\n },\n \"surfaceOp\": \"append\"\n}\n```\n\n(Omitted 266 bytes. Full formatted result stored at: /tmp/dsh-acp-snap-035d1d054/session-aa56455bb13a/dfff8c2b8a66-session_event_read.txt. Use read with offset/limit, or grep this path to search within it.)"}],"isError":false}],"role":"user","id":"8f96f03f-4fca-4c3a-ba34-ce891adde50f"}},"sourceEventSeqs":[15],"surfaceOp":"append"} +{"type":"tool/result","seq":16,"time":1785730422286,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_session_query_spill"},"content":[{"type":"tool-result","toolCallId":"call_session_query_spill","content":[{"type":"text","text":"Session {{sessionId}} — Read request event 5 with\nTarget event seq 5:\n```json\n{\n \"type\": \"user/message\",\n \"seq\": 5,\n \"time\": 1785987646184,\n \"data\": {\n \"content\": [\n {\n \"type\": \"text\",\n \"text\": \"Current runtime context. This snapshot supersedes mpts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\"\n }\n ]\n },\n \"role\": \"user\",\n \"id\": \"985f57e7-e296-4210-af78-78a485f09894\"\n },\n \"surfaceOp\": \"append\"\n}\n```\n\n(Omitted 782 bytes. Full formatted result stored at: /tmp/dsh-acp-snap-035d1d054/session-aa56455bb13a/dfff8c2b8a66-session_event_read.txt. Use read with offset/limit, or grep this path to search within it.)"}],"isError":false}],"role":"user","id":"8f96f03f-4fca-4c3a-ba34-ce891adde50f"}},"sourceEventSeqs":[15],"surfaceOp":"append"} {"type":"step/end","seq":17,"time":1785730422286,"data":{"turn":1,"step":1}} {"type":"step/start","seq":18,"time":1785730422296,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/session-sandbox-root/session.jsonl b/examples/acp-agent/tests/snapshots/session-sandbox-root/session.jsonl index 22b34e01e1..322d931e1a 100644 --- a/examples/acp-agent/tests/snapshots/session-sandbox-root/session.jsonl +++ b/examples/acp-agent/tests/snapshots/session-sandbox-root/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821448088,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1784821266397,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498831818,"data":{"content":[{"type":"text","text":"Use the write tool (NOT bash) to create session-root.txt in the current directory containing exactly: session root. Then reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"f7d05c95-98f0-44b5-9463-2449682817ff"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730483789,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"/Users/cty/acp-snap-cwd-MABAjO\". Some platform temporary areas may also be writable.\n\nApproval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"7855df4a-1a61-4d6c-bb03-84b80edb0075"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730483789,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"/Users/cty/acp-snap-cwd-MABAjO\". Some platform temporary areas may also be writable.\n\nApproval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"/Users/cty/acp-snap-cwd-MABAjO\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval policy: ask. Operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"7855df4a-1a61-4d6c-bb03-84b80edb0075"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730483789,"data":{"title":"Use the write tool (NOT","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498831819,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730483790,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/session-title-after-turn/session.jsonl b/examples/acp-agent/tests/snapshots/session-title-after-turn/session.jsonl index a2654b2fde..0993d85ded 100644 --- a/examples/acp-agent/tests/snapshots/session-title-after-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/session-title-after-turn/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821360788,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1785222848199,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498762955,"data":{"content":[{"type":"text","text":"Reply with exactly TITLE_DONE. Do not use tools."}],"source":{"kind":"user"},"role":"user","id":"07495f06-71ba-4146-b27c-de2cf46a60fb"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730416395,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"d2f80db6-391b-4fe4-bfd8-744807253b12"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730416395,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"d2f80db6-391b-4fe4-bfd8-744807253b12"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730416395,"data":{"title":"Reply with exactly TITLE_DONE. Do","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498762958,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730416397,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index f12ff2f85e..f30dc715cf 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821378605,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1785498773754,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498773754,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"0ca31b92-27ac-451d-98d3-d1e5f605454b"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785498773755,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"3fc7e2f8-90fc-496c-b516-700cef1d86f1"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785498773755,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"3fc7e2f8-90fc-496c-b516-700cef1d86f1"},"surfaceOp":"append"} {"type":"user/message","seq":6,"time":1785730426818,"data":{"content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `model-only-skill`: Prove user-disabled skills remain available to the model.\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}],"source":{"kind":"skill-catalog","form":"catalog","entries":[{"name":"model-only-skill","description":"Prove user-disabled skills remain available to the model."},{"name":"snapshot-skill","description":"Exercise project skill discovery and loading in snapshot tests."}]},"role":"user","id":"60880315-9799-44c8-8a99-e6fe9ee5bdc5"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1785730426818,"data":{"title":"Load the snapshot-skill skill with","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785498773756,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-continuable/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-continuable/session.1.jsonl index ccaf248ca3..554de6f448 100644 --- a/examples/acp-agent/tests/snapshots/subagent-continuable/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-continuable/session.1.jsonl @@ -4,11 +4,11 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785730451347,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly the word CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"c67a308f-d867-424e-b198-c9f464228703"}]}} {"type":"turn/start","seq":3,"time":1785821409024,"data":{"turn":1}} {"type":"agent/inbox/spliced","seq":4,"time":1785730917162,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} -{"type":"agent/inbox/spliced","seq":5,"time":1785730917192,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Now reply with exactly SECOND_OK."}],"source":{"kind":"coordinator","senderSessionId":"11111111-1111-4111-8111-111111111111"},"role":"user","id":"e7d15a94-203d-43ab-8279-4e22d5218feb"}]}} -{"type":"agent/inbox/spliced","seq":6,"time":1785821409076,"data":{"target":"next-turn","start":1,"inserted":[{"content":[{"type":"text","text":"Now reply with exactly THIRD_OK."}],"source":{"kind":"coordinator","senderSessionId":"11111111-1111-4111-8111-111111111111"},"role":"user","id":"755c76db-6ee8-432d-a2d0-f8a3b7914e08"}]}} +{"type":"agent/inbox/spliced","seq":5,"time":1785730917192,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Now reply with exactly SECOND_OK."}],"source":{"kind":"coordinator","form":"relay","senderSessionId":"11111111-1111-4111-8111-111111111111"},"role":"user","id":"e7d15a94-203d-43ab-8279-4e22d5218feb"}]}} +{"type":"agent/inbox/spliced","seq":6,"time":1785821409076,"data":{"target":"next-turn","start":1,"inserted":[{"content":[{"type":"text","text":"Now reply with exactly THIRD_OK."}],"source":{"kind":"coordinator","form":"relay","senderSessionId":"11111111-1111-4111-8111-111111111111"},"role":"user","id":"755c76db-6ee8-432d-a2d0-f8a3b7914e08"}]}} {"type":"step/start","seq":7,"time":1785730917198,"data":{"turn":1,"step":1}} {"type":"user/message","seq":8,"time":1785730917198,"data":{"content":[{"type":"text","text":"Reply with exactly the word CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"c67a308f-d867-424e-b198-c9f464228703"},"surfaceOp":"append"} -{"type":"user/message","seq":9,"time":1785730917198,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"49acbc16-4d58-460e-8cc0-62838472dce6"},"surfaceOp":"append"} +{"type":"user/message","seq":9,"time":1785730917198,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"49acbc16-4d58-460e-8cc0-62838472dce6"},"surfaceOp":"append"} {"type":"session/title","seq":10,"time":1785730917198,"data":{"title":"Reply with exactly the word","messageSeqs":[8],"source":{"kind":"fallback"}}} {"type":"request/header","seq":11,"time":1785730917198,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":12,"time":1785730917199,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} @@ -23,7 +23,7 @@ {"type":"turn/start","seq":21,"time":1785821409092,"data":{"turn":2}} {"type":"agent/inbox/spliced","seq":22,"time":1785821409092,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":23,"time":1785730696682,"data":{"turn":2,"step":1}} -{"type":"user/message","seq":24,"time":1785730696682,"data":{"content":[{"type":"text","text":"Now reply with exactly SECOND_OK."}],"source":{"kind":"coordinator","senderSessionId":"11111111-1111-4111-8111-111111111111"},"role":"user","id":"e7d15a94-203d-43ab-8279-4e22d5218feb"},"surfaceOp":"append"} +{"type":"user/message","seq":24,"time":1785730696682,"data":{"content":[{"type":"text","text":"Now reply with exactly SECOND_OK."}],"source":{"kind":"coordinator","form":"relay","senderSessionId":"11111111-1111-4111-8111-111111111111"},"role":"user","id":"e7d15a94-203d-43ab-8279-4e22d5218feb"},"surfaceOp":"append"} {"type":"assistant/chunk","seq":25,"time":1785730696686,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":26,"time":1785730696686,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":0,"text":"SECOND_OK"}}} {"type":"assistant/chunk","seq":27,"time":1789000000023,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"SECOND_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-continuable/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-continuable/session.jsonl index 3c8efb1ddd..898d4b250c 100644 --- a/examples/acp-agent/tests/snapshots/subagent-continuable/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-continuable/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821408972,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1785730451327,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785730451327,"data":{"content":[{"type":"text","text":"Follow these steps exactly, then stop. 1. Call the subagent tool once with run_in_background set to true, description 'Reply with CHILD_OK', and prompt 'Reply with exactly the word CHILD_OK and nothing else.'. 2. Call send_message twice in a row, both with the subagent id from step 1: first with message 'Now reply with exactly SECOND_OK.', then with message 'Now reply with exactly THIRD_OK.'. 3. Call send_message with subagent_id exactly '22222222-2222-4222-8222-222222222222' (a subagent that does not exist) and message 'Please continue.', and observe that it fails. 4. Reply with the single word DONE. Do not use the bash tool."}],"source":{"kind":"user"},"role":"user","id":"125665d3-8c03-4190-b4f9-c27d61d245f4"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730451328,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"e7521889-28d8-4434-84b2-21ff0e044fe7"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730451328,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"e7521889-28d8-4434-84b2-21ff0e044fe7"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730451328,"data":{"title":"Follow these steps exactly, then","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785730451329,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730451329,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl index e1362f5cdb..8b8b8cc0c2 100644 --- a/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl @@ -5,7 +5,7 @@ {"type":"subagent/descriptor","seq":3,"time":1785821414185,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Start depth one"}} {"type":"step/start","seq":4,"time":1785730456013,"data":{"turn":1,"step":1}} {"type":"user/message","seq":5,"time":1785730456014,"data":{"content":[{"type":"text","text":"Call subagent once. Ask that child to attempt one further subagent call, then report the result."}],"source":{"kind":"user"},"role":"user","id":"a8129357-1bde-4cbd-90b4-6b8ad51d52e1"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1785730456014,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"3244b13c-f211-445f-acf5-fb8d1534537c"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1785730456014,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"3244b13c-f211-445f-acf5-fb8d1534537c"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1785730456014,"data":{"title":"Call subagent once. Ask that","messageSeqs":[5],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785730456014,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":9,"time":1785730456014,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl b/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl index 8a957dd636..7f2ae89966 100644 --- a/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl @@ -5,7 +5,7 @@ {"type":"subagent/descriptor","seq":3,"time":1785821414214,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Start depth two"}} {"type":"step/start","seq":4,"time":1785730456041,"data":{"turn":1,"step":1}} {"type":"user/message","seq":5,"time":1785730456041,"data":{"content":[{"type":"text","text":"Attempt one subagent call beyond the configured cap, then report the rejection."}],"source":{"kind":"user"},"role":"user","id":"d4dc5a16-e542-4dd9-8e82-e6b7829cfc4b"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1785730456041,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"4a252f7d-8523-433f-a3fc-33812be802ec"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1785730456041,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"4a252f7d-8523-433f-a3fc-33812be802ec"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1785730456041,"data":{"title":"Attempt one subagent call beyond","messageSeqs":[5],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785730456041,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":9,"time":1785730456042,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.jsonl index 37c7b008be..6288b6d516 100644 --- a/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821414127,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1784540790308,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498798839,"data":{"content":[{"type":"text","text":"Delegate through two child generations. The depth-two child must attempt one more subagent call and report the rejection."}],"source":{"kind":"user"},"role":"user","id":"b2260a25-4667-49ed-9297-16b233f22332"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730455980,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"d3ba1b18-4d27-4c90-a95d-125e9ffc9f29"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730455980,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"d3ba1b18-4d27-4c90-a95d-125e9ffc9f29"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730455980,"data":{"title":"Delegate through two child generations.","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498798841,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730455981,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl index b26e6e1227..a56f7ccf60 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821406454,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352134840,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498796115,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is MARMALADE. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"},"role":"user","id":"8e65a90a-a69c-44f1-b55f-49fefdabb74c"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730448968,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"40eb2299-67e0-44db-8132-84564259fc8b"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730448968,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"40eb2299-67e0-44db-8132-84564259fc8b"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730448968,"data":{"title":"Remember this fact for later:","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498796118,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730448969,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl index 7daf489e18..c7eb17a0cb 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821406454,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352134840,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498796115,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is MARMALADE. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"},"role":"user","id":"8e65a90a-a69c-44f1-b55f-49fefdabb74c"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730448968,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"40eb2299-67e0-44db-8132-84564259fc8b"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730448968,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"40eb2299-67e0-44db-8132-84564259fc8b"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730448968,"data":{"title":"Remember this fact for later:","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498796118,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730448969,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-list-agents/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-list-agents/session.1.jsonl index 9a0ee79f04..d6e54e2096 100644 --- a/examples/acp-agent/tests/snapshots/subagent-list-agents/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-list-agents/session.1.jsonl @@ -6,7 +6,7 @@ {"type":"agent/inbox/spliced","seq":4,"time":1785821412774,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":5,"time":1785730454835,"data":{"turn":1,"step":1}} {"type":"user/message","seq":6,"time":1785730454835,"data":{"content":[{"type":"text","text":"Reply with exactly the word CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"2a46160e-89d3-433b-bf04-66fb0313abfa"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":1785730454835,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"524be394-8639-4c12-a41d-799b9e0120a1"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":1785730454835,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"524be394-8639-4c12-a41d-799b9e0120a1"},"surfaceOp":"append"} {"type":"session/title","seq":8,"time":1785730454835,"data":{"title":"Reply with exactly the word","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":9,"time":1785730454835,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":10,"time":1785730454835,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-list-agents/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-list-agents/session.jsonl index edf5ca3ea2..1a0113e440 100644 --- a/examples/acp-agent/tests/snapshots/subagent-list-agents/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-list-agents/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821412725,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1785730454783,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785730454783,"data":{"content":[{"type":"text","text":"Call the subagent tool once with run_in_background set to true, description 'Reply with CHILD_OK', and prompt 'Reply with exactly the word CHILD_OK and nothing else.'. Then reply with the single word STARTED. Do not call any other tool."}],"source":{"kind":"user"},"role":"user","id":"c2febfff-792d-4457-a944-933ff0de0570"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730454783,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"cc8cb20d-5802-46a9-87b8-d3ee784f8e52"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730454783,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"cc8cb20d-5802-46a9-87b8-d3ee784f8e52"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730454783,"data":{"title":"Call the subagent tool once","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785730454784,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730454784,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl index fd2593bc1f..e275607cbf 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl @@ -5,7 +5,7 @@ {"type":"subagent/descriptor","seq":3,"time":1785821407767,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Reply ALPHA only"}} {"type":"step/start","seq":4,"time":1785730450187,"data":{"turn":1,"step":1}} {"type":"user/message","seq":5,"time":1785730450187,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"73ce401a-faaf-408a-879e-7485380d537d"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1785730450187,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"4a5a7c59-b6f8-47b0-8c09-d9a05607deac"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1785730450187,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"4a5a7c59-b6f8-47b0-8c09-d9a05607deac"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1785730450187,"data":{"title":"Reply with exactly the word","messageSeqs":[5],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785730450187,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":9,"time":1785730450188,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl index d24cb8a038..fb6e5e0971 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821407687,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352142835,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498797379,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is SAFFRON. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"},"role":"user","id":"3d1ea7cb-c273-4c38-a765-5ff256eaaf51"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730450135,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"473ecf9e-52c4-4db2-be56-1c8f7fa7d932"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730450135,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"473ecf9e-52c4-4db2-be56-1c8f7fa7d932"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730450135,"data":{"title":"Remember this fact for later:","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498797380,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730450136,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl index dc704cc32a..fa390cf176 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821407687,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352142835,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498797379,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is SAFFRON. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"},"role":"user","id":"3d1ea7cb-c273-4c38-a765-5ff256eaaf51"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730450135,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"473ecf9e-52c4-4db2-be56-1c8f7fa7d932"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730450135,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"473ecf9e-52c4-4db2-be56-1c8f7fa7d932"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730450135,"data":{"title":"Remember this fact for later:","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498797380,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730450136,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl index d0b798bf1f..7948013736 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl @@ -5,7 +5,7 @@ {"type":"subagent/descriptor","seq":3,"time":1785821405245,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Return ALPHA only"}} {"type":"step/start","seq":4,"time":1785730447828,"data":{"turn":1,"step":1}} {"type":"user/message","seq":5,"time":1785730447828,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"a287f842-f6f2-4a17-ab4c-820e41f498d5"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1785730447828,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"bab5cdff-7925-478d-b55a-daa2ef524d7c"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1785730447828,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"bab5cdff-7925-478d-b55a-daa2ef524d7c"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1785730447828,"data":{"title":"Reply with exactly the word","messageSeqs":[5],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785730447828,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":9,"time":1785730447828,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl index 51b8e8cca8..64e58b3741 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl @@ -5,7 +5,7 @@ {"type":"subagent/descriptor","seq":3,"time":1785821405299,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Return BETA only"}} {"type":"step/start","seq":4,"time":1785730447881,"data":{"turn":1,"step":1}} {"type":"user/message","seq":5,"time":1785730447881,"data":{"content":[{"type":"text","text":"Reply with exactly the word BETA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"53f6419d-8ddc-4eee-8803-5b68411336f9"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1785730447881,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"036067ef-a106-4955-841c-a0d2effe51ef"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1785730447881,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"036067ef-a106-4955-841c-a0d2effe51ef"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1785730447881,"data":{"title":"Reply with exactly the word","messageSeqs":[5],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785730447881,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":9,"time":1785730447881,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl index 66fedff41c..3a48c2d760 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821405184,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352126252,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498794765,"data":{"content":[{"type":"text","text":"Use the subagent tool TWICE, once at a time, to delegate two subtasks to child agents. First subtask: 'Reply with exactly the word ALPHA and nothing else.' Second subtask (after the first returns): 'Reply with exactly the word BETA and nothing else.' After both subagents return, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"},"role":"user","id":"07bf16df-0499-420d-9510-3204061f0122"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730447790,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"9b4b262d-cbd7-4cd8-b24b-70b2b401b0fe"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730447790,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"9b4b262d-cbd7-4cd8-b24b-70b2b401b0fe"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730447790,"data":{"title":"Use the subagent tool TWICE,","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498794766,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730447791,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-published-run-failure/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-published-run-failure/session.jsonl index ef64d948af..4578a14b09 100644 --- a/examples/acp-agent/tests/snapshots/subagent-published-run-failure/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-published-run-failure/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821410244,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1785730452505,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785730452505,"data":{"content":[{"type":"text","text":"Delegate one foreground subagent. Its published run will fail; report that failure as PARENT_OBSERVED_ERROR."}],"source":{"kind":"user"},"role":"user","id":"07e6bcfc-3d70-46ef-8bdd-17a45c2c346e"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730452505,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"902b2d5b-6b6a-471a-b765-5a5ca5d0ff53"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730452505,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"902b2d5b-6b6a-471a-b765-5a5ca5d0ff53"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730452505,"data":{"title":"Delegate one foreground subagent. Its","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785730452506,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730452506,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-report/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-report/session.1.jsonl index 27eb9b020f..b9992f1519 100644 --- a/examples/acp-agent/tests/snapshots/subagent-report/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-report/session.1.jsonl @@ -6,7 +6,7 @@ {"type":"agent/inbox/spliced","seq":4,"time":1785821411475,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":5,"time":1785730453639,"data":{"turn":1,"step":1}} {"type":"user/message","seq":6,"time":1785730453639,"data":{"content":[{"type":"text","text":"Call the report tool once with output exactly CHILD_REPORT_OK, then stop."}],"source":{"kind":"user"},"role":"user","id":"9045ac78-393a-4f24-b20d-8999286dd6ce"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":1785730453639,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"67c76a21-6142-45a6-9a49-0485f51edc8d"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":1785730453639,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"67c76a21-6142-45a6-9a49-0485f51edc8d"},"surfaceOp":"append"} {"type":"session/title","seq":8,"time":1785730453639,"data":{"title":"Call the report tool once","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":9,"time":1785730453639,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":10,"time":1785730453639,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-report/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-report/session.jsonl index 17f822c19e..db5cd4a77f 100644 --- a/examples/acp-agent/tests/snapshots/subagent-report/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-report/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821411429,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1785730453591,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785730453591,"data":{"content":[{"type":"text","text":"Follow these steps exactly, then stop. 1. Call the subagent tool once with run_in_background set to true, description 'Report a finding', and prompt 'Call the report tool once with output exactly CHILD_REPORT_OK, then stop.'. 2. Reply with the single word STARTED. Do not use the bash tool."}],"source":{"kind":"user"},"role":"user","id":"5cf78378-e004-4fd5-af4f-cef3b7e190ad"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730453592,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"77141070-eb99-4ec0-908d-646c387982f6"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730453592,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"77141070-eb99-4ec0-908d-646c387982f6"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730453592,"data":{"title":"Follow these steps exactly, then","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785730453592,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730453593,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} @@ -26,13 +26,13 @@ {"type":"assistant/message","seq":24,"time":1785730453628,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"STARTED"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"571faad7-adbd-480c-922a-1499e1329ead"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[19,20,21,22,23],"surfaceOp":"append"} {"type":"step/end","seq":25,"time":1785730453628,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":26,"time":1785730453629,"data":{"turn":1,"reason":{"kind":"completed"}}} -{"type":"agent/inbox/spliced","seq":27,"time":1785730453654,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"Background subagent 33333333-3333-4333-8333-333333333333 reported:"},{"type":"text","text":"CHILD_REPORT_OK"}],"source":{"kind":"subagent-report","senderSessionId":"33333333-3333-4333-8333-333333333333"},"role":"user","id":"824dc60a-f9d7-48ea-a0d4-6d56df83bd4f"}]}} +{"type":"agent/inbox/spliced","seq":27,"time":1785730453654,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"Background subagent 33333333-3333-4333-8333-333333333333 reported:"},{"type":"text","text":"CHILD_REPORT_OK"}],"source":{"kind":"subagent-report","form":"relay","senderSessionId":"33333333-3333-4333-8333-333333333333"},"role":"user","id":"824dc60a-f9d7-48ea-a0d4-6d56df83bd4f"}]}} {"type":"agent/inbox/spliced","seq":28,"time":1785730453673,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Repeat back, verbatim, the exact output the background subagent reported to you. Reply with only that text. Do not use any tools."}],"source":{"kind":"user"},"role":"user","id":"43f17984-22c3-48b9-911e-923a2f68dce0"}]}} {"type":"turn/start","seq":29,"time":1785821411548,"data":{"turn":2}} {"type":"agent/inbox/spliced","seq":30,"time":1785730453673,"data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}} {"type":"agent/inbox/spliced","seq":31,"time":1785821411548,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":32,"time":1785730453683,"data":{"turn":2,"step":1}} -{"type":"user/message","seq":33,"time":1785730453683,"data":{"content":[{"type":"text","text":"Background subagent 33333333-3333-4333-8333-333333333333 reported:"},{"type":"text","text":"CHILD_REPORT_OK"}],"source":{"kind":"subagent-report","senderSessionId":"33333333-3333-4333-8333-333333333333"},"role":"user","id":"824dc60a-f9d7-48ea-a0d4-6d56df83bd4f"},"surfaceOp":"append"} +{"type":"user/message","seq":33,"time":1785730453683,"data":{"content":[{"type":"text","text":"Background subagent 33333333-3333-4333-8333-333333333333 reported:"},{"type":"text","text":"CHILD_REPORT_OK"}],"source":{"kind":"subagent-report","form":"relay","senderSessionId":"33333333-3333-4333-8333-333333333333"},"role":"user","id":"824dc60a-f9d7-48ea-a0d4-6d56df83bd4f"},"surfaceOp":"append"} {"type":"user/message","seq":34,"time":1785730453683,"data":{"content":[{"type":"text","text":"Repeat back, verbatim, the exact output the background subagent reported to you. Reply with only that text. Do not use any tools."}],"source":{"kind":"user"},"role":"user","id":"43f17984-22c3-48b9-911e-923a2f68dce0"},"surfaceOp":"append"} {"type":"assistant/chunk","seq":35,"time":1785730453687,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":36,"time":1785730453687,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":0,"text":"CHILD_REPORT_OK"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl index aa6df16217..7fa229c2e3 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl @@ -5,7 +5,7 @@ {"type":"subagent/descriptor","seq":3,"time":1785821404020,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Reply with CHILD_OK"}} {"type":"step/start","seq":4,"time":1785730446720,"data":{"turn":1,"step":1}} {"type":"user/message","seq":5,"time":1785730446720,"data":{"content":[{"type":"text","text":"Reply with exactly the word CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"54ed23d6-e960-4f36-b192-cf06e1618ea6"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1785730446720,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"1b537017-6493-4f52-8504-01a7384e8cc6"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1785730446720,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"1b537017-6493-4f52-8504-01a7384e8cc6"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1785730446720,"data":{"title":"Reply with exactly the word","messageSeqs":[5],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785730446720,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":9,"time":1785730446721,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl index 9ae84809f1..edf8950dac 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821403947,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352119275,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498793625,"data":{"content":[{"type":"text","text":"Use the subagent tool exactly once to delegate this subtask to a child agent: 'Reply with exactly the word CHILD_OK and nothing else.' After the subagent returns, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"},"role":"user","id":"a9485ebd-2b4a-434a-bc35-afd757ce141b"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730446685,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"e40b1354-1856-48c3-a638-1be67af32920"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730446685,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"e40b1354-1856-48c3-a638-1be67af32920"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730446685,"data":{"title":"Use the subagent tool exactly","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498793626,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730446686,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 5da6e46877..5016b38b30 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821359466,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783600629542,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498761313,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"},"role":"user","id":"3e25dc34-48e0-4738-8401-1a8d181d37e5"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730415287,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"4b8d9730-0b7b-4e14-8a30-3d852f808f0e"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730415287,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"4b8d9730-0b7b-4e14-8a30-3d852f808f0e"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730415287,"data":{"title":"Reply with exactly the word:","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498761318,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730415288,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/todo-write/session.jsonl b/examples/acp-agent/tests/snapshots/todo-write/session.jsonl index 32a6ab449c..46461efaa1 100644 --- a/examples/acp-agent/tests/snapshots/todo-write/session.jsonl +++ b/examples/acp-agent/tests/snapshots/todo-write/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821376741,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352057657,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498772510,"data":{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"5ecf5e4b-6a18-447d-9341-48f38afdd12e"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730425725,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"8d4ac045-8016-4cec-8b12-91d9459231e1"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730425725,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"8d4ac045-8016-4cec-8b12-91d9459231e1"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730425725,"data":{"title":"Use the todo_write tool to","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498772511,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730425726,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl b/examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl index 15734149cf..c5f2f28f4d 100644 --- a/examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821362944,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783352044773,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498764188,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo SNAPSHOT_OK. Then reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"fe479aa0-1194-40fb-897b-bc7f99b54148"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730417556,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"11ca1551-2073-4990-bf8c-828c614d47a8"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730417556,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"11ca1551-2073-4990-bf8c-828c614d47a8"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730417556,"data":{"title":"Use the bash tool to","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498764190,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730417557,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/web-fetch/session.jsonl b/examples/acp-agent/tests/snapshots/web-fetch/session.jsonl index b15f1a8e00..87c02446d6 100644 --- a/examples/acp-agent/tests/snapshots/web-fetch/session.jsonl +++ b/examples/acp-agent/tests/snapshots/web-fetch/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821381783,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1785078727730,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498776258,"data":{"content":[{"type":"text","text":"Use the web_fetch tool exactly once to fetch http://127.0.0.1:43117/menu.html, then reply with exactly DONE. Do not describe the content."}],"source":{"kind":"user"},"role":"user","id":"7a222307-4336-4772-8a19-aa1b56558e31"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730429237,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"86a43ffd-fecc-482d-806b-54c13a88c9e5"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730429237,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"86a43ffd-fecc-482d-806b-54c13a88c9e5"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730429237,"data":{"title":"Use the web_fetch tool exactly","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498776259,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730429239,"data":{"provider":"deepseek-official","model":"deepseek-v4-pro"}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl index c6fb4f7983..7b77a09f5e 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl @@ -5,7 +5,7 @@ {"type":"subagent/descriptor","seq":3,"time":1785821416542,"data":{"version":2,"mode":"one-shot","provider":"spawn"}} {"type":"step/start","seq":4,"time":1785730457309,"data":{"turn":1,"step":1}} {"type":"user/message","seq":5,"time":1785730457309,"data":{"content":[{"type":"text","text":"Reply with exactly the word WF_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"f0f46771-663a-494a-8d40-6866a5bbe7c9"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1785730457309,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"e076edc0-a2bf-4fc6-aa58-d44bf1e8fd00"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1785730457309,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"e076edc0-a2bf-4fc6-aa58-d44bf1e8fd00"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1785730457309,"data":{"title":"Reply with exactly the word","messageSeqs":[5],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785730457310,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":9,"time":1785730457310,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl index fc488e435f..6ee104dd0c 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821416248,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1783600631839,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498800152,"data":{"content":[{"type":"text","text":"Use the workflow tool exactly once, with args omitted, meta set to { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }, and this EXACT script body (copy it verbatim):\nphase('Run')\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\nreturn { reply }\nAfter the workflow returns, reply with the single word WORKFLOW_DONE and stop. Do not use any other tool."}],"source":{"kind":"user"},"role":"user","id":"5188a9c7-d3ca-4679-b8df-1443e0a0a4df"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730457160,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"1c92c213-1d4f-45ad-be50-161f26a23e65"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730457160,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"1c92c213-1d4f-45ad-be50-161f26a23e65"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730457160,"data":{"title":"Use the workflow tool exactly","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498800153,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730457161,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl b/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl index 21511c2d27..d51a6c820a 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl @@ -5,7 +5,7 @@ {"type":"step/start","seq":3,"time":1785901433981,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498790356,"data":{"content":[{"type":"text","text":"Read nested/task.txt, then read scope/task.txt with the read tool, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"22938d3b-c065-46c8-acb7-18f758285842"},"surfaceOp":"append"} {"type":"user/message","seq":5,"time":1785901433982,"data":{"content":[{"type":"text","text":"\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nRoot snapshot instruction.\n\n"}],"source":{"kind":"workspace-instructions","form":"instructions","baseline":true,"changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2e18766c26603608f321508caae00ea8f4434d59"}]},"role":"user","id":"ec039e95-6864-49ef-ad23-4f65b331dc29"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1785730689193,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"cbea9bd9-3e08-48bf-951f-fe3e5aa4b5d9"},"surfaceOp":"append"} +{"type":"user/message","seq":6,"time":1785730689193,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"cbea9bd9-3e08-48bf-951f-fe3e5aa4b5d9"},"surfaceOp":"append"} {"type":"session/title","seq":7,"time":1785730689193,"data":{"title":"Read nested/task.txt, then read scope mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."}},"required":["command","description"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"ralph","description":"Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.","parameters":{"type":"object","properties":{"objective":{"type":"string","description":"The immutable completion objective for every fresh Ralph round."},"maxRounds":{"type":"number","description":"Optional positive safe-integer round cap, bounded by the deployment ceiling."}},"required":["objective"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"send_message","description":"Send a message to a background subagent by its subagent id, continuing the same conversation. It becomes the subagent's next turn: if it is still working, the message waits until its current turn finishes, so it cannot redirect work already underway. This call returns no answer from the subagent — only confirmation that the message was delivered — so use it to give it more work. A failure means the message was NOT delivered.","parameters":{"type":"object","properties":{"subagent_id":{"type":"string","description":"The subagent id returned when the background subagent was started."},"message":{"type":"string","description":"The message to deliver to the subagent."}},"required":["subagent_id","message"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to start a background subagent that keeps its conversation: you receive only its subagent id, never its result, and it works on its own. Use this for work whose result you do not need returned by this call; `send_message` sends it more work.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."},"run_in_background":{"type":"boolean","description":"Run as a background subagent that keeps its conversation and return only its subagent id. This call never returns its result; send it more work with send_message."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to start a background subagent that keeps its conversation: you receive only its subagent id, never its result, and it works on its own. Use this for work whose result you do not need returned by this call; `send_message` sends it more work.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."},"run_in_background":{"type":"boolean","description":"Run as a background subagent that keeps its conversation and return only its subagent id. This call never returns its result; send it more work with send_message."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"terminal_close","description":"Close one persistent terminal and wait until its captured owned process tree is gone.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."}},"required":["sessionId"]}},{"name":"terminal_list","description":"List persistent terminal sessions owned by the current agent.","parameters":{"type":"object","properties":{}}},{"name":"terminal_open","description":"Create a persistent, owner-isolated terminal session from a registered backend type. Use this for shell or REPL state that must survive across tool calls.","parameters":{"type":"object","properties":{"type":{"type":"string","description":"Registered terminal backend type, usually \"shell\"."},"name":{"type":"string","description":"Optional owner-local display name such as \"main\" or \"gdb\"."},"cwd":{"type":"string","description":"Initial working directory. Defaults to the deployment workspace root."}},"required":["type"]}},{"name":"terminal_read","description":"Read a bounded page of retained output from a persistent terminal without sending input.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"offset":{"type":"number","description":"Newest-relative line offset (default 0)."},"count":{"type":"number","description":"Requested line count (default 500; backend caps apply)."}},"required":["sessionId"]}},{"name":"terminal_send","description":"Send text to a persistent terminal. By default Enter is submitted and the call waits for a prompt, stdin wait, output silence, timeout, or session exit. Background mode returns a task id for task_output/task_kill.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id returned by terminal_open or terminal_list."},"text":{"type":"string","description":"UTF-8 text to write to the terminal."},"submit":{"type":"boolean","description":"Submit Enter after text (default true). Set false for control characters or incomplete REPL input."},"run_in_background":{"type":"boolean","description":"Return a task id immediately; collect with task_output or stop with task_kill."}},"required":["sessionId","text"]}},{"name":"terminal_signal","description":"Send an allowed signal to the current foreground process group of a persistent terminal.","parameters":{"type":"object","properties":{"sessionId":{"type":"string","description":"Terminal session id."},"signal":{"type":"string","description":"Signal to deliver. Shell-targeted SIGKILL is rejected; use terminal_close.","enum":["SIGINT","SIGTERM","SIGKILL","SIGTSTP","SIGHUP"]}},"required":["sessionId","signal"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730504660,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/headless-agent/tests/snapshots/pty-tools/stream-json.expected.jsonl b/examples/headless-agent/tests/snapshots/pty-tools/stream-json.expected.jsonl index 5af477ac6b..2ef42323fb 100644 --- a/examples/headless-agent/tests/snapshots/pty-tools/stream-json.expected.jsonl +++ b/examples/headless-agent/tests/snapshots/pty-tools/stream-json.expected.jsonl @@ -3,7 +3,7 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"agent/inbox/spliced","seq":2,"time":0,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":4,"time":0,"data":{"content":[{"type":"text","text":"Exercise the six PTY tools in order, including one missing-session signal error, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":5,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":5,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":6,"time":0,"data":{"title":"Exercise the six PTY tools","messageSeqs":[4],"source":{"kind":"fallback"}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":7,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/context","seq":8,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}} diff --git a/examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/child.expected.jsonl b/examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/child.expected.jsonl index d1d98988ce..dbcd59cc5a 100644 --- a/examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/child.expected.jsonl +++ b/examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/child.expected.jsonl @@ -6,7 +6,7 @@ {"type":"subagent/descriptor","seq":4,"time":0,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Delegated write probe"}} {"type":"step/start","seq":5,"time":0,"data":{"turn":1,"step":1}} {"type":"user/message","seq":6,"time":0,"data":{"content":[{"type":"text","text":"Use the write tool exactly once with file_path set to exactly the relative path inherited.txt and content escaped. If the write is denied, reply with the single word CHILD_DENIED and the denial marker line; do not retry and do not request escalation. If it succeeds, reply CHILD_WROTE."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} -{"type":"user/message","seq":7,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} +{"type":"user/message","seq":7,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} {"type":"session/title","seq":8,"time":0,"data":{"title":"Use the write tool exactly","messageSeqs":[6],"source":{"kind":"fallback"}}} {"type":"request/header","seq":9,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":10,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/parent.expected.jsonl b/examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/parent.expected.jsonl index 748e69dc28..0bdcc94938 100644 --- a/examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/parent.expected.jsonl +++ b/examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/parent.expected.jsonl @@ -9,7 +9,7 @@ {"type":"agent/inbox/spliced","seq":7,"time":0,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":8,"time":0,"data":{"turn":2,"step":1}} {"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Delegate the write probe to a subagent."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} -{"type":"user/message","seq":10,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} +{"type":"user/message","seq":10,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} {"type":"session/title","seq":11,"time":0,"data":{"title":"Tighten this session to read-only.","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"request/header","seq":12,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":13,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/examples/jsonrpc-agent/tests/snapshots/persistent-tools/notifications.expected.jsonl b/examples/jsonrpc-agent/tests/snapshots/persistent-tools/notifications.expected.jsonl index cbf8b34e75..ea8f220308 100644 --- a/examples/jsonrpc-agent/tests/snapshots/persistent-tools/notifications.expected.jsonl +++ b/examples/jsonrpc-agent/tests/snapshots/persistent-tools/notifications.expected.jsonl @@ -4,7 +4,7 @@ {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"agent/inbox/spliced","seq":2,"time":0,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"user/message","seq":4,"time":0,"data":{"content":[{"type":"text","text":"Prove that bash state persists. Then create {{cwd}}/note.txt with a tab-indented line, view it, replace that literal tab-indented line, and make the persistent shell exit with code 9."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}} -{"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"user/message","seq":5,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}} +{"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"user/message","seq":5,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"session/title","seq":6,"time":0,"data":{"title":"Prove that bash state persists.","messageSeqs":[4],"source":{"kind":"fallback"}}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"request/header","seq":7,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"request/context","seq":8,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}}} diff --git a/examples/jsonrpc-agent/tests/snapshots/persistent-tools/session.jsonl b/examples/jsonrpc-agent/tests/snapshots/persistent-tools/session.jsonl index a436a9e5c2..be559eeb9a 100644 --- a/examples/jsonrpc-agent/tests/snapshots/persistent-tools/session.jsonl +++ b/examples/jsonrpc-agent/tests/snapshots/persistent-tools/session.jsonl @@ -4,7 +4,7 @@ {"type":"agent/inbox/spliced","seq":2,"time":1785821461907,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1785331618312,"data":{"turn":1,"step":1}} {"type":"user/message","seq":4,"time":1785498592368,"data":{"content":[{"type":"text","text":"Prove that bash state persists. Then create {{cwd}}/note.txt with a tab-indented line, view it, replace that literal tab-indented line, and make the persistent shell exit with code 9."}],"source":{"kind":"user"},"role":"user","id":"9a08e199-69d7-4b85-bfa4-27b41a92672a"},"surfaceOp":"append"} -{"type":"user/message","seq":5,"time":1785730508088,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"bb38bdc2-276e-46ec-87a1-089732acbc8d"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1785730508088,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."}]},"role":"user","id":"bb38bdc2-276e-46ec-87a1-089732acbc8d"},"surfaceOp":"append"} {"type":"session/title","seq":6,"time":1785730508088,"data":{"title":"Prove that bash state persists.","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":7,"time":1785498592370,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":8,"time":1785730508089,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index 933df15509..788c086ba6 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -202,7 +202,12 @@ describe('bash tool through the agent loop', () => { expect(pendingNotice.content.some( block => block.type === 'text' && block.text.includes('background task bash-1 (bash: echo bg-ok) finished'), )).toBe(true) - expect(pendingNotice.source).toEqual({ kind: 'plugin', plugin: 'tool-tasks' }) + expect(pendingNotice.source).toEqual({ + kind: 'plugin', + plugin: 'tool-tasks', + form: 'notice', + summary: 'bash echo bg-ok [status: completed, exit code: 0]', + }) // The next turn first admits that notice as user/message, then collects // the output through the generic task tool. diff --git a/packages/client/runtime/src/client/sessions/context-provenance.ts b/packages/client/runtime/src/client/sessions/context-provenance.ts index 95d44a04fd..5d231b6bd8 100644 --- a/packages/client/runtime/src/client/sessions/context-provenance.ts +++ b/packages/client/runtime/src/client/sessions/context-provenance.ts @@ -97,7 +97,7 @@ export function contextProvenance(source: unknown): ContextProvenanceView { * dropping the row, so a log written by a newer or foreign producer still * renders. */ -const KNOWN_FORMS = ['instructions', 'catalog'] as const +const KNOWN_FORMS = ['instructions', 'catalog', 'snapshot', 'notice', 'relay', 'recall'] as const /** One durable context form this UI version knows how to present. */ export type KnownContextForm = typeof KNOWN_FORMS[number] diff --git a/packages/client/runtime/tests/context-provenance.spec.ts b/packages/client/runtime/tests/context-provenance.spec.ts index e4d11f5fe3..11d8931439 100644 Binary files a/packages/client/runtime/tests/context-provenance.spec.ts and b/packages/client/runtime/tests/context-provenance.spec.ts differ diff --git a/packages/client/ui-conversation/src/client/chat/ContextBody.module.css b/packages/client/ui-conversation/src/client/chat/ContextBody.module.css index d204943fea..c1f6f5361b 100644 --- a/packages/client/ui-conversation/src/client/chat/ContextBody.module.css +++ b/packages/client/ui-conversation/src/client/chat/ContextBody.module.css @@ -100,3 +100,62 @@ text-overflow: ellipsis; white-space: nowrap; } + +/* snapshot: one titled block per contributing subsystem. */ +.sections { + display: flex; + flex-direction: column; + gap: 8px; + margin: 0; +} + +.section { + display: flex; + flex-direction: column; + gap: 2px; + min-width: 0; +} + +.sectionName { + color: var(--dsw-alias-label-caption); +} + +.sectionText { + margin: 0; + color: var(--dsw-alias-label-secondary); + white-space: pre-wrap; + overflow-wrap: anywhere; +} + +/* relay: who sent this, above what they said. */ +.relaySender { + margin: 0 0 6px; + color: var(--dsw-alias-label-caption); + overflow-wrap: anywhere; +} + +/* recall: one row per source session, with how much of it survived. */ +.recalls { + display: flex; + flex-direction: column; + gap: 2px; + margin: 0 0 8px; + padding: 0; + list-style: none; +} + +.recall { + display: flex; + gap: 8px; + min-width: 0; +} + +.recallLabel { + color: var(--dsw-alias-label-secondary); + overflow-wrap: anywhere; +} + +.recallCounts { + flex: none; + color: var(--dsw-alias-label-caption); +} diff --git a/packages/client/ui-conversation/src/client/chat/ContextBody.tsx b/packages/client/ui-conversation/src/client/chat/ContextBody.tsx index 1e770af57a..6af65bcdb9 100644 --- a/packages/client/ui-conversation/src/client/chat/ContextBody.tsx +++ b/packages/client/ui-conversation/src/client/chat/ContextBody.tsx @@ -345,31 +345,242 @@ export function CatalogBody({ content, source, t }: { ) } +/** One named contribution to a runtime snapshot, as the durable source records it. */ +interface SnapshotSection { + name: string + text: string +} + +/** Snapshot sections read off the source, or null when the record is unusable. */ +function snapshotSections(source: unknown): SnapshotSection[] | null { + const record = asRecord(source) + const list = record === null ? undefined : record['sections'] + if (!Array.isArray(list)) return null + const sections: SnapshotSection[] = [] + for (const item of list as readonly unknown[]) { + const section = asRecord(item) + if (section === null) return null + const name = section['name'] + const text = section['text'] + if (typeof name !== 'string' || name === '' || typeof text !== 'string') return null + sections.push({ name, text }) + } + return sections.length === 0 ? null : sections +} + +/** + * `snapshot` form: the named contributions this snapshot assembled, in order. + * + * The sections are the same bytes the model read, split at the boundaries the + * producer assembled them on, so a reader sees which subsystem contributed + * which state instead of one undifferentiated wall. + * + * One sentence of the model-facing text is NOT in any section: the producer's + * framing line declaring that this snapshot supersedes earlier ones. Unlike the + * `` wrapper an instruction context carries — which wraps + * content and cannot be separated from it — that line states the form's own + * semantics, so the body states them as a caption instead of reprinting the + * joined prose beside the sections it was split from. + * @param props - Durable content, its source, and the locale seat. + * @returns The snapshot context body, or the opaque body when unreadable. + */ +export function SnapshotBody({ content, source, t }: { + content: ContextMessageNode['content'] + source: unknown + t: Translate +}): ReactNode { + const sections = snapshotSections(source) + /* v8 ignore next -- contextBody reads the sections before choosing this body. */ + if (sections === null) return + return ( + <> +

+ {t('message.context.snapshot.supersedes')} +

+
+ {sections.map((section, index) => ( +
+
{section.name}
+
{boundedText(section.text, t)}
+
+ ))} +
+ + ) +} + +/** + * `notice` form: what just happened, with the model-facing text beneath it. + * + * The one-line account also rides the collapsed row ({@link contextBody}), so a + * notice is usually readable without expanding at all. + * @param props - Durable content, its source, and the locale seat. + * @returns The notice context body. + */ +export function NoticeBody({ content, t }: { + content: ContextMessageNode['content'] + source: unknown + t: Translate +}): ReactNode { + return +} + +/** + * `relay` form: which agent sent this, then what it said. + * + * The sender is an opaque session id; it is shown as provenance rather than a + * label, because this client cannot resolve it to a title. + * @param props - Durable content, its source, and the locale seat. + * @returns The relay context body. + */ +export function RelayBody({ content, source, t }: { + content: ContextMessageNode['content'] + source: unknown + t: Translate +}): ReactNode { + const sender = relaySender(source) + /* v8 ignore next -- contextBody resolves the sender before choosing this body. */ + if (sender === null) return + return ( + <> +

+ {t('message.context.relay.from', { session: sender })} +

+ + + ) +} + +/** The sending agent's session id, or null when the record does not name one. */ +function relaySender(source: unknown): string | null { + const sender = asRecord(source)?.['senderSessionId'] + return typeof sender === 'string' && sender !== '' ? sender : null +} + +/** One recalled session, as the durable source records it. */ +interface RecalledSession { + label: string + retained: number + omitted: number + truncated: boolean +} + +/** Recalled sessions read off the source, or null when the record is unusable. */ +function recalledSessions(source: unknown): RecalledSession[] | null { + const record = asRecord(source) + const list = record === null ? undefined : record['references'] + if (!Array.isArray(list)) return null + const sessions: RecalledSession[] = [] + for (const item of list as readonly unknown[]) { + const reference = asRecord(item) + if (reference === null) return null + const label = reference['label'] + const retained = reference['retainedMessages'] + const omitted = reference['omittedMessages'] + const truncated = reference['truncated'] + // Completeness is the fact this card exists to report, so a reference that + // cannot state it is not a readable recall — showing the label alone would + // present a confident card over unknown loss. + if (typeof label !== 'string' || label === '' + || typeof retained !== 'number' || typeof omitted !== 'number' + || typeof truncated !== 'boolean') return null + sessions.push({ label, retained, omitted, truncated }) + } + return sessions.length === 0 ? null : sessions +} + +/** + * `recall` form: which sessions this material came from and how much of each + * survived the read, then the material itself. + * + * Completeness is the fact a reader needs first: recalled context is bounded on + * the way in, so a card that hid the omitted count would overstate what the + * model received. + * @param props - Durable content, its source, and the locale seat. + * @returns The recall context body, or the opaque body when unreadable. + */ +export function RecallBody({ content, source, t }: { + content: ContextMessageNode['content'] + source: unknown + t: Translate +}): ReactNode { + const sessions = recalledSessions(source) + if (sessions === null) return + return ( + <> +
    + {sessions.map((session, index) => ( +
  • + {session.label} + + {t('message.context.recall.counts', { + retained: session.retained, + omitted: session.omitted, + })} + + {session.truncated && ( + {t('message.context.recall.truncated')} + )} +
    • + ))} +
+ + + ) +} + +/** The one-line account a `notice` puts on its collapsed row, when it records one. */ +function noticeSummary(source: unknown): string | null { + const summary = asRecord(source)?.['summary'] + return typeof summary === 'string' && summary !== '' ? summary : null +} + /** * Choose the body for one context node. * * Returns the form the body actually rendered as, which is not always the * declared one: a declared form whose fields are unreadable falls back to * opaque, and the caller labels the row with what it really shows. + * `summary` is the collapsed row's one-line account, which only a `notice` + * records: its whole point is being readable without expanding. * @param form - the producer-declared form projected onto the node. * @param props - durable content, its source, and the locale seat. - * @returns the rendered form (null for opaque) and its body. + * @returns the rendered form (null for opaque), its collapsed summary, and its body. */ export function contextBody( form: ContextMessageNode['form'], props: { content: ContextMessageNode['content']; source: unknown; t: Translate }, -): { rendered: KnownContextForm | null; body: ReactNode } { +): { rendered: KnownContextForm | null; summary: string | null; body: ReactNode } { + const opaque = { rendered: null, summary: null, body: } switch (form) { case 'instructions': return instructionChanges(props.source) === null - ? { rendered: null, body: } - : { rendered: 'instructions', body: } + ? opaque + : { rendered: 'instructions', summary: null, body: } case 'catalog': return catalogEntries(props.source) === null - ? { rendered: null, body: } - : { rendered: 'catalog', body: } + ? opaque + : { rendered: 'catalog', summary: null, body: } + case 'snapshot': + return snapshotSections(props.source) === null + ? opaque + : { rendered: 'snapshot', summary: null, body: } + case 'notice': { + const summary = noticeSummary(props.source) + return summary === null + ? opaque + : { rendered: 'notice', summary, body: } + } + case 'relay': + return relaySender(props.source) === null + ? opaque + : { rendered: 'relay', summary: null, body: } + case 'recall': + return recalledSessions(props.source) === null + ? opaque + : { rendered: 'recall', summary: null, body: } case null: - return { rendered: null, body: } + return opaque /* v8 ignore next 4 -- closed-union backstop; the compiler rejects a new KnownContextForm here rather than letting it degrade to opaque silently. */ default: { diff --git a/packages/client/ui-conversation/src/client/chat/ContextInjectionRow.module.css b/packages/client/ui-conversation/src/client/chat/ContextInjectionRow.module.css index 3e8a10b658..e72bd594a2 100644 --- a/packages/client/ui-conversation/src/client/chat/ContextInjectionRow.module.css +++ b/packages/client/ui-conversation/src/client/chat/ContextInjectionRow.module.css @@ -24,6 +24,18 @@ } .source { + flex: none; + min-width: 0; + overflow: hidden; + color: var(--dsw-alias-label-tertiary); + font-size: 14px; + line-height: 24px; + text-overflow: ellipsis; + white-space: nowrap; +} + +/* A notice's one-line account: the reason it rarely needs expanding. */ +.summary { flex: 1 1 auto; min-width: 0; overflow: hidden; diff --git a/packages/client/ui-conversation/src/client/chat/ContextInjectionRow.tsx b/packages/client/ui-conversation/src/client/chat/ContextInjectionRow.tsx index 2c561c96de..6cfc1eebfb 100644 --- a/packages/client/ui-conversation/src/client/chat/ContextInjectionRow.tsx +++ b/packages/client/ui-conversation/src/client/chat/ContextInjectionRow.tsx @@ -33,7 +33,7 @@ export function ContextInjectionRow({ content, source, provenance, form, t }: Co const [open, setOpen] = useState(false) // Resolved rather than declared: a form whose fields are unreadable renders // the opaque body, and the marker must say what the row actually shows. - const { rendered, body } = contextBody(form, { content, source, t }) + const { rendered, summary, body } = contextBody(form, { content, source, t }) return ( {provenance.label} + {summary !== null && ( + <> + + {summary} + + )} )} keepContentWhenOpen diff --git a/packages/client/ui-conversation/src/client/locales.ts b/packages/client/ui-conversation/src/client/locales.ts index 39a013b3e2..0147cd3315 100644 --- a/packages/client/ui-conversation/src/client/locales.ts +++ b/packages/client/ui-conversation/src/client/locales.ts @@ -73,6 +73,10 @@ export const zh = { 'message.context.instructions.removed': '已移除', 'message.context.catalog.replaced': '替换目录', 'message.context.catalog.more': '…还有 {count} 条', + 'message.context.snapshot.supersedes': '取代先前的快照', + 'message.context.relay.from': '来自会话 {session}', + 'message.context.recall.counts': '保留 {retained} 条 · 省略 {omitted} 条', + 'message.context.recall.truncated': '已截断', 'message.steering': '插话', 'message.compaction': '上下文已压缩', 'message.compaction.expand': '点击查看压缩摘要', @@ -208,6 +212,10 @@ export const en = { 'message.context.instructions.removed': 'removed', 'message.context.catalog.replaced': 'Replacement catalog', 'message.context.catalog.more': '… {count} more', + 'message.context.snapshot.supersedes': 'Supersedes earlier snapshots', + 'message.context.relay.from': 'From session {session}', + 'message.context.recall.counts': '{retained} kept · {omitted} omitted', + 'message.context.recall.truncated': 'truncated', 'message.steering': 'Interjection', 'message.compaction': 'Context compacted', 'message.compaction.expand': 'View compaction summary', diff --git a/packages/client/ui-conversation/tests/chat-branch-tails.spec.tsx b/packages/client/ui-conversation/tests/chat-branch-tails.spec.tsx index 4f9a452e3c..53793f86c2 100644 --- a/packages/client/ui-conversation/tests/chat-branch-tails.spec.tsx +++ b/packages/client/ui-conversation/tests/chat-branch-tails.spec.tsx @@ -571,6 +571,145 @@ describe('MessageItem arms', () => { expect(fields).toEqual(['plugin', 'form']) }) + it('the snapshot form attributes each part to the subsystem that produced it', () => { + const view = render( + , + ) + fireEvent.click(view.getByRole('button', { name: /^上下文注入\s*@deepseek-ai\/dsh-system-prompt$/ })) + const rows = [...view.container.querySelectorAll('[data-context-sections] div')].map(node => node.textContent) + expect(rows).toEqual(['sandbox:policyworkspace-write', 'workspace/repo']) + }) + + it('a notice puts its account on the collapsed row', () => { + // The whole point of the form: readable without expanding. + const view = render( + , + ) + expect(view.container.querySelector('[data-context-summary]')?.textContent) + .toBe('bash pnpm test [status: completed]') + expect(view.container.querySelector('[data-context-injection-body]')).toBeNull() + }) + + it('a notice without its account falls back to the opaque body', () => { + const view = render( + , + ) + expect(view.container.querySelector('[data-context-summary]')).toBeNull() + fireEvent.click(view.getByRole('button', { name: /^上下文注入\s*tool-tasks$/ })) + expect(view.container.querySelector('[data-context-fields]')).not.toBeNull() + }) + + it('each form falls back to the opaque body when its required facts are unreadable', () => { + // The fallback chain is the load-bearing wall: every dedicated form must + // reach it, and the row marker must not claim a form that did not render. + const cases = [ + { form: 'snapshot', source: { kind: 'plugin', form: 'snapshot', sections: 'not-a-list' }, label: 'plugin' }, + { form: 'relay', source: { kind: 'subagent-report', form: 'relay' }, label: 'subagent-report' }, + { form: 'recall', source: { kind: 'session-reference', form: 'recall', references: [{ label: 'x' }] }, label: 'session-reference' }, + ] as const + for (const { form, source, label } of cases) { + cleanup() + const view = render( + , + ) + fireEvent.click(view.getByRole('button', { name: new RegExp(`^上下文注入\\s*${label}$`) })) + expect(view.container.querySelector('[data-context-text]')?.textContent).toBe(`${form} prose`) + expect(view.container.querySelector('[data-context-injection-body]')?.getAttribute('data-context-form')) + .toBeNull() + } + }) + + it('a snapshot states the supersession its framing line carries', () => { + const view = render( + , + ) + fireEvent.click(view.getByRole('button', { name: /^上下文注入\s*plugin$/ })) + expect(view.container.querySelector('[data-context-snapshot-supersedes]')?.textContent) + .toBe('取代先前的快照') + }) + + it('a relay names the agent that sent it above what it said', () => { + const view = render( + , + ) + fireEvent.click(view.getByRole('button', { name: /^上下文注入\s*subagent-report$/ })) + expect(view.container.querySelector('[data-context-relay-sender]')?.textContent).toBe('来自会话 child-7') + expect(view.container.querySelector('[data-context-text]')?.textContent).toBe('child report body') + }) + + it('a recall reports how much of each source session survived the read', () => { + // Recalled context is bounded on the way in, so hiding the omitted count + // would overstate what the model received. + const view = render( + , + ) + fireEvent.click(view.getByRole('button', { name: /^跨会话召回\s*重构 loader, 修 CI$/ })) + const rows = [...view.container.querySelectorAll('[data-context-recalls] li')].map(node => node.textContent) + expect(rows).toEqual(['重构 loader保留 18 条 · 省略 42 条已截断', '修 CI保留 3 条 · 省略 0 条']) + expect(view.container.querySelector('[data-context-text]')?.textContent).toBe('recalled material') + }) + it('unknown nodes retain the generic JSON row', () => { const unknownView = render( , diff --git a/packages/context/session-reference/src/index.ts b/packages/context/session-reference/src/index.ts index d368c2e1e5..01a6965027 100644 --- a/packages/context/session-reference/src/index.ts +++ b/packages/context/session-reference/src/index.ts @@ -199,6 +199,7 @@ export class SessionReferenceService extends Service { const prompt = renderPrompt(rendered.map(source => source.data)) const source: SessionReferenceSource = { kind: 'session-reference', + form: 'recall', version: 1, references: rendered.map((source, index) => ({ sessionId: source.data.sessionId, diff --git a/packages/context/session-reference/src/types.ts b/packages/context/session-reference/src/types.ts index 78df17058d..0693e0d212 100644 --- a/packages/context/session-reference/src/types.ts +++ b/packages/context/session-reference/src/types.ts @@ -6,6 +6,8 @@ import type { SessionId, UserMessage } from '@deepseek-ai/dsh-session' /** Durable provenance for one prepared cross-session context. */ export interface SessionReferenceSource { kind: 'session-reference' + /** Material lifted out of another session's log (`recall` context form). */ + form: 'recall' version: 1 references: { sessionId: string diff --git a/packages/context/time-context/src/index.ts b/packages/context/time-context/src/index.ts index ff939219aa..4cc9e5de9c 100644 --- a/packages/context/time-context/src/index.ts +++ b/packages/context/time-context/src/index.ts @@ -174,13 +174,14 @@ export function apply(ctx: Context, config: Config): void { const previous = step === 1 ? precedingMessageTime(agent) : precedingStepContextTime(agent, turn) + const text = renderText(now, turn, step, previous, formatter, resolvedTimeZone) return { kind: 'enter', messages: [ ...decision.messages, createUserMessage({ - content: [{ type: 'text', text: renderText(now, turn, step, previous, formatter, resolvedTimeZone) }], - source: { kind: 'plugin', plugin: name }, + content: [{ type: 'text', text }], + source: { kind: 'plugin', plugin: name, form: 'snapshot', sections: [{ name, text }] }, }), ], } diff --git a/packages/context/time-context/tests/time-context.e2e.ts b/packages/context/time-context/tests/time-context.e2e.ts index a4aa6bc3a2..33d63cf843 100644 --- a/packages/context/time-context/tests/time-context.e2e.ts +++ b/packages/context/time-context/tests/time-context.e2e.ts @@ -56,7 +56,14 @@ describe('time-context through a real headless cordis.yml', () => { for (let index = 0; index < contexts.length; index += 1) { expect(contexts[index]!.seq).toBeGreaterThan(starts[index]!.seq) expect(contexts[index]!.surfaceOp).toBe('append') - expect(contexts[index]!.data.source).toEqual({ kind: 'plugin', plugin: 'time-context' }) + // `snapshot` form: one named contribution whose text is exactly what the + // model read, so a consumer attributes it without re-splitting prose. + expect(contexts[index]!.data.source).toMatchObject({ + kind: 'plugin', + plugin: 'time-context', + form: 'snapshot', + sections: [{ name: 'time-context' }], + }) } const contextText = contexts.map(event => event.data.content .filter(block => block.type === 'text') diff --git a/packages/context/time-context/tests/time-context.spec.ts b/packages/context/time-context/tests/time-context.spec.ts index 1b85595bb9..94228bbc9f 100644 --- a/packages/context/time-context/tests/time-context.spec.ts +++ b/packages/context/time-context/tests/time-context.spec.ts @@ -161,7 +161,19 @@ describe('durable step context', () => { const event = session.events.at(-1) expect(event?.type).toBe('user/message') if (event?.type !== 'user/message') throw new Error('missing time context') - expect(event.data.source).toEqual({ kind: 'plugin', plugin: 'time-context' }) + // The reading is a `snapshot`-form context: one named contribution whose + // text is exactly what the model read, so a consumer attributes it without + // re-splitting prose. + expect(event.data.source).toEqual({ + kind: 'plugin', + plugin: 'time-context', + form: 'snapshot', + sections: [{ + name: 'time-context', + text: 'Time sampled while preparing turn 1, step 1: 2026-07-15T09:01:01+08:00[Asia/Shanghai]\n' + + 'Elapsed since the preceding model-visible message: 1d 1h 1m 1s.', + }], + }) expect(event.surfaceOp).toBe('append') }) diff --git a/packages/context/tmux-context/src/index.ts b/packages/context/tmux-context/src/index.ts index 130efb919b..ff9243416e 100644 --- a/packages/context/tmux-context/src/index.ts +++ b/packages/context/tmux-context/src/index.ts @@ -234,12 +234,13 @@ export function apply(ctx: Context, config: Config): void { if (location === undefined) return decision const state = renderState(location) if (previous !== undefined && previous.state === state) return decision + const text = renderReading(location, turn) return { kind: 'enter', messages: [ createUserMessage({ - content: [{ type: 'text', text: renderReading(location, turn) }], - source: { kind: 'plugin', plugin: name }, + content: [{ type: 'text', text }], + source: { kind: 'plugin', plugin: name, form: 'snapshot', sections: [{ name, text }] }, }), ...decision.messages, ], diff --git a/packages/context/tmux-context/tests/tmux-context.spec.ts b/packages/context/tmux-context/tests/tmux-context.spec.ts index e7b501d462..d7e4a0a7fb 100644 --- a/packages/context/tmux-context/tests/tmux-context.spec.ts +++ b/packages/context/tmux-context/tests/tmux-context.spec.ts @@ -170,7 +170,14 @@ describe('tmux-context injection', () => { ]) const event = session.events.at(-1) if (event?.type !== 'user/message') throw new Error('missing tmux context') - expect(event.data.source).toEqual({ kind: 'plugin', plugin: 'tmux-context' }) + // `snapshot` form: one named contribution carrying exactly the reading the + // model saw, so a consumer attributes it without re-splitting prose. + expect(event.data.source).toMatchObject({ + kind: 'plugin', + plugin: 'tmux-context', + form: 'snapshot', + sections: [{ name: 'tmux-context' }], + }) expect(event.surfaceOp).toBe('append') }) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 9a807f3234..d41da6ac9d 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -1794,12 +1794,12 @@ export const TYPE_API: readonly TypeApiEntry[] = [ declaration: 'export type ContentBlockType = keyof ContentBlockMap;', }, { - name: 'ContextForm', - declaration: 'export type ContextForm = \'instructions\' | \'catalog\';', + name: 'ContextFormed', + declaration: 'export type ContextFormed = {\n readonly form?: never;\n} | {\n readonly form: \'instructions\';\n} | {\n readonly form: \'catalog\';\n} | {\n readonly form: \'snapshot\';\n readonly sections: readonly ContextSnapshotSection[];\n} | {\n readonly form: \'notice\';\n readonly summary: string;\n} | {\n readonly form: \'relay\';\n} | {\n readonly form: \'recall\';\n};', }, { - name: 'ContextFormed', - declaration: 'export interface ContextFormed {\n readonly form?: ContextForm;\n}', + name: 'ContextSnapshotSection', + declaration: 'export interface ContextSnapshotSection {\n readonly name: string;\n readonly text: string;\n}', }, { name: 'ContinuableCreateRequest', diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index 1931d6efb0..2b97dad3a4 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -27,7 +27,7 @@ import type { Scope } from '@deepseek-ai/dsh-scope' import { createScope } from '@deepseek-ai/dsh-scope' import type { EpochHeader, RequestContext, Session, SessionId, TurnEndReason, UserMessage } from '@deepseek-ai/dsh-session' import { canonicalHeader, headerEquals } from '@deepseek-ai/dsh-session' -import { renderContextSnapshot, renderPrompt } from '@deepseek-ai/dsh-system-prompt' +import { joinContextSections, renderContextSections, renderPrompt } from '@deepseek-ai/dsh-system-prompt' import type { PromptAssembly } from '@deepseek-ai/dsh-system-prompt' import type { Context } from 'cordis' import { RuntimeContextProjection } from './runtime-context.ts' @@ -202,7 +202,8 @@ export class ReactLoopAgent implements Agent { const claimed = this.inbox.claim(target, position.turn) const assembly = await this.loopCtx.systemPrompt.assemble(assembleContextFor(this, signal)) signal.throwIfAborted() - const context = this.runtimeContext.project(renderContextSnapshot(assembly)) + const sections = renderContextSections(assembly) + const context = this.runtimeContext.project(joinContextSections(sections), sections) const decision = await agentEvents(this.loopCtx, this).waterfall( 'agent/pre-step', claimed, { ...position, signal }, () => Promise.resolve({ diff --git a/packages/core/agent-loop/src/runtime-context.ts b/packages/core/agent-loop/src/runtime-context.ts index 26c33a18c5..8cf4a41403 100644 --- a/packages/core/agent-loop/src/runtime-context.ts +++ b/packages/core/agent-loop/src/runtime-context.ts @@ -4,6 +4,7 @@ */ import { createUserMessage } from '@deepseek-ai/dsh-llm' +import type { ContextSnapshotSection } from '@deepseek-ai/dsh-llm' import type { Session, UserMessage } from '@deepseek-ai/dsh-session' import { isReplacementSurfaceEvent } from '@deepseek-ai/dsh-session' import type { Context } from 'cordis' @@ -57,15 +58,19 @@ export class RuntimeContextProjection { /** * Create an uncommitted snapshot only when the retained value differs. * @param current - fully rendered dynamic context. + * @param sections - named contributions that formed the current snapshot. * @returns a candidate user message, or `undefined` when no update is needed. */ - project(current: string): UserMessage | undefined { + project(current: string, sections: readonly ContextSnapshotSection[]): UserMessage | undefined { if (this.retained === undefined && current.length === 0) return const snapshot = current.length === 0 ? CLEARED : current if (this.retained?.text === snapshot) return return createUserMessage({ content: [{ type: 'text', text: snapshot }], - source: { kind: 'plugin', plugin: SOURCE }, + // The cleared marker has no contributions left to attribute. + source: sections.length === 0 + ? { kind: 'plugin', plugin: SOURCE } + : { kind: 'plugin', plugin: SOURCE, form: 'snapshot', sections }, }) } } diff --git a/packages/core/agent-loop/tests/runtime-context.spec.ts b/packages/core/agent-loop/tests/runtime-context.spec.ts index ed524a9e4b..463515a61b 100644 --- a/packages/core/agent-loop/tests/runtime-context.spec.ts +++ b/packages/core/agent-loop/tests/runtime-context.spec.ts @@ -30,10 +30,16 @@ describe('RuntimeContextProjection', () => { const projection = new RuntimeContextProjection(ctx, session) expect(session.surface.nodes).toContain(retained.seq) - expect(projection.project('retained')).toBeUndefined() + expect(projection.project('retained', [])).toBeUndefined() + expect(projection.project('next', [{ name: 'sandbox:policy', text: 'policy' }])?.source).toEqual({ + kind: 'plugin', + plugin: SOURCE, + form: 'snapshot', + sections: [{ name: 'sandbox:policy', text: 'policy' }], + }) const other = ctx.sessions.create(SessionId('runtime-context-other')) other.append('user/message', contextMessage('other'), { surfaceOp: 'append' }) - expect(projection.project('retained')).toBeUndefined() + expect(projection.project('retained', [])).toBeUndefined() }) }) diff --git a/packages/core/system-prompt/src/index.ts b/packages/core/system-prompt/src/index.ts index cb191bcada..16fc1394fa 100644 --- a/packages/core/system-prompt/src/index.ts +++ b/packages/core/system-prompt/src/index.ts @@ -8,7 +8,7 @@ import { Context, Service } from 'cordis' import z from 'schemastery' import { AnonymousEntries, NamedEntries, ScopedLayers, scopeTarget } from '@deepseek-ai/dsh-scope' import type { ScopeKey, ScopeLayer, Scoped } from '@deepseek-ai/dsh-scope' -import type { ToolSchema } from '@deepseek-ai/dsh-llm' +import type { ContextSnapshotSection, ToolSchema } from '@deepseek-ai/dsh-llm' declare module 'cordis' { interface Context { @@ -200,15 +200,39 @@ export function renderPrompt(assembly: PromptAssembly): string { * @returns the current full snapshot, or `''` when no context is active. */ export function renderContextSnapshot(assembly: PromptAssembly): string { - const body = assembly.contexts - .map(context => interpolate(context, assembly.variables, 'context')) - .filter(text => text.length > 0) - .join('\n\n') + return joinContextSections(renderContextSections(assembly)) +} + +/** + * The model-facing snapshot text for an already-rendered section list. + * + * A caller that also needs the sections renders them once and joins here, so a + * request does not interpolate every context twice. + * @param sections - sections from {@link renderContextSections}. + * @returns the current full snapshot, or `''` when no context is active. + */ +export function joinContextSections(sections: readonly ContextSnapshotSection[]): string { + const body = sections.map(section => section.text).join('\n\n') if (body.length === 0) return '' return `Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\n${body}` } -/** Interpolate one section or context and attribute diagnostics to its owner. */ +/** + * The same snapshot, kept as the named contributions it was assembled from. + * + * {@link renderContextSnapshot} joins these for the model; a consumer that + * presents the snapshot uses them to attribute each part to the subsystem that + * contributed it, without re-splitting the joined prose. + * @param assembly - the assembly whose contexts and variables to render. + * @returns one entry per contributing context that rendered to non-empty text. + */ +export function renderContextSections(assembly: PromptAssembly): ContextSnapshotSection[] { + return assembly.contexts + .map(context => ({ name: context.name, text: interpolate(context, assembly.variables, 'context') })) + .filter(section => section.text.length > 0) +} + +/** Interpolate one section or context and attribute diagnostics to its owning input. */ function interpolate( input: AssembledSection | AssembledContext, variables: Record, diff --git a/packages/goal/tool-goal/src/index.ts b/packages/goal/tool-goal/src/index.ts index 9ceed21bc9..d22ff26dc2 100644 --- a/packages/goal/tool-goal/src/index.ts +++ b/packages/goal/tool-goal/src/index.ts @@ -8,7 +8,7 @@ import type { Context } from 'cordis' import z from 'schemastery' import { GoalId } from '@deepseek-ai/dsh-goal' import type { GoalRef, GoalView } from '@deepseek-ai/dsh-goal' -import { createUserMessage, HarnessError } from '@deepseek-ai/dsh-llm' +import { boundContextSummary, createUserMessage, HarnessError } from '@deepseek-ai/dsh-llm' import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView } from '@deepseek-ai/dsh-tools' import type {} from '@deepseek-ai/dsh-system-prompt' @@ -315,7 +315,12 @@ export function apply(ctx: Context, config: Config): void { content: args.action === 'complete' ? renderWrapupContext(goal.objective) : renderWrapupContext(goal.objective, args.blocked_reason as string), - source: { kind: 'plugin', plugin: 'tool-goal' }, + source: { + kind: 'plugin', + plugin: 'tool-goal', + form: 'notice', + summary: boundContextSummary(`${args.action as string}: ${goal.objective}`), + }, })) } return Promise.resolve(goalValue(goal)) diff --git a/packages/goal/tool-goal/tests/tool-goal.spec.ts b/packages/goal/tool-goal/tests/tool-goal.spec.ts index 3b1e892ec5..c9e3ade8fe 100644 --- a/packages/goal/tool-goal/tests/tool-goal.spec.ts +++ b/packages/goal/tool-goal/tests/tool-goal.spec.ts @@ -374,7 +374,12 @@ describe('goal tool state transitions', () => { expect(complete.concludesTurn).toBeUndefined() const contexts = complete.additionalContexts ?? [] expect(contexts).toHaveLength(1) - expect(contexts[0]?.source).toEqual({ kind: 'plugin', plugin: 'tool-goal' }) + expect(contexts[0]?.source).toEqual({ + kind: 'plugin', + plugin: 'tool-goal', + form: 'notice', + summary: 'complete: pause cleanly', + }) const block = contexts[0]?.content[0] if (block?.type !== 'text') throw new Error('expected one text wrap-up block') expect(block.text).toContain('') diff --git a/packages/guard/repeat-tool-guard/src/index.ts b/packages/guard/repeat-tool-guard/src/index.ts index d58d4f0528..f07d59e417 100644 --- a/packages/guard/repeat-tool-guard/src/index.ts +++ b/packages/guard/repeat-tool-guard/src/index.ts @@ -200,7 +200,10 @@ export function apply(ctx: Context, config: Config): void { const text = count === thresholds[0] ? GENTLE_REMINDER : detailedReminder(exec.name, count, previewArguments(canonical, argumentsPreviewChars)) - return createUserMessage({ content: [{ type: 'text', text }], source: PLUGIN_SOURCE }) + return createUserMessage({ + content: [{ type: 'text', text }], + source: { ...PLUGIN_SOURCE, form: 'notice', summary: `${exec.name} × ${count}` }, + }) } // Observe-and-enrich, never veto: count first (state advances regardless of diff --git a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts index a7c31a2a09..d6858f6d1a 100644 --- a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts +++ b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts @@ -45,7 +45,14 @@ function reminders(agent: Agent): { text: string; source: unknown }[] { })) } -const GUARD_SOURCE = { kind: 'plugin', plugin: 'repeat-tool-guard' } +// The reminder is a `notice`-form context; its summary names the repeated +// call so a reader sees it without expanding the row. +const guardSource = (tool: string, count: number) => ({ + kind: 'plugin', + plugin: 'repeat-tool-guard', + form: 'notice', + summary: `${tool} × ${count}`, +}) describe('threshold escalation', () => { it('reminds gently at the first default threshold (3) and in detail at the second (5)', async () => { @@ -62,11 +69,11 @@ describe('threshold escalation', () => { const found = reminders(agent) expect(found).toHaveLength(2) expect(found[0]!.text).toContain('repeating the exact same tool call') - expect(found[0]!.source).toEqual(GUARD_SOURCE) + expect(found[0]!.source).toEqual(guardSource('probe', 3)) expect(found[1]!.text).toContain('consecutive_calls: 5') expect(found[1]!.text).toContain('- tool: probe') expect(found[1]!.text).toContain('{"q":"same"}') - expect(found[1]!.source).toEqual(GUARD_SOURCE) + expect(found[1]!.source).toEqual(guardSource('probe', 5)) }) it('keys the gentle text to thresholds[0], not the literal 3', async () => { @@ -327,7 +334,7 @@ describe('fold onto the downstream decision', () => { expect(found[0]!.text).toBe('downstream-ctx') expect(found[0]!.source).toEqual({ kind: 'plugin', plugin: 'test' }) expect(found[1]!.text).toContain('repeating the exact same tool call') - expect(found[1]!.source).toEqual(GUARD_SOURCE) + expect(found[1]!.source).toEqual(guardSource('probe', 2)) expect(found[2]).toEqual({ text: 'downstream-ctx', source: { kind: 'plugin', plugin: 'test' } }) // The block's feedback reached the tool result unchanged. const results = [...agent.session.events].filter((e): e is SessionEvent<'tool/result'> => e.type === 'tool/result') diff --git a/packages/llm/llm/src/message.ts b/packages/llm/llm/src/message.ts index d44a501a60..7db1f855a8 100644 --- a/packages/llm/llm/src/message.ts +++ b/packages/llm/llm/src/message.ts @@ -50,12 +50,49 @@ export type ContextForm = | 'instructions' /** A catalog of items available in this session, republished as it changes. */ | 'catalog' + /** Current state, where a later snapshot from the same producer supersedes an earlier one. */ + | 'snapshot' + /** A one-off account of something that just happened; it supersedes nothing. */ + | 'notice' + /** A message another agent addressed to this one. */ + | 'relay' + /** Material lifted out of another session's log, possibly reduced on the way in. */ + | 'recall' -/** Optional producer-declared {@link ContextForm}, mixed into the source shapes that carry one. */ -export interface ContextFormed { - readonly form?: ContextForm +/** One named contribution to a `snapshot`-form context, in assembly order. */ +export interface ContextSnapshotSection { + /** The contributing subsystem's name. */ + readonly name: string + /** That contribution's model-facing text, exactly as assembled. */ + readonly text: string } +/** + * Producer-declared {@link ContextForm} and the fields that form requires, + * mixed into the source shapes that carry one. + * + * Discriminated by `form` so a producer cannot declare a shape without the + * facts that shape is presented from: a `notice` must record its one-line + * account, a `snapshot` its sections. Omitting `form` stays valid — an + * undeclared context is the documented default. + */ +export type ContextFormed = + | { readonly form?: never } + | { readonly form: 'instructions' } + | { readonly form: 'catalog' } + | { + readonly form: 'snapshot' + /** The named contributions this snapshot assembled, in order. */ + readonly sections: readonly ContextSnapshotSection[] + } + | { + readonly form: 'notice' + /** One-line account of what happened, shown without expanding the row. */ + readonly summary: string + } + | { readonly form: 'relay' } + | { readonly form: 'recall' } + /** * Where a message (or injected content) came from. * Merge-extensible sum type — plugins add their own `kind`s. @@ -67,6 +104,24 @@ export interface MessageSourceMap { tool: ToolMessageSource } +/** + * Bound for a `notice` summary. The account rides a collapsed transcript row + * and is committed to the durable log, while its inputs — task labels, goal + * objectives, tool arguments — are caller text with no length of their own. + */ +export const CONTEXT_SUMMARY_MAX_CHARS = 120 + +/** + * Bound one `notice` summary to {@link CONTEXT_SUMMARY_MAX_CHARS}. + * @param summary - the producer's one-line account, of any length. + * @returns the account, ellipsized when it exceeds the bound. + */ +export function boundContextSummary(summary: string): string { + return summary.length <= CONTEXT_SUMMARY_MAX_CHARS + ? summary + : `${summary.slice(0, CONTEXT_SUMMARY_MAX_CHARS - 1)}…` +} + /** Any known message source, derived from {@link MessageSourceMap}; switch on `kind` and fall through unknowns (merge-extensible). */ export type MessageSource = MessageSourceMap[keyof MessageSourceMap] diff --git a/packages/plan/plan-mode/src/index.ts b/packages/plan/plan-mode/src/index.ts index 835b4b9036..75b8ffd36b 100644 --- a/packages/plan/plan-mode/src/index.ts +++ b/packages/plan/plan-mode/src/index.ts @@ -464,7 +464,8 @@ export class PlanModeService extends Service { : 'The user switched this session back to the default mode.' return createUserMessage({ content: [{ type: 'text', text }], - source: { kind: 'plugin', plugin: 'plan-mode' }, + // The narration is already one sentence, so it is its own summary. + source: { kind: 'plugin', plugin: 'plan-mode', form: 'notice', summary: text }, }) } } diff --git a/packages/subagent/subagent/src/continuation.ts b/packages/subagent/subagent/src/continuation.ts index 3644180056..4b038871a1 100644 --- a/packages/subagent/subagent/src/continuation.ts +++ b/packages/subagent/subagent/src/continuation.ts @@ -47,6 +47,8 @@ import type SubagentActivationSetupRegistry from './activation-setup-registry.ts /** Attribution for a model coordinator's follow-up to one of its children. */ export interface CoordinatorMessageSource { readonly kind: 'coordinator' + /** A message another agent addressed to this one (`relay` context form). */ + readonly form: 'relay' /** Session id of the agent whose tool call produced the follow-up. */ readonly senderSessionId: SessionId } @@ -54,6 +56,8 @@ export interface CoordinatorMessageSource { /** Durable attribution for a continuable child's explicit parent report. */ export interface SubagentReportMessageSource { readonly kind: 'subagent-report' + /** A message another agent addressed to this one (`relay` context form). */ + readonly form: 'relay' /** Session id of the reporting child. */ readonly senderSessionId: SessionId } @@ -481,6 +485,7 @@ export class SubagentContinuationManager { ], source: { kind: 'subagent-report' as const, + form: 'relay' as const, senderSessionId: activation.childId, }, }) diff --git a/packages/subagent/tool-subagent-control/src/index.ts b/packages/subagent/tool-subagent-control/src/index.ts index 5406a4dcc4..95cf4e4183 100644 --- a/packages/subagent/tool-subagent-control/src/index.ts +++ b/packages/subagent/tool-subagent-control/src/index.ts @@ -66,7 +66,7 @@ export function apply(ctx: Context): void { SessionId(args.subagent_id), message, { - source: { kind: 'coordinator', senderSessionId: parent.id }, + source: { kind: 'coordinator', form: 'relay', senderSessionId: parent.id }, signal: exec.signal, }, ) diff --git a/packages/subagent/tool-subagent-control/tests/tool-subagent-control.spec.ts b/packages/subagent/tool-subagent-control/tests/tool-subagent-control.spec.ts index bc8d2aa5fd..302e053abe 100644 --- a/packages/subagent/tool-subagent-control/tests/tool-subagent-control.spec.ts +++ b/packages/subagent/tool-subagent-control/tests/tool-subagent-control.spec.ts @@ -102,6 +102,7 @@ describe('dsh-tool-subagent-control', () => { // Durable provenance records the calling agent without granting authority. expect(followUp?.type === 'user/message' && followUp.data.source).toEqual({ kind: 'coordinator', + form: 'relay', senderSessionId: parent.id, }) }) diff --git a/packages/tasks/tool-tasks/src/index.ts b/packages/tasks/tool-tasks/src/index.ts index 5a907de989..5372fffdb2 100644 --- a/packages/tasks/tool-tasks/src/index.ts +++ b/packages/tasks/tool-tasks/src/index.ts @@ -8,7 +8,7 @@ import type { Context } from 'cordis' import z from 'schemastery' -import { createUserMessage, type ContentBlock } from '@deepseek-ai/dsh-llm' +import { boundContextSummary, createUserMessage, type ContentBlock } from '@deepseek-ai/dsh-llm' import { TextRetainer } from '@deepseek-ai/dsh-retention' import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView, ToolDefinition, ToolExecution } from '@deepseek-ai/dsh-tools' @@ -114,6 +114,15 @@ function fitWithSuffix( return `${retainTail(content, maxBytes - fixedBytes)}${fixed}` } +/** + * One-line account of a settled task for the `notice` form's collapsed row. + * @param snapshot - the settled task. + * @returns its kind, label, and status, bounded like every notice summary. + */ +function completionSummary(snapshot: TaskSnapshot): string { + return boundContextSummary(`${snapshot.kind} ${snapshot.label} ${statusLine(snapshot)}`) +} + function fitCompletionNotice(snapshot: TaskSnapshot): string { const prefix = `background task ${snapshot.id}` const detail = ` (${snapshot.kind}: ${snapshot.label}) finished ${statusLine(snapshot)}` @@ -228,7 +237,12 @@ export function apply(ctx: Context, config: Config): void { type: 'text', text: fitCompletionNotice(snapshot), }], - source: { kind: 'plugin', plugin: 'tool-tasks' }, + source: { + kind: 'plugin', + plugin: 'tool-tasks', + form: 'notice', + summary: completionSummary(snapshot), + }, })) }) diff --git a/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts b/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts index c04bca5295..0f1bce7ecf 100644 --- a/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts +++ b/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts @@ -460,7 +460,12 @@ describe('completion notices', () => { id: expect.any(String) as unknown, role: 'user', content: [{ type: 'text', text: 'background task bash-1 (bash: pnpm test) finished [status: completed, exit code: 0]. Read its output with task_output.' }], - source: { kind: 'plugin', plugin: 'tool-tasks' }, + source: { + kind: 'plugin', + plugin: 'tool-tasks', + form: 'notice', + summary: 'bash pnpm test [status: completed, exit code: 0]', + }, }) }) @@ -484,7 +489,14 @@ describe('completion notices', () => { id: expect.any(String) as unknown, role: 'user', content: [{ type: 'text', text: 'background task subagent-1\n[notice truncated]\nDone; task_output.' }], - source: { kind: 'plugin', plugin: 'tool-tasks' }, + // The label and status detail are unbounded caller text, so the durable + // one-line account caps itself rather than committing their full length. + source: { + kind: 'plugin', + plugin: 'tool-tasks', + form: 'notice', + summary: `subagent ${'x'.repeat(110)}…`, + }, }, ) diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 74c0ec265e..73bb8844d0 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -31,6 +31,11 @@ "symbol": "ContextForm", "source": "packages/llm/llm/src/message.ts" }, + { + "doc": "docs/core-data-structures/core.md", + "symbol": "ContextSnapshotSection", + "source": "packages/llm/llm/src/message.ts" + }, { "doc": "docs/core-data-structures/core.md", "symbol": "ContextFormed",