fix(headless): dsh run is a direct core front door
This commit is contained in:
@@ -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 packages/host/apiproxy/README.md
|
||||
README.md: a3c9f214690144ec0f39a8690e4fd346f5e315e2
|
||||
README.zh.md: 65475351e279f258f4417f2082673382e76a5be3
|
||||
README.md: 5e3a6cf57ce3fe11b3f31d7f68055f34708d74eb
|
||||
README.zh.md: b96487d6d67deb8a0a6ddf4a92784f31dafb3e89
|
||||
|
||||
@@ -2,19 +2,19 @@
|
||||
|
||||
English | [中文](README.zh.md)
|
||||
|
||||
The API gateway every client shape shares: the TS contract (`src/api/`, zero Node dependencies, importable from the browser), the fetch carrier pair (`src/fetch/`: `toFetchHandler` on the host side, `AbstractApiClient` plus platform subclasses on the client side), and the host-side implementation (`src/api-proxy.ts`: `createApiProxy` plus the default-exported `ApiProxyService` gateway plugin — config `{provider, model, reasoningEffort?, workspaceRoot?}`, provides `ctx.apiProxy`). Transport-agnostic by design: this package registers no routes; carriers such as HTTP wrap `ctx.apiProxy` themselves. The shipped core composition lives in [`packages/bundle/base/cordis.patch.yml`](../../bundle/base/cordis.patch.yml).
|
||||
The API gateway every client shape shares: the TS contract (`src/api/`, zero Node dependencies, importable from the browser), the fetch carrier pair (`src/fetch/`: `toFetchHandler` on the host side, `AbstractApiClient` plus platform subclasses on the client side), and the host-side implementation (`src/api-proxy.ts`: `createApiProxy` plus the default-exported `ApiProxyService` gateway plugin — config `{workspaceRoot?}`, provides `ctx.apiProxy`). Transport-agnostic by design: this package registers no routes; carriers such as HTTP wrap `ctx.apiProxy` themselves. The shipped Web composition lives in [`packages/bundle/web-app/cordis.patch.yml`](../../bundle/web-app/cordis.patch.yml), while its default Agent model selection belongs to [`@deepseek-ai/dsh-agent-default-model`](../../core/agent-default-model/README.md) in the base bundle.
|
||||
|
||||
## The default route (`api-gateway` settings section)
|
||||
## The shared Agent default (`agent-default-model` Settings section)
|
||||
|
||||
`{provider, model, reasoningEffort?}` is also the gateway's user-settings section, registered under `api-gateway`: the composition entry is the `base` layer and `settings.yaml` layers the user's own choice over it. `workspaceRoot` is deliberately outside the section — a launcher fact, not a preference.
|
||||
`ApiProxyService` consumes `ctx.agentDefaultModel`; it does not own a provider/model config or settings section. The shared service registers `{provider, model, reasoningEffort?}` under `agent-default-model`: the base bundle's composition entry is the lower layer and `settings.yaml` layers the user's choice over it. `workspaceRoot` remains ApiProxy config because it is a Host launcher fact, not a model preference.
|
||||
|
||||
A session resolves its route from three tiers, re-read on every access rather than seeded once: a selection made in this process, else the session's own latest logged `request/header`, else this default. Re-reading is what makes both directions hold — a session that has run a turn derives its route from its log forever after, so changing the default never retargets it, while a session still blank (New Session reuses one rather than minting another) starts from a default saved after it was created.
|
||||
A session resolves its model selection from three tiers on every access: a selection made in this process, otherwise the session's latest logged `request/header`, otherwise this default. A session that has run a turn derives its selection from its log, while a blank session observes a default saved after it was created.
|
||||
|
||||
`session.selectModel` records an accepted switch as the new default, which is how the default is chosen in practice: there is no separate gesture. What it stores is the RESOLVED target, so an adapter-materialized default effort is pinned as the user saw it and a later adapter-default change does not silently move stored defaults. The write replaces the section wholesale rather than merging, because switching to a model with no reasoning effort has to clear a stored one; a storage failure is logged without undoing the switch, which already applies to its own session. A deployment with no settings provider keeps the composition entry and a switch stays process-local.
|
||||
`session.selectModel` saves an accepted switch as the deployment default; there is no separate gesture. It stores the resolved `ModelSelection`, including an adapter-materialized default effort. The complete-section write clears a stored effort when the selected model has none. A storage failure is logged without undoing the session selection. A deployment with no settings provider keeps the composition entry and the switch remains session-local.
|
||||
|
||||
The section's `reasoningEffort` has no counterpart in the plugin config, deliberately: the seam merges the user layer over the composition entry per field, so an absent key cannot override a present one and a composition-set effort would survive every later switch to a model without one. A deployment default for effort belongs on the adapter profile, which resolves per model.
|
||||
The section's `reasoningEffort` has no counterpart in the agent-default-model plugin config, deliberately: the seam merges the user layer over the composition entry per field, so an absent key cannot override a present one and a composition-set effort would survive every later switch to a model without one. A deployment default for effort belongs on the adapter profile, which resolves per model.
|
||||
|
||||
The stored route is not validated against the registry, in either direction. A default naming a route the Models page has since removed still reaches `session.models` as the session's `current` — matching no advertised group, which is precisely what makes a selector prompt for a replacement instead of naming a model the deployment cannot reach. Repairing it silently would also break the deliberate converse: an adapter may serve a model its catalog does not advertise.
|
||||
The stored selection is independent of catalog membership. A default naming an unavailable provider still reaches `session.models` as the session's `current`, allowing the selector to request a replacement instead of silently choosing another model. Conversely, an adapter may serve a model that its catalog does not advertise.
|
||||
|
||||
## Contract layer (`/api`)
|
||||
|
||||
@@ -30,9 +30,9 @@ Question responses are validated against their pending request before the first
|
||||
|
||||
Session titles ride the generic projection pair like every other domain — the history-tail `projections` block plus `session/projection` frames under the `title` key (the bespoke `session/title` frame is retired). Titles do not join `session.list`; cold sessions remain metadata-only there until opening or resuming attaches their logs. `session.rename` accepts an explicit user title (resuming a cold session first), delegating to `ctx.sessionTitle.rename` — the accepted `session/title` event pins the title against automatic regeneration — and returns the normalized title plus its event seq so a client settles its `title` projection cell ahead of the push frame; a title that normalizes to empty returns `title-invalid`.
|
||||
|
||||
`session.fork` maps an optional event anchor to the first `turn/end` at or after it, letting a message action include that message's whole turn. An omitted or past-end anchor selects the last completed turn; an in-log anchor whose turn remains open returns `fork-unavailable` rather than clipping backward. The published child inherits the source's seeded history, cwd, latest logged provider/model/reasoning target, and lineage before joining the source Workspace. If Workspace attachment fails, `workspace-attach-failed` carries the already-published child id so clients can reconcile it. The [SessionStore fork decision](../../../.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md) owns the boundary rationale.
|
||||
`session.fork` maps an optional event anchor to the first `turn/end` at or after it, letting a message action include that message's whole turn. An omitted or past-end anchor selects the last completed turn; an in-log anchor whose turn remains open returns `fork-unavailable` rather than clipping backward. The published child inherits the source's seeded history, cwd, latest logged `ModelSelection`, and lineage before joining the source Workspace. If Workspace attachment fails, `workspace-attach-failed` carries the already-published child id so clients can reconcile it. The [SessionStore fork decision](../../../.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md) owns the boundary rationale.
|
||||
|
||||
Session model routing is a session-domain contract. `session.models` returns the selected provider/model/reasoning target separately from provider-grouped advisory models, exact-route reasoning metadata, and provider-local lookup failures. The current target may be absent from the groups and is never injected as a synthetic row; clients can prompt for a replacement without turning the directory into a routing whitelist. `session.selectModel` validates the optional adapter-owned reasoning effort and replaces the complete target selected for the next prompt-assembly boundary. Catalog membership is not validation: an adapter may resolve an unlisted model, while an unavailable route or unsupported effort returns `model-unavailable`. `session.models` additionally reports `routable`: whether an adapter currently serves the current target's route, which is deliberately NOT derivable from the groups — a route serving a model it stopped advertising is absent from them yet perfectly usable, while a route whose adapter is gone can serve nothing. `session.prompt` refuses on that same fact with `model-unavailable` rather than spending the pre-step path to fail inside an adapter; a client that disables its composer is an affordance, and this method stays callable regardless.
|
||||
Session model selection is a session-domain contract. `session.models` returns the current `ModelSelection` separately from provider-grouped advisory models, exact-model reasoning metadata, and provider-local lookup failures. The selection may be absent from the groups and is never injected as a synthetic row; clients can prompt for another selection without turning the directory into a routing whitelist. `session.selectModel` validates the optional adapter-owned reasoning effort and assigns the complete selection for the next prompt-assembly boundary. Catalog membership is not validation: an adapter may resolve an unlisted model, while an unavailable provider or unsupported effort returns `model-unavailable`. `session.models` additionally reports `routable`: whether an adapter currently serves the selected provider. This is deliberately not derivable from the groups because an adapter may serve an unadvertised model. `session.prompt` refuses on the same fact with `model-unavailable` before opening a turn; a disabled composer is a client affordance, and the method remains callable.
|
||||
|
||||
Pending queued input is a live control-plane contract, not conversation history. The gateway derives the complete `next-turn` queue from durable `agent/inbox/spliced` mutations and broadcasts authoritative `session/queue` snapshots after each change and on reconnect; pending `next-step` steering stays outside this Web projection. Within `next-step`, user-origin messages carry the `steering` placement while injected context (approval notices, task completion, attached snapshots) carries `context` and is not surfaced until claimed. The message-local `agent/inbox/inserted`, `claimed`, and `discarded` notifications remain available to lifecycle observers but do not build the queue view. `session.updateQueue` addresses one `MessageId`; edit and remove mutate the attached Agent through `Inbox.splice()`. A claim's pure deletion splice wins races before pre-step admission, so a later operation returns `queue-item-not-found`. `session.cancel` aborts only the active turn and preserves pending inbox work; after cancellation reaches quiescence and the closing turn flushes, AgentLoop claims the next waking message in FIFO order, and the browser never resends or promotes it. Queue operations never resume a cold session, and the client never infers retirement from turn or status events.
|
||||
|
||||
@@ -52,7 +52,7 @@ The `settings.*`, `credentials.*`, and `llm.*` domains are the configuration-pag
|
||||
|
||||
## Carrier layer (`/client` + root)
|
||||
|
||||
`AbstractApiClient` holds every protocol invariant — rpcId minting, envelope wrap/unwrap, zod parsing, SSE frame decoding, unary timeout, microtask-batched envelope observation (`subscribeEnvelopes`) — while platform subclasses supply only the `doFetch` transport aspect. `InProcessApiClient` over `toFetchHandler(api)` is the isomorphic point: the full wire serialization/validation path with no network, used by `dsh run` headless.
|
||||
`AbstractApiClient` holds every protocol invariant — rpcId minting, envelope wrap/unwrap, zod parsing, SSE frame decoding, unary timeout, microtask-batched envelope observation (`subscribeEnvelopes`) — while platform subclasses supply only the `doFetch` transport aspect. `InProcessApiClient` over `toFetchHandler(api)` remains the isomorphic point for callers and carrier tests that need the full wire serialization/validation path without a network. Product `dsh run` is a direct core front door and does not mount this package.
|
||||
|
||||
## Model Experience
|
||||
|
||||
|
||||
@@ -2,19 +2,19 @@
|
||||
|
||||
[English](README.md) | 中文
|
||||
|
||||
所有客户端形态共用的 API 网关:TS 约定(`src/api/`,不依赖 Node,可从浏览器导入)、fetch 载体对(`src/fetch/`:宿主侧的 `toFetchHandler`,以及客户端侧的 `AbstractApiClient` 与平台子类)和宿主侧实现(`src/api-proxy.ts`:`createApiProxy` 加上默认导出的 `ApiProxyService` 网关插件,其配置为 `{provider, model, reasoningEffort?, workspaceRoot?}`,提供 `ctx.apiProxy`)。该包在设计上与传输方式无关,不注册任何路由;HTTP 等载体自行包装 `ctx.apiProxy`。已发布的核心组合位于 [`packages/bundle/base/cordis.patch.yml`](../../bundle/base/cordis.patch.yml)。
|
||||
所有客户端形态共用的 API 网关:TS 约定(`src/api/`,不依赖 Node,可从浏览器导入)、fetch 载体对(`src/fetch/`:宿主侧的 `toFetchHandler`,以及客户端侧的 `AbstractApiClient` 与平台子类)和宿主侧实现(`src/api-proxy.ts`:`createApiProxy` 加上默认导出的 `ApiProxyService` 网关插件,其配置为 `{workspaceRoot?}`,提供 `ctx.apiProxy`)。该包在设计上与传输方式无关,不注册任何路由;HTTP 等载体自行包装 `ctx.apiProxy`。随发行版交付的 Web 组合位于 [`packages/bundle/web-app/cordis.patch.yml`](../../bundle/web-app/cordis.patch.yml),其默认 Agent(智能体)模型选择属于 base 组合包中的 [`@deepseek-ai/dsh-agent-default-model`](../../core/agent-default-model/README.md)。
|
||||
|
||||
## 默认路由(`api-gateway` 设置段)
|
||||
## 共享 Agent 默认值(`agent-default-model` Settings 分节)
|
||||
|
||||
`{provider, model, reasoningEffort?}` 同时是网关的用户设置段,注册在 `api-gateway` 之下:组合条目是 `base` 层,`settings.yaml` 把用户自己的选择叠加其上。`workspaceRoot` 刻意不在段内——它是启动器事实,不是偏好。
|
||||
`ApiProxyService` 消费 `ctx.agentDefaultModel`;它不持有提供方/模型配置或 Settings 分节。共享服务在 `agent-default-model` 下注册 `{provider, model, reasoningEffort?}`:base 组合包的组合条目是底层,`settings.yaml` 把用户选择叠加其上。`workspaceRoot` 仍属于 ApiProxy 配置,因为它是 Host 启动器事实,而不是模型偏好。
|
||||
|
||||
会话按三级解析自己的路由,且每次读取都重新解析,而不是只在创建时种一次:本进程内的显式选择,其次是该会话自己最新记录的 `request/header`,最后才是这个默认值。重新解析正是让两个方向都成立的原因——已经跑过一轮的会话此后永远从自己的日志推导路由,改默认值不会重定向它;而仍然空白的会话(新建会话会复用一个,而不是再开一个)则会用上它创建之后才保存的默认值。
|
||||
会话每次访问时都按三级解析模型选择:本进程内作出的选择,其次是该会话日志中最新的 `request/header`,最后是这个默认值。已经跑过一轮的会话从自己的日志推导选择,空白会话则能观察到创建之后保存的默认值。
|
||||
|
||||
`session.selectModel` 会把被接受的切换记录为新的默认值,实践中默认值就是这样选定的,没有另一个单独的手势。它存下来的是**解析后**的目标,因此适配器实体化出来的默认推理等级会按用户当时看到的样子钉住,日后适配器改了自己的默认值也不会悄悄移动已存的默认路由。写入是整段替换而非合并,因为切到一个不带推理等级的模型必须清掉已存的等级;存储失败只记日志,不会撤销这次切换——它对自己所在的会话已经生效。没有设置提供方的部署保留组合条目,切换只停留在进程内。
|
||||
`session.selectModel` 会把接受的切换保存为部署默认值;没有单独的选择动作。它存储已解析的 `ModelSelection`,包括适配器实体化的默认推理强度。完整分节写入会在所选模型没有推理强度时清除已存值。存储失败只记日志,不会撤销会话选择。没有设置提供方的部署保留组合条目,切换只对当前会话生效。
|
||||
|
||||
设置段里的 `reasoningEffort` 在插件配置中刻意没有对应字段:seam 是按字段把用户层合并到组合条目之上的,缺席的键覆盖不了存在的键,因此组合层设的推理等级会在此后每一次切到不带推理等级的模型时继续存活。推理等级的部署级默认值属于适配器 profile,那里是按模型解析的。
|
||||
Settings 分节中的 `reasoningEffort` 在 agent-default-model 插件配置中刻意没有对应字段:seam 按字段把用户层合并到组合条目之上,因此缺席的键无法覆盖已有键,组合层中的推理强度会在以后选择没有推理强度的模型时继续存在。推理强度的部署默认值属于按模型解析的适配器 profile。
|
||||
|
||||
存下来的路由不做注册表校验,两个方向都不做。默认值指向一个已在模型页删除的路由时,它照样作为会话的 `current` 送到 `session.models`——匹配不到任何已公布的分组,而这恰恰是让选择器提示重新选择、而不是显示一个部署根本够不着的模型的原因。静默修复它还会破坏刻意保留的反面情形:适配器可以服务一个自己目录未公布的模型。
|
||||
存储的选择独立于目录成员关系。默认值指向不可用的提供方时,它仍会作为会话的 `current` 送到 `session.models`,让选择器请求用户重新选择,而不是静默选用其他模型。反过来,适配器也可以服务其目录中未公布的模型。
|
||||
|
||||
## 约定层(`/api`)
|
||||
|
||||
@@ -24,15 +24,15 @@
|
||||
|
||||
首个回答认领待处理请求之前,系统会对照该请求校验问题响应。多选题的回答项可以同时携带 `selected` 中的请求选项标签与非空 `custom` 文本;单选题的回答项必须二选一。标签重复、标签未知、id 不匹配、批次不完整以及自定义文本为空都会以 `bad-response` 拒绝。
|
||||
|
||||
`session.history` 会读取已附加 Session 的内存状态,或通过持久化检查冷日志,而不会恢复或发布 agent(智能体),然后按追加来源的消息边界分页:`maxMessages` 统计以追加方式进入 surface 的 `user/message` 和 `assistant/message` 事件,因此仅供模型使用的替换副本不占用配额。每一页仍是一段连续的原始事件区间,从而让压缩(compaction)的仅日志溯源信息与引用它的替换留在同一页。
|
||||
`session.history` 会读取已附加 Session 的内存状态,或通过持久化检查冷日志,而不会恢复或发布 agent,然后按追加来源的消息边界分页:`maxMessages` 统计以追加方式进入 surface 的 `user/message` 和 `assistant/message` 事件,因此仅供模型使用的替换副本不占用配额。每一页仍是一段连续的原始事件区间,从而让压缩(compaction)的仅日志溯源信息与引用它的替换留在同一页。
|
||||
|
||||
`session.history` 的尾页(不带 `beforeSeq`)额外携带一个可选的 `projections` 块——`ctx.sessionProjections`(`@deepseek-ai/dsh-session-projection`)上每个已注册单元的水位线快照,`asOfSeq` = 这些值共同反映到的最后一个事件 seq(空日志为 `-1`)。网关还订阅注册表的变更流,为每个状态发生变化的单元生成一个 `session/projection` mux 帧(`{sessionId, key, value, seq}`——实时推送状态,绝不入日志;客户端按 seq 高者胜维护一个按会话的通用值仓)。载体不持有任何领域知识(每个值在注册表内部已过其单元自己的 schema;协议 schema 对 `values`/`value` 保持宽松);loadOlder 页永不携带该块,未装注册表的组合则两个面都不提供。
|
||||
|
||||
会话标题与其他所有领域一样搭乘这对通用投影机制——历史尾页的 `projections` 块外加 `title` 键下的 `session/projection` 帧(专设的 `session/title` 帧已下线)。标题不会加入 `session.list`;冷会话在其中仍只有元数据,直到打开或恢复操作附加其日志。`session.rename` 接受用户显式标题(冷会话先恢复),委托给 `ctx.sessionTitle.rename`——被接受的 `session/title` 事件将标题钉住、不再被自动生成覆盖——并返回规范化后的标题及其事件 seq,让 client 在推送帧到达前就结算自己的 `title` 投影格;规范化后为空的标题返回 `title-invalid`。
|
||||
|
||||
`session.fork` 将可选事件锚点映射到该锚点处或其后的首个 `turn/end`,使消息操作可包含该消息所在的完整轮次。锚点省略或超过末尾时,选择最后一个已完成轮次;若锚点已在日志中,而其所在轮次仍开放,则返回 `fork-unavailable`,不会向较早位置裁剪。发布后的子会话会先继承源会话的种子历史、cwd、日志中最新的提供方/模型/推理(reasoning)目标及谱系,再加入源 Workspace。如果附加到 Workspace 失败,`workspace-attach-failed` 会携带已发布的子会话 id,供客户端对账。[SessionStore fork 决策](../../../.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md)给出边界设计的理由。
|
||||
`session.fork` 将可选事件锚点映射到该锚点处或其后的首个 `turn/end`,使消息操作可包含该消息所在的完整轮次。锚点省略或超过末尾时,选择最后一个已完成轮次;若锚点已在日志中,而其所在轮次仍开放,则返回 `fork-unavailable`,不会向较早位置裁剪。发布后的子会话会先继承源会话的种子历史、cwd、日志中最新的 `ModelSelection` 及谱系,再加入源 Workspace。如果附加到 Workspace 失败,`workspace-attach-failed` 会携带已发布的子会话 id,供客户端对账。[SessionStore fork 决策](../../../.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md)给出边界设计的理由。
|
||||
|
||||
会话模型路由属于会话领域约定。`session.models` 将选中的提供方/模型/推理目标,与按提供方分组的建议性模型、精确路由推理元数据和逐提供方查询失败记录分开返回。当前目标可能不在这些分组中,也绝不会作为合成行注入;客户端可以提示用户选择替代目标,而无需把目录变成路由白名单。`session.selectModel` 校验由适配器持有的可选推理强度,并替换将在下一提示词组装边界使用的完整目标。目录成员关系不构成校验:适配器可以解析未列出的模型,而不可用路由或不受支持的推理强度会返回 `model-unavailable`。`session.models` 还会报告 `routable`:当前目标的路由是否有适配器在服务。这一点刻意不由分组推导——一条仍在服务、只是不再公布该模型的路由不在分组里,却完全可用;而适配器已经消失的路由什么都服务不了。`session.prompt` 依据同一个事实以 `model-unavailable` 拒绝,而不是把整条 pre-step 路径走完再在适配器内部失败;客户端禁用输入框只是提示性设计,这个方法始终可被调用。
|
||||
会话模型选择属于会话领域约定。`session.models` 将当前 `ModelSelection` 与按提供方分组的建议性模型、精确模型的推理(reasoning)元数据和逐提供方查询失败记录分开返回。该选择可能不在这些分组中,也绝不会作为合成行注入;客户端可以提示用户作出另一项选择,而无需把目录变成路由白名单。`session.selectModel` 校验由适配器持有的可选推理强度,并指定将在下一提示词组装边界使用的完整选择。目录成员关系不构成校验:适配器可以解析未列出的模型,而不可用的提供方或不受支持的推理强度会返回 `model-unavailable`。`session.models` 还会报告 `routable`,即当前是否有适配器为所选提供方提供服务。该值刻意不从分组推导,因为适配器可以服务未公布的模型。`session.prompt` 会依据同一事实,在开启轮次之前以 `model-unavailable` 拒绝;客户端禁用 composer 只是提示性设计,这个方法始终可被调用。
|
||||
|
||||
待处理的 queued 输入属于实时控制平面约定,而非对话历史。网关根据持久 `agent/inbox/spliced` 变更派生完整的 `next-turn` 队列,并在每次变更后及重连时广播权威 `session/queue` 快照;待处理的 `next-step` steering(中途引导)不进入此 Web 投影。在 `next-step` 内,用户来源的消息携带 `steering` placement,而注入上下文(审批通知、任务完成、附加快照)携带 `context`,领取前不对外呈现。面向单条消息的 `agent/inbox/inserted`、`claimed` 与 `discarded` 通知仍供生命周期观察方使用,但不用于构建队列视图。`session.updateQueue` 通过 `MessageId` 寻址单个项;编辑和移除经已挂载 Agent 的 `Inbox.splice()` 修改队列。claim 的纯删除 splice 会在 pre-step 准入前赢得竞态,因此之后的操作返回 `queue-item-not-found`。`session.cancel` 仅中止活动轮次并保留待处理 inbox 工作;取消达到完全停稳且结束中的轮次完成 flush 后,AgentLoop 按 FIFO 顺序认领下一条可唤醒消息,浏览器绝不重发或提升它。队列操作绝不恢复冷会话,客户端也绝不根据轮次或状态事件推断某项已退出队列。
|
||||
|
||||
@@ -52,7 +52,7 @@ Workspace 列表与 Session 列表是相互独立的重连基线。`workspace.cr
|
||||
|
||||
## 载体层(`/client` + 根路径)
|
||||
|
||||
`AbstractApiClient` 持有全部协议不变量:签发 rpcId、包装/解包信封、Zod 解析、SSE 帧解码、一元请求超时,以及按微任务批处理的信封观测(`subscribeEnvelopes`);平台子类只提供 `doFetch` 传输环节。`InProcessApiClient` 以 `toFetchHandler(api)` 为基础,是同构接点:它运行完整的协议序列化与校验路径而不经过网络,供 `dsh run` headless 模式使用。
|
||||
`AbstractApiClient` 持有全部协议不变量:签发 rpcId、包装/解包信封、Zod 解析、SSE 帧解码、一元请求超时,以及按微任务批处理的信封观测(`subscribeEnvelopes`);平台子类只提供 `doFetch` 传输环节。`InProcessApiClient` 以 `toFetchHandler(api)` 为基础,仍是同构接点:它运行完整的协议序列化与校验路径而不经过网络,供需要该路径的调用方和载体测试使用。产品的 `dsh run` 是直连 core 的入口,不挂载本包。
|
||||
|
||||
## 模型体验
|
||||
|
||||
|
||||
@@ -39,6 +39,7 @@
|
||||
"license": "BSD-3-Clause",
|
||||
"dependencies": {
|
||||
"@deepseek-ai/dsh-agent": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent-default-model": "workspace:^",
|
||||
"@deepseek-ai/dsh-api-remotes": "workspace:^",
|
||||
"@deepseek-ai/dsh-brand": "workspace:^",
|
||||
"@deepseek-ai/dsh-commands": "workspace:^",
|
||||
|
||||
@@ -7,8 +7,9 @@ import { randomUUID } from 'node:crypto'
|
||||
import { mkdir, stat } from 'node:fs/promises'
|
||||
import { join } from 'node:path'
|
||||
import type { Context } from 'cordis'
|
||||
import { installAgentLlmTarget } from '@deepseek-ai/dsh-agent'
|
||||
import type { Agent, AgentLlmTarget, AgentLlmTargetRef, AgentOptions, AgentStatus } from '@deepseek-ai/dsh-agent'
|
||||
import { installModelSelection } from '@deepseek-ai/dsh-agent'
|
||||
import type { Agent, ModelSelection, ModelSelectionRef, AgentOptions, AgentStatus } from '@deepseek-ai/dsh-agent'
|
||||
import { AGENT_DEFAULT_MODEL_SETTINGS_NAMESPACE } from '@deepseek-ai/dsh-agent-default-model'
|
||||
import { createUserMessage, freezeMessage, ReasoningEffortId } from '@deepseek-ai/dsh-llm'
|
||||
import { errorChain } from '@deepseek-ai/dsh-llm'
|
||||
import type { MessageSource } from '@deepseek-ai/dsh-llm'
|
||||
@@ -83,14 +84,6 @@ import { openNativePath, openNativeTextFile } from './native-path-opener.ts'
|
||||
/** Page size when history is called without maxMessages. */
|
||||
const DEFAULT_MAX_MESSAGES = 50
|
||||
|
||||
/**
|
||||
* The settings namespace carrying the user's default route. Named for the
|
||||
* gateway rather than for the package, because this key is what a person reads
|
||||
* and writes in `settings.yaml`; the row id in a composition happens to match
|
||||
* but does not determine it.
|
||||
*/
|
||||
export const API_GATEWAY_SETTINGS_NAMESPACE = settingsNamespace('api-gateway')
|
||||
|
||||
/** Non-model settings namespaces intentionally served to the Web client. */
|
||||
const WEB_SETTINGS_NAMESPACES = ['permission'] as const
|
||||
|
||||
@@ -152,7 +145,7 @@ function ok<T>(request: RpcRequest<unknown>, value: T): RpcResponse<T> {
|
||||
/**
|
||||
* Build the provider/model catalog over every registered route. Shared by the
|
||||
* session-scoped `session.models` and host-scoped `llm.models`. Catalog
|
||||
* membership stays advisory: an unlisted session target remains valid for
|
||||
* membership stays advisory: an unlisted session selection remains valid for
|
||||
* provider dispatch, but is not injected back into the selector after its
|
||||
* owning catalog stops advertising it. Per-provider failures ride `failures`
|
||||
* without failing the sound groups; groups that advertise nothing are dropped.
|
||||
@@ -345,14 +338,14 @@ function directoryError(error: unknown): RpcError {
|
||||
return { code: 'internal', message: error instanceof Error ? error.message : String(error), details: {} }
|
||||
}
|
||||
|
||||
/** Resolved Host routing and project-directory defaults consumed by the API implementation. */
|
||||
/** Resolved Agent model and project-directory defaults consumed by the API implementation. */
|
||||
export interface ApiProxyDefaults {
|
||||
/**
|
||||
* The route a session starts from when its own log names none. Read on
|
||||
* The model selection a session starts from when its own log names none. Read on
|
||||
* every access rather than captured, so a default saved during this process
|
||||
* reaches the sessions that have not run a turn yet.
|
||||
*/
|
||||
defaultTarget: () => AgentLlmTarget
|
||||
defaultModelSelection: () => ModelSelection
|
||||
/**
|
||||
* Record a selection as the new default. Either absent, or a closure that
|
||||
* may itself decline — the gateway plugin always passes one, and it no-ops
|
||||
@@ -361,7 +354,7 @@ export interface ApiProxyDefaults {
|
||||
* reported and swallowed: the switch already applies to its own session,
|
||||
* and undoing it because storage failed would be the worse outcome.
|
||||
*/
|
||||
persistDefaultTarget?: (target: AgentLlmTarget) => Promise<void>
|
||||
saveDefaultModelSelection?: (selection: ModelSelection) => Promise<void>
|
||||
/** Default project directory for new sessions whose create request carries no cwd. */
|
||||
cwd: string
|
||||
/** Parent directory for name-created workspaces. */
|
||||
@@ -734,17 +727,17 @@ function changedWorkspaceView(workspaceId: string, value: unknown): WorkspaceVie
|
||||
/**
|
||||
* Implement ApiProxy over a composed host context.
|
||||
* @param ctx - a context with the Host spine and Workspace registry mounted.
|
||||
* @param defaults - host routing and project-directory defaults.
|
||||
* @param defaults - Agent model and project-directory defaults.
|
||||
* @returns the ApiProxy implementation.
|
||||
*/
|
||||
export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiProxy {
|
||||
/** The seed route each create/resume declares; re-read so it never goes stale. */
|
||||
/** The seed model each create/resume declares; re-read so it never goes stale. */
|
||||
const agentOptions = (): AgentOptions => {
|
||||
const { provider, model } = defaults.defaultTarget()
|
||||
const { provider, model } = defaults.defaultModelSelection()
|
||||
return { provider, model }
|
||||
}
|
||||
type WebLlmTargetRef = AgentLlmTargetRef & { current: AgentLlmTarget }
|
||||
const targets = new WeakMap<Agent, WebLlmTargetRef>()
|
||||
type WebModelSelectionRef = ModelSelectionRef & { current: ModelSelection }
|
||||
const selections = new WeakMap<Agent, WebModelSelectionRef>()
|
||||
/** Client-chosen identity creation/resume, deduplicated across concurrent retries. */
|
||||
const sessionCreations = new Map<SessionId, Promise<Agent>>()
|
||||
/** Serializes path ownership and explicit title checks with Workspace mutations. */
|
||||
@@ -754,29 +747,28 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
const muxQueues = new Set<FrameQueue<RpcRequest<MuxFrame>>>()
|
||||
|
||||
/**
|
||||
* Install or return the session-local target that prompt assembly snapshots.
|
||||
* Install or return the session-local model selection that prompt assembly snapshots.
|
||||
*
|
||||
* Precedence, resolved on EVERY read rather than seeded once: a selection
|
||||
* made in this process, else the session's own latest logged request/header,
|
||||
* else the live host default. Re-reading is what keeps the two tiers honest
|
||||
* in both directions — a session that has run a turn derives its route from
|
||||
* its log forever after, so changing the default never retargets it; and a
|
||||
* session still blank (New Session reuses one rather than minting another)
|
||||
* starts from a default saved after it was created. There is no create-time
|
||||
* else the live Agent default. Re-reading keeps the two tiers exact in both
|
||||
* directions: a session with a recorded request derives its selection from
|
||||
* its log, while a blank session (New Session reuses one rather than minting
|
||||
* another) reads any default saved after it was created. There is no create-time
|
||||
* per-session override tier on this wire — if one returns (a create-options
|
||||
* contribution), it must fold in between the selection and the log.
|
||||
*/
|
||||
function targetFor(agent: Agent): WebLlmTargetRef {
|
||||
const installed = targets.get(agent)
|
||||
function selectionFor(agent: Agent): WebModelSelectionRef {
|
||||
const installed = selections.get(agent)
|
||||
if (installed !== undefined) return installed
|
||||
let picked: AgentLlmTarget | undefined
|
||||
const target: WebLlmTargetRef = {
|
||||
get current(): AgentLlmTarget {
|
||||
let picked: ModelSelection | undefined
|
||||
const selection: WebModelSelectionRef = {
|
||||
get current(): ModelSelection {
|
||||
if (picked !== undefined) return picked
|
||||
// Incrementally folded by the session, so a per-step read costs
|
||||
// O(new events) rather than a rescan.
|
||||
const logged = agent.session.requestHeader()?.config
|
||||
if (logged === undefined) return defaults.defaultTarget()
|
||||
if (logged === undefined) return defaults.defaultModelSelection()
|
||||
return {
|
||||
provider: logged.provider,
|
||||
model: logged.model,
|
||||
@@ -785,21 +777,21 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
: { reasoningEffort: logged.reasoningEffort },
|
||||
}
|
||||
},
|
||||
set current(next: AgentLlmTarget) {
|
||||
set current(next: ModelSelection) {
|
||||
picked = next
|
||||
},
|
||||
assembled: undefined,
|
||||
}
|
||||
installAgentLlmTarget(agent.ctx, target)
|
||||
targets.set(agent, target)
|
||||
return target
|
||||
installModelSelection(agent.ctx, selection)
|
||||
selections.set(agent, selection)
|
||||
return selection
|
||||
}
|
||||
|
||||
/** Pre-publication setup used by both fresh and resumed Web agents. */
|
||||
function installTarget(agentCtx: Context): void {
|
||||
function installSelection(agentCtx: Context): void {
|
||||
const agent = agentCtx.agent
|
||||
if (agent === undefined) throw new Error('api-proxy: agent setup has no scoped agent')
|
||||
targetFor(agent)
|
||||
selectionFor(agent)
|
||||
}
|
||||
|
||||
const hasSubagentOwner = (
|
||||
@@ -810,7 +802,7 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
apiRemoteSubagentOwnershipError(sessionId)
|
||||
const inspectServable = (sessionId: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }> =>
|
||||
inspectApiRemoteSession(ctx, sessionId)
|
||||
const agentFor = createApiRemoteAgentResolver(ctx, { agentOptions, setup: installTarget })
|
||||
const agentFor = createApiRemoteAgentResolver(ctx, { agentOptions, setup: installSelection })
|
||||
|
||||
/** Send one transient frame to every connected mux consumer. */
|
||||
function broadcast(payload: MuxFrame): void {
|
||||
@@ -1076,7 +1068,7 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
return (await ctx.agents.resume({
|
||||
resumeSessionId: sessionId,
|
||||
agentOptions: agentOptions(),
|
||||
setup: installTarget,
|
||||
setup: installSelection,
|
||||
})).agent
|
||||
}
|
||||
|
||||
@@ -1089,7 +1081,7 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
sessionId,
|
||||
agentOptions: agentOptions(),
|
||||
meta: { cwd },
|
||||
setup: installTarget,
|
||||
setup: installSelection,
|
||||
})).agent
|
||||
})().catch((error: unknown) => {
|
||||
// Another Host entry path may have published the same identity while
|
||||
@@ -1235,10 +1227,10 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
}
|
||||
|
||||
/**
|
||||
* Whether an adapter currently serves this route, and therefore whether a
|
||||
* session pointed at it can start a turn. Catalog membership cannot answer
|
||||
* Whether an adapter currently serves this provider, and therefore whether
|
||||
* a session selecting it can start a turn. Catalog membership cannot answer
|
||||
* it: an adapter may serve a model its own catalog stopped advertising, so
|
||||
* a route missing from the groups is not the same as one nothing serves.
|
||||
* a provider missing from the groups is not the same as one nothing serves.
|
||||
* A composition with no llm registry at all cannot judge and says yes —
|
||||
* the dispatch it would have refused fails on its own terms.
|
||||
*/
|
||||
@@ -1249,7 +1241,7 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
|
||||
/**
|
||||
* Resolve the addressed agent for a turn-starting method and refuse when no
|
||||
* adapter serves its current route: a route nothing serves cannot start a
|
||||
* adapter serves its current selection: a provider nothing serves cannot start a
|
||||
* turn, and letting it try spends the whole pre-step path to fail inside
|
||||
* the adapter with a message about registration. Refusing here names the
|
||||
* model the session is pointed at while the draft is still in the composer.
|
||||
@@ -1262,13 +1254,13 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
const found = await agentFor(sessionId)
|
||||
if ('error' in found) return { refused: err(request, found.error) }
|
||||
const agent = found.agent
|
||||
const target = targetFor(agent).current
|
||||
if (!routeServed(target.provider)) {
|
||||
const selection = selectionFor(agent).current
|
||||
if (!routeServed(selection.provider)) {
|
||||
return {
|
||||
refused: err(request, {
|
||||
code: 'model-unavailable',
|
||||
message: `no adapter serves provider "${target.provider}"; select a model for this session`,
|
||||
details: { provider: target.provider, model: target.model },
|
||||
message: `no adapter serves provider "${selection.provider}"; select a model for this session`,
|
||||
details: { provider: selection.provider, model: selection.model },
|
||||
}),
|
||||
}
|
||||
}
|
||||
@@ -1643,7 +1635,7 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
const { sessionId } = request.payload
|
||||
const found = await agentFor(sessionId)
|
||||
if ('error' in found) return err(request, found.error)
|
||||
const current = targetFor(found.agent).current
|
||||
const current = selectionFor(found.agent).current
|
||||
const { groups, failures } = await buildModelCatalog(ctx)
|
||||
const routable = routeServed(current.provider)
|
||||
return ok(request, { current: { ...current }, routable, groups, failures })
|
||||
@@ -1661,20 +1653,20 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
? {}
|
||||
: { reasoningEffort: ReasoningEffortId(reasoningEffort) },
|
||||
})
|
||||
const selected: AgentLlmTarget = {
|
||||
const selected: ModelSelection = {
|
||||
provider: resolved.provider,
|
||||
model: resolved.model,
|
||||
...resolved.reasoningEffort === undefined
|
||||
? {}
|
||||
: { reasoningEffort: resolved.reasoningEffort },
|
||||
}
|
||||
targetFor(found.agent).current = selected
|
||||
selectionFor(found.agent).current = selected
|
||||
// A switch is also how this deployment's default is chosen: the next
|
||||
// session created without one of its own starts here. Sessions that
|
||||
// have already logged a route are unaffected — they derive from
|
||||
// their own log (see targetFor).
|
||||
// have already logged a selection are unaffected — they derive from
|
||||
// their own log (see selectionFor).
|
||||
try {
|
||||
await defaults.persistDefaultTarget?.(selected)
|
||||
await defaults.saveDefaultModelSelection?.(selected)
|
||||
} catch (error: unknown) {
|
||||
ctx.logger.warn(
|
||||
`api-proxy: the model switch applies to this session but was not saved as the default: ${String(error)}`,
|
||||
@@ -1783,7 +1775,7 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
seedLength: cut,
|
||||
},
|
||||
agentOptions: agentOptions(),
|
||||
setup: installTarget,
|
||||
setup: installSelection,
|
||||
})
|
||||
} catch (error: unknown) {
|
||||
return err(request, {
|
||||
@@ -2192,7 +2184,7 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
host: {
|
||||
describe(request) {
|
||||
// TODO(step2): version should read apps/cli's package.json; placeholder for now.
|
||||
const route = defaults.defaultTarget()
|
||||
const selection = defaults.defaultModelSelection()
|
||||
return Promise.resolve(ok(request, {
|
||||
version: '0.0.1',
|
||||
// Same source as session.create's fallback: the UI's default project
|
||||
@@ -2200,8 +2192,8 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
cwd: defaults.cwd,
|
||||
// Read live for the same reason: this is what the NEXT session will
|
||||
// start from, so a saved default has to be what it reports.
|
||||
provider: route.provider,
|
||||
model: route.model,
|
||||
provider: selection.provider,
|
||||
model: selection.model,
|
||||
attachedSessions: ctx.agents.list().length,
|
||||
}))
|
||||
},
|
||||
@@ -2730,11 +2722,11 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
// A provider's own settings carry its model catalog and endpoint,
|
||||
// so a change there invalidates the model list even when the route
|
||||
// set is untouched — `llm/adapters-updated` alone misses it. The
|
||||
// gateway's own section is the other such source: it names the
|
||||
// route every session with no logged one resolves to, so an
|
||||
// Agent default section is the other such source: it names the
|
||||
// selection every session with no logged one resolves to, so an
|
||||
// externally edited default (another tab, a hand-edited
|
||||
// settings.yaml) has to reach an open selector too.
|
||||
if (modelProviderNamespaces().has(name) || name === String(API_GATEWAY_SETTINGS_NAMESPACE)) {
|
||||
if (modelProviderNamespaces().has(name) || name === String(AGENT_DEFAULT_MODEL_SETTINGS_NAMESPACE)) {
|
||||
queue.push(frame({ type: 'host/models-changed' }))
|
||||
}
|
||||
}),
|
||||
|
||||
@@ -37,7 +37,7 @@ export interface ApiProxy {
|
||||
// ---- Domain interfaces and payload entities ----
|
||||
export type {
|
||||
HistoryEntry, ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning,
|
||||
ModelReasoningEffort, ModelTarget, QueueAction, SessionModels, SessionProjectionsBlock, SessionSearchItem,
|
||||
ModelReasoningEffort, ModelSelection, QueueAction, SessionModels, SessionProjectionsBlock, SessionSearchItem,
|
||||
SessionsApi, SessionSummary,
|
||||
} from './sessions.ts'
|
||||
export type { DirectoryEntry, DirectoryListing, HostApi } from './host.ts'
|
||||
|
||||
@@ -3,8 +3,8 @@
|
||||
* surfaces. `llm.providers` merges the configurable-provider directory
|
||||
* (which providers CAN be configured, and where their settings live) with the
|
||||
* live route registry; `llm.models` is the session-independent model catalog
|
||||
* (the same groups as `session.models`, without the per-session current
|
||||
* target). Both invalidate on the `host/models-changed` frame.
|
||||
* (the same groups as `session.models`, without a per-session selection).
|
||||
* Both invalidate on the `host/models-changed` frame.
|
||||
*/
|
||||
|
||||
import type { RpcRequest, RpcResponse } from './rpc.ts'
|
||||
|
||||
@@ -12,7 +12,7 @@ import type { RequestPayload, ResponseValue } from './rpc-map.ts'
|
||||
import type { Wire } from './rpc.schema.ts'
|
||||
import type {
|
||||
HistoryEntry, ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning,
|
||||
ModelReasoningEffort, ModelTarget, SessionProjectionsBlock, SessionSearchItem, SessionSummary,
|
||||
ModelReasoningEffort, ModelSelection, SessionProjectionsBlock, SessionSearchItem, SessionSummary,
|
||||
} from './sessions.ts'
|
||||
import type { ToolEventView } from './events.ts'
|
||||
import type { WorkspaceId } from './workspace.ts'
|
||||
@@ -140,12 +140,12 @@ export const sessionHistoryRequestSchema = z.object({
|
||||
maxMessages: z.number().int().positive().optional(),
|
||||
}) satisfies z.ZodType<Wire<RequestPayload<'session.history'>>>
|
||||
|
||||
/** Complete provider/model target. */
|
||||
export const modelTargetSchema = z.object({
|
||||
/** Complete provider/model selection. */
|
||||
export const modelSelectionSchema = z.object({
|
||||
provider: z.string().min(1),
|
||||
model: z.string().min(1),
|
||||
reasoningEffort: z.string().min(1).optional(),
|
||||
}) satisfies z.ZodType<Wire<ModelTarget>>
|
||||
}) satisfies z.ZodType<Wire<ModelSelection>>
|
||||
|
||||
/** One adapter-owned reasoning effort. */
|
||||
export const modelReasoningEffortSchema = z.object({
|
||||
@@ -224,7 +224,7 @@ export const sessionModelsRequestSchema = z.object({
|
||||
|
||||
/** session.models response value. */
|
||||
export const sessionModelsValueSchema = z.object({
|
||||
current: modelTargetSchema,
|
||||
current: modelSelectionSchema,
|
||||
routable: z.boolean(),
|
||||
groups: z.array(modelProviderGroupSchema),
|
||||
failures: z.array(modelCatalogFailureSchema),
|
||||
@@ -240,7 +240,7 @@ export const sessionSelectModelRequestSchema = z.object({
|
||||
|
||||
/** session.selectModel response value. */
|
||||
export const sessionSelectModelValueSchema = z.object({
|
||||
selected: modelTargetSchema,
|
||||
selected: modelSelectionSchema,
|
||||
}) satisfies z.ZodType<Wire<ResponseValue<'session.selectModel'>>>
|
||||
|
||||
/** ContentBlock passthrough: core is merge-extensible — the type discriminant envelope is strict, the rest stays wide. */
|
||||
|
||||
@@ -53,8 +53,8 @@ export interface SessionProjectionsBlock {
|
||||
values: Partial<SessionProjectionMap>
|
||||
}
|
||||
|
||||
/** Complete model target selected for one session. */
|
||||
export interface ModelTarget {
|
||||
/** Complete model selection for one session. */
|
||||
export interface ModelSelection {
|
||||
/** Registered provider route. */
|
||||
provider: string
|
||||
/** Provider-owned model id. */
|
||||
@@ -115,8 +115,8 @@ export interface ModelCatalogFailure {
|
||||
|
||||
/** Detached model-directory snapshot for one session. */
|
||||
export interface SessionModels {
|
||||
/** Target selected for the session's next assembled step. */
|
||||
current: ModelTarget
|
||||
/** Model selection for the session's next assembled step. */
|
||||
current: ModelSelection
|
||||
/**
|
||||
* Whether an adapter currently serves `current.provider`, and therefore
|
||||
* whether this session can start a turn at all. Deliberately NOT derivable
|
||||
@@ -240,7 +240,7 @@ export interface SessionsApi {
|
||||
models(request: RpcRequest<{ sessionId: SessionId }>): Promise<RpcResponse<SessionModels>>
|
||||
|
||||
/**
|
||||
* Selects the complete target for this session. Exact model metadata
|
||||
* Selects the complete model selection for this session. Exact model metadata
|
||||
* validates an optional reasoning effort, while catalog membership remains
|
||||
* advisory. Session-backed subagents reject with `agent-busy`.
|
||||
*/
|
||||
@@ -250,7 +250,7 @@ export interface SessionsApi {
|
||||
model: string
|
||||
reasoningEffort?: string
|
||||
}>):
|
||||
Promise<RpcResponse<{ selected: ModelTarget }>>
|
||||
Promise<RpcResponse<{ selected: ModelSelection }>>
|
||||
|
||||
/**
|
||||
* Renames a session: appends a `session/title` event with the `user`
|
||||
|
||||
@@ -7,28 +7,24 @@
|
||||
* `ctx.apiProxy`). Transport-agnostic by design: this package registers no
|
||||
* routes — physical carriers wrap `ctx.apiProxy` themselves.
|
||||
*
|
||||
* The gateway also owns the `api-gateway` settings section: the route a
|
||||
* session starts from when its own log names none. The composition entry is
|
||||
* the shipped default and the section layers the user's choice over it, so
|
||||
* switching models in a conversation is what sets the default for the next
|
||||
* one. Sessions that have already logged a route are never retargeted by it.
|
||||
* The gateway consumes `ctx.agentDefaultModel`, the transport-independent default
|
||||
* shared with direct front doors. Switching models persists through that
|
||||
* service; sessions that have already logged a selection remain unchanged.
|
||||
*/
|
||||
|
||||
import { resolve } from 'node:path'
|
||||
import { Context, Service } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
import type { AgentLlmTarget } from '@deepseek-ai/dsh-agent'
|
||||
import { ReasoningEffortId } from '@deepseek-ai/dsh-llm'
|
||||
import { installSettingsSection } from '@deepseek-ai/dsh-settings'
|
||||
import type {} from '@deepseek-ai/dsh-agent-default-model'
|
||||
import type { ApiProxy } from './api/index.ts'
|
||||
import { API_GATEWAY_SETTINGS_NAMESPACE, createApiProxy } from './api-proxy.ts'
|
||||
import { createApiProxy } from './api-proxy.ts'
|
||||
|
||||
export type * from './api/index.ts'
|
||||
export { RpcId } from './api/rpc.ts'
|
||||
export { toFetchHandler } from './fetch/handler.ts'
|
||||
export { AbstractApiClient, InProcessApiClient } from './fetch/client.ts'
|
||||
export type { IApiClient } from './fetch/client.ts'
|
||||
export { API_GATEWAY_SETTINGS_NAMESPACE, createApiProxy } from './api-proxy.ts'
|
||||
export { createApiProxy } from './api-proxy.ts'
|
||||
export type { ApiProxyDefaults } from './api-proxy.ts'
|
||||
|
||||
declare module 'cordis' {
|
||||
@@ -38,62 +34,12 @@ declare module 'cordis' {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* The `api-gateway` settings section: the route a session starts from when its
|
||||
* own log names none. `workspaceRoot` is deliberately not part of it — that is
|
||||
* a launcher fact, not a preference.
|
||||
*/
|
||||
export interface DefaultRouteSettings {
|
||||
/** Default provider route for created agents. */
|
||||
provider: string
|
||||
/** Default model id. */
|
||||
model: string
|
||||
/** Default reasoning effort; absence preserves the adapter/provider default. */
|
||||
reasoningEffort?: string
|
||||
}
|
||||
|
||||
/**
|
||||
* Gateway plugin config: host-level agent routing and Workspace creation root.
|
||||
*
|
||||
* `reasoningEffort` is deliberately absent, so the section carries one field
|
||||
* the composition cannot. The seam resolves a section by MERGING the user
|
||||
* layer over the composition entry per field, and an absent key cannot
|
||||
* override a present one — so a composition-set effort would survive every
|
||||
* later switch to a model that has none, and strand it for the next session
|
||||
* to fail on. Effort is a per-model fact anyway: a deployment default belongs
|
||||
* on the adapter profile (`llm-pi-ai`'s `reasoning`, `llm-deepseek`'s own),
|
||||
* which resolves per model rather than per gateway.
|
||||
*/
|
||||
/** Gateway plugin config: the Host-only Workspace creation root. */
|
||||
export interface Config {
|
||||
/** Default provider route for created agents. */
|
||||
provider: string
|
||||
/** Default model id. */
|
||||
model: string
|
||||
/** Parent directory for name-created Workspaces; defaults to the Host cwd. */
|
||||
workspaceRoot?: string
|
||||
}
|
||||
|
||||
/**
|
||||
* Schema of the `api-gateway` section, exported because it IS that section's
|
||||
* contract — the shape anything reading or writing `settings.yaml` addresses.
|
||||
*/
|
||||
export const DEFAULT_ROUTE_SCHEMA: z<DefaultRouteSettings> = z.object({
|
||||
provider: z.string().required(),
|
||||
model: z.string().required(),
|
||||
reasoningEffort: z.string(),
|
||||
})
|
||||
|
||||
/** Project the stored/composed section onto the agent-facing target shape. */
|
||||
function routeTarget(settings: DefaultRouteSettings): AgentLlmTarget {
|
||||
return {
|
||||
provider: settings.provider,
|
||||
model: settings.model,
|
||||
...settings.reasoningEffort === undefined
|
||||
? {}
|
||||
: { reasoningEffort: ReasoningEffortId(settings.reasoningEffort) },
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* The API gateway service: implements the ApiProxy contract over the composed
|
||||
* host context and provides it as `ctx.apiProxy`. The Host cwd is the default
|
||||
@@ -101,13 +47,11 @@ function routeTarget(settings: DefaultRouteSettings): AgentLlmTarget {
|
||||
*/
|
||||
export class ApiProxyService extends Service implements ApiProxy {
|
||||
static inject = [
|
||||
'agents', 'directoryPicker', 'llm', 'sessions', 'subagents', 'sessionQuery',
|
||||
'agentDefaultModel', 'agents', 'directoryPicker', 'llm', 'sessions', 'subagents', 'sessionQuery',
|
||||
'tools', 'userInteraction', 'workspace',
|
||||
]
|
||||
|
||||
static Config: z<Config> = z.object({
|
||||
provider: z.string().required(),
|
||||
model: z.string().required(),
|
||||
workspaceRoot: z.string(),
|
||||
})
|
||||
|
||||
@@ -127,30 +71,9 @@ export class ApiProxyService extends Service implements ApiProxy {
|
||||
constructor(ctx: Context, config: Config) {
|
||||
super(ctx, 'apiProxy')
|
||||
const cwd = process.cwd()
|
||||
// The composition entry is the shipped default; the settings section
|
||||
// layers the user's own choice over it, and a deployment without a
|
||||
// settings provider simply keeps the entry.
|
||||
const entry: DefaultRouteSettings = { provider: config.provider, model: config.model }
|
||||
let route: () => DefaultRouteSettings = () => entry
|
||||
installSettingsSection(ctx, API_GATEWAY_SETTINGS_NAMESPACE, DEFAULT_ROUTE_SCHEMA, entry, {
|
||||
setSource: (current) => {
|
||||
route = current
|
||||
},
|
||||
// Nothing registration-level derives from the default: every consumer
|
||||
// reads it through the thunk at the moment it needs a route.
|
||||
onChange: () => {},
|
||||
})
|
||||
const api = createApiProxy(ctx, {
|
||||
defaultTarget: () => routeTarget(route()),
|
||||
// Wholesale, never a merge: switching to a model with no reasoning
|
||||
// effort must clear a stored one, and a merged patch would strand it
|
||||
// for the next session to fail on. This clears it because the entry
|
||||
// below the user layer carries no effort to re-inherit — the reason
|
||||
// `Config` deliberately has no such field. The section holds no
|
||||
// secrets, so there is nothing a replace can collaterally drop.
|
||||
persistDefaultTarget: async (target) => {
|
||||
await ctx.get('settings')?.replace(API_GATEWAY_SETTINGS_NAMESPACE, target)
|
||||
},
|
||||
defaultModelSelection: () => ctx.agentDefaultModel.currentSelection(),
|
||||
saveDefaultModelSelection: selection => ctx.agentDefaultModel.saveSelection(selection),
|
||||
cwd,
|
||||
workspaceRoot: resolve(config.workspaceRoot ?? cwd),
|
||||
})
|
||||
|
||||
@@ -27,7 +27,7 @@ async function harness(): Promise<{ ctx: Context; api: ApiProxy }> {
|
||||
await ctx.plugin(UserInteractionService)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(ApprovalService)
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
return { ctx, api }
|
||||
}
|
||||
|
||||
@@ -217,7 +217,7 @@ describe('approval pending registry', () => {
|
||||
await ctx.plugin(ApprovalService)
|
||||
let api!: ApiProxy
|
||||
const fiber = ctx.plugin(Object.assign((fiberCtx: Context) => {
|
||||
api = createApiProxy(fiberCtx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
api = createApiProxy(fiberCtx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
}, { inject: ['sessions', 'agents', 'userInteraction', 'approval'] }))
|
||||
await fiber.await()
|
||||
const abort = new AbortController()
|
||||
|
||||
@@ -35,7 +35,7 @@ async function harness(): Promise<{ ctx: Context; api: ApiProxy; attach: (sessio
|
||||
await ctx.plugin(AgentRegistry)
|
||||
return {
|
||||
ctx,
|
||||
api: createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }),
|
||||
api: createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }),
|
||||
attach: (session) => {
|
||||
ctx.agents.register({ id: session.id, session, status: 'idle', ctx } as Agent)
|
||||
},
|
||||
|
||||
@@ -64,7 +64,7 @@ describe('sessions.list cold merge', () => {
|
||||
return undefined
|
||||
},
|
||||
})
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
const response = await api.sessions.list(request({}))
|
||||
expect(response.result.ok).toBe(true)
|
||||
@@ -92,7 +92,7 @@ describe('attached updatedAt excludes end-seed', () => {
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(UserInteractionService)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
// Old work, resumed just now: the log tail would report the pickup.
|
||||
const worked = 1_000_000
|
||||
@@ -150,7 +150,7 @@ describe('cold history recovery view', () => {
|
||||
inspect: (id: SessionId, signal?: AbortSignal) => coordinator.inspect(id, signal),
|
||||
locate: () => undefined,
|
||||
} as never)
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
const history = await api.sessions.history(request({ sessionId, beforeSeq: 2, maxMessages: 10 }))
|
||||
if (!history.result.ok) throw new Error('history failed')
|
||||
@@ -206,7 +206,7 @@ describe('Remote Agent and Session lookup policy', () => {
|
||||
})
|
||||
const defaultAgentLookup = ctx.typert.lookups.get('agent')
|
||||
const defaultSessionLookup = ctx.typert.lookups.get('session')
|
||||
createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
await vi.waitFor(() => {
|
||||
expect(ctx.typert.lookups.get('agent')).not.toBe(defaultAgentLookup)
|
||||
expect(ctx.typert.lookups.get('session')).not.toBe(defaultSessionLookup)
|
||||
@@ -250,7 +250,7 @@ describe('Remote Agent and Session lookup policy', () => {
|
||||
const resume = vi.spyOn(ctx.agents, 'resume')
|
||||
const defaultAgentLookup = ctx.typert.lookups.get('agent')
|
||||
const defaultSessionLookup = ctx.typert.lookups.get('session')
|
||||
createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
await vi.waitFor(() => {
|
||||
expect(ctx.typert.lookups.get('agent')).not.toBe(defaultAgentLookup)
|
||||
expect(ctx.typert.lookups.get('session')).not.toBe(defaultSessionLookup)
|
||||
@@ -312,7 +312,7 @@ describe('subagent ownership fence', () => {
|
||||
locate: () => undefined,
|
||||
} as never)
|
||||
const resume = vi.spyOn(ctx.agents, 'resume')
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
const history = await api.sessions.history(request({ sessionId }))
|
||||
expect(history.result.ok).toBe(true)
|
||||
@@ -371,7 +371,7 @@ describe('subagent ownership fence', () => {
|
||||
// instead of answering `agent-busy`.
|
||||
const resume = vi.spyOn(ctx.agents, 'resume')
|
||||
.mockRejectedValue(new Error('registry unavailable in this bench'))
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
const prompt = await api.sessions.prompt(request({
|
||||
sessionId,
|
||||
@@ -412,7 +412,7 @@ describe('subagent ownership fence', () => {
|
||||
})
|
||||
const startingChild = { id: startingSession.id, session: startingSession, status: 'idle', ctx } as Agent
|
||||
ctx.agents.enter(startingChild, parent)
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
const stopped = await api.sessions.cancel(request({ sessionId: originChild.id }))
|
||||
expect(stopped.result.ok).toBe(false)
|
||||
@@ -458,7 +458,7 @@ describe('subagent ownership fence', () => {
|
||||
const followup = vi.fn()
|
||||
const agent = { id: session.id, session, status: 'idle', ctx, followup } as unknown as Agent
|
||||
ctx.agents.register(agent)
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
const response = await api.sessions.prompt(request({
|
||||
sessionId: agent.id,
|
||||
@@ -476,7 +476,7 @@ describe('degenerate composition (no persistence, no factory)', () => {
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(UserInteractionService)
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
const listed = await api.sessions.list(request({}))
|
||||
expect(listed.result.ok).toBe(true)
|
||||
@@ -501,7 +501,7 @@ describe('degenerate composition (no persistence, no factory)', () => {
|
||||
list: () => Promise.resolve([]),
|
||||
inspect,
|
||||
} as never)
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
const response = await api.sessions.history(request({ sessionId: sid('session-missing') }))
|
||||
expect(response.result.ok).toBe(false)
|
||||
@@ -527,7 +527,7 @@ describe('sessions.prompt synchronous rejection', () => {
|
||||
followup: () => { throw new Error('agent "session-throwing" lifecycle disposed') },
|
||||
steer: () => { throw new Error('agent "session-throwing" lifecycle disposed') },
|
||||
} as unknown as Agent)
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
for (const mode of ['queue', 'steer'] as const) {
|
||||
const response = await api.sessions.prompt(request({
|
||||
@@ -571,7 +571,7 @@ describe('sessions.prompt synchronous rejection', () => {
|
||||
ctx.agents.register(child)
|
||||
throw new Error('session id already published')
|
||||
})
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
const models = await api.sessions.models(request({ sessionId }))
|
||||
expect(models.result.ok).toBe(false)
|
||||
|
||||
@@ -25,7 +25,7 @@ import type { RpcRequest, RpcResponse } from '../src/api/rpc.ts'
|
||||
import { RpcId } from '../src/api/rpc.ts'
|
||||
import { createApiProxy } from '../src/api-proxy.ts'
|
||||
|
||||
const DEFAULTS = { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }
|
||||
const DEFAULTS = { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }
|
||||
|
||||
function request<P>(payload: P): RpcRequest<P> {
|
||||
return { rpcId: RpcId(`req-${String(nextRpc++)}`), payload }
|
||||
|
||||
@@ -22,9 +22,10 @@ import type { CredentialInfo, CredentialRef, ResolvedCredential } from '@deepsee
|
||||
import type { HostFrame } from '../src/api/index.ts'
|
||||
import type { RpcRequest, RpcResponse } from '../src/api/rpc.ts'
|
||||
import { RpcId } from '../src/api/rpc.ts'
|
||||
import { API_GATEWAY_SETTINGS_NAMESPACE, createApiProxy } from '../src/api-proxy.ts'
|
||||
import { AGENT_DEFAULT_MODEL_SETTINGS_NAMESPACE } from '@deepseek-ai/dsh-agent-default-model'
|
||||
import { createApiProxy } from '../src/api-proxy.ts'
|
||||
|
||||
const DEFAULTS = { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }
|
||||
const DEFAULTS = { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }
|
||||
|
||||
let nextRpc = 1
|
||||
function request<P>(payload: P): RpcRequest<P> {
|
||||
@@ -398,21 +399,21 @@ describe('settings domain', () => {
|
||||
expect(frames).toEqual([{ type: 'host/settings-changed', ns: 'permission' }])
|
||||
})
|
||||
|
||||
it('invalidates the model catalog when the gateway default route changes', async () => {
|
||||
it('invalidates the model catalog when the Agent default selection changes', async () => {
|
||||
const ctx = await harness()
|
||||
const route = ctx.settings.register(API_GATEWAY_SETTINGS_NAMESPACE, z.object({
|
||||
const defaultModel = ctx.settings.register(AGENT_DEFAULT_MODEL_SETTINGS_NAMESPACE, z.object({
|
||||
provider: z.string().required(),
|
||||
model: z.string().required(),
|
||||
}), { base: { provider: 'deepseek-official', model: 'deepseek-v4-flash' } })
|
||||
const api = createApiProxy(ctx, DEFAULTS)
|
||||
// The gateway's own section names the route every session with no logged
|
||||
// one resolves to, so an externally edited default — another tab, a
|
||||
// The shared section names the selection every blank session resolves to,
|
||||
// so an externally edited default — another tab, a
|
||||
// hand-edited settings.yaml — has to reach an open selector as well.
|
||||
const frames = await collectHost(api, ['host/settings-changed', 'host/models-changed'], 2, async () => {
|
||||
await route.replace({ provider: 'deepseek-official', model: 'deepseek-reasoner' })
|
||||
await defaultModel.replace({ provider: 'deepseek-official', model: 'deepseek-reasoner' })
|
||||
})
|
||||
expect(frames).toEqual([
|
||||
{ type: 'host/settings-changed', ns: 'api-gateway' },
|
||||
{ type: 'host/settings-changed', ns: 'agent-default-model' },
|
||||
{ type: 'host/models-changed' },
|
||||
])
|
||||
})
|
||||
|
||||
@@ -1,108 +0,0 @@
|
||||
/**
|
||||
* The `api-gateway` settings section over a REAL settings provider: the
|
||||
* composition entry as the base layer, the wholesale replace the gateway
|
||||
* persists with, and the fallback when the provider detaches. The other model
|
||||
* specs drive hand-rolled `defaultTarget`/`persistDefaultTarget` closures, so
|
||||
* this is the only place the layering itself is exercised.
|
||||
*/
|
||||
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import { Settings, installSettingsSection } from '@deepseek-ai/dsh-settings'
|
||||
import type { SettingsNamespace } from '@deepseek-ai/dsh-settings'
|
||||
import { API_GATEWAY_SETTINGS_NAMESPACE, DEFAULT_ROUTE_SCHEMA } from '../src/index.ts'
|
||||
import type { DefaultRouteSettings } from '../src/index.ts'
|
||||
|
||||
/** The smallest real provider: one in-memory document, always writable. */
|
||||
class MemorySettings extends Settings {
|
||||
doc: Record<string, unknown> = {}
|
||||
|
||||
get writable(): boolean {
|
||||
return true
|
||||
}
|
||||
|
||||
protected load(): Promise<Record<string, unknown>> {
|
||||
return Promise.resolve(structuredClone(this.doc))
|
||||
}
|
||||
|
||||
protected persist(ns: SettingsNamespace, section: Record<string, unknown>): Promise<void> {
|
||||
this.doc = { ...this.doc, [ns]: structuredClone(section) }
|
||||
return Promise.resolve()
|
||||
}
|
||||
}
|
||||
|
||||
/** Mount the gateway's own section wiring over a live provider. */
|
||||
async function boot(entry: DefaultRouteSettings) {
|
||||
const ctx = new Context()
|
||||
const fiber = ctx.plugin(MemorySettings)
|
||||
await fiber.await()
|
||||
let route: () => DefaultRouteSettings = () => entry
|
||||
const consumer = ctx.plugin(function section(child: Context) {
|
||||
installSettingsSection(child, API_GATEWAY_SETTINGS_NAMESPACE, DEFAULT_ROUTE_SCHEMA, entry, {
|
||||
setSource: (current) => { route = current },
|
||||
onChange: () => {},
|
||||
})
|
||||
})
|
||||
await consumer.await()
|
||||
const settings = ctx.get('settings')
|
||||
if (settings === undefined) throw new Error('settings provider did not mount')
|
||||
return { ctx, fiber, consumer, settings, read: () => route() }
|
||||
}
|
||||
|
||||
describe('the api-gateway default-route section', () => {
|
||||
it('resolves the composition entry until the user layer overrides it', async () => {
|
||||
const bench = await boot({ provider: 'deepseek-official', model: 'deepseek-v4-flash' })
|
||||
expect(bench.read()).toEqual({ provider: 'deepseek-official', model: 'deepseek-v4-flash' })
|
||||
|
||||
await bench.settings.replace(API_GATEWAY_SETTINGS_NAMESPACE, {
|
||||
provider: 'acme-gateway', model: 'acme-large', reasoningEffort: 'high',
|
||||
})
|
||||
expect(bench.read()).toEqual({
|
||||
provider: 'acme-gateway', model: 'acme-large', reasoningEffort: 'high',
|
||||
})
|
||||
await bench.ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('clears a stored effort when the next switch has none', async () => {
|
||||
const bench = await boot({ provider: 'deepseek-official', model: 'deepseek-v4-flash' })
|
||||
await bench.settings.replace(API_GATEWAY_SETTINGS_NAMESPACE, {
|
||||
provider: 'acme-gateway', model: 'acme-large', reasoningEffort: 'high',
|
||||
})
|
||||
expect(bench.read().reasoningEffort).toBe('high')
|
||||
|
||||
// The whole reason the gateway persists with `replace` rather than a merge
|
||||
// patch — and the reason `Config` carries no effort for the base layer to
|
||||
// re-inherit here. A stranded effort would fail the next session's first
|
||||
// request against a model that does not support it.
|
||||
await bench.settings.replace(API_GATEWAY_SETTINGS_NAMESPACE, {
|
||||
provider: 'acme-gateway', model: 'acme-plain',
|
||||
})
|
||||
expect(bench.read()).toEqual({ provider: 'acme-gateway', model: 'acme-plain' })
|
||||
await bench.ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('layers a hand-written partial section over the entry', async () => {
|
||||
const bench = await boot({ provider: 'deepseek-official', model: 'deepseek-v4-flash' })
|
||||
// Someone editing settings.yaml by hand may name only the model. The
|
||||
// entry supplies the provider, which is what makes this legal — and is
|
||||
// exactly why an effort in the entry could never be cleared, so there
|
||||
// is none to inherit.
|
||||
await bench.settings.replace(API_GATEWAY_SETTINGS_NAMESPACE, { model: 'deepseek-reasoner' })
|
||||
expect(bench.read()).toEqual({ provider: 'deepseek-official', model: 'deepseek-reasoner' })
|
||||
await bench.ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('falls back to the composition entry when the provider detaches', async () => {
|
||||
const bench = await boot({ provider: 'deepseek-official', model: 'deepseek-v4-flash' })
|
||||
await bench.settings.replace(API_GATEWAY_SETTINGS_NAMESPACE, {
|
||||
provider: 'acme-gateway', model: 'acme-large',
|
||||
})
|
||||
expect(bench.read().provider).toBe('acme-gateway')
|
||||
|
||||
// A deployment that loses its settings provider keeps serving the route it
|
||||
// was composed with rather than the one it can no longer read.
|
||||
await bench.fiber.dispose()
|
||||
expect(bench.read()).toEqual({ provider: 'deepseek-official', model: 'deepseek-v4-flash' })
|
||||
await bench.ctx.fiber.dispose()
|
||||
})
|
||||
})
|
||||
@@ -82,7 +82,7 @@ function liveAgent(
|
||||
}
|
||||
|
||||
const api = (ctx: Context) => createApiProxy(ctx, {
|
||||
defaultTarget: () => ({ provider: 'default-provider', model: 'default-model' }),
|
||||
defaultModelSelection: () => ({ provider: 'default-provider', model: 'default-model' }),
|
||||
cwd: '/tmp',
|
||||
workspaceRoot: '/tmp',
|
||||
})
|
||||
@@ -254,7 +254,7 @@ describe('sessions.fork', () => {
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('installs the latest logged model target before the child can run', async () => {
|
||||
it('installs the latest logged model selection before the child can run', async () => {
|
||||
const ctx = await composed()
|
||||
const source = liveAgent(ctx, 'session-routed', 1)
|
||||
source.append('request/header', {
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/**
|
||||
* Web session model-directory and selection behavior: dynamic provider grouping,
|
||||
* provider-local catalog failures, logged-target restoration without stale
|
||||
* provider-local catalog failures, logged-selection restoration without stale
|
||||
* catalog injection, advisory pass-through models, and the prompt-assembly
|
||||
* boundary for a running selection change.
|
||||
*/
|
||||
@@ -119,13 +119,13 @@ function expectValue<T>(response: { result: { ok: true; value: T } | { ok: false
|
||||
}
|
||||
|
||||
describe('Web session model selection', () => {
|
||||
it('groups successful providers and leaves an unlisted current target out of the catalog', async () => {
|
||||
it('groups successful providers and leaves an unlisted current selection out of the catalog', async () => {
|
||||
const { ctx, sessionId } = await harness({
|
||||
provider: 'deepseek-official',
|
||||
model: 'private-preview',
|
||||
reasoningEffort: ReasoningEffortId('max'),
|
||||
})
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'deepseek-official', model: 'deepseek-chat' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'deepseek-official', model: 'deepseek-chat' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
const catalog = expectValue(await api.sessions.models(request({ sessionId })))
|
||||
expect(catalog.current).toEqual({
|
||||
@@ -160,7 +160,7 @@ describe('Web session model selection', () => {
|
||||
|
||||
it('accepts an advisory-unlisted model, rejects an unavailable provider, and switches only after the next assembly', async () => {
|
||||
const { ctx, agent, sessionId } = await harness()
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'deepseek-official', model: 'deepseek-chat' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'deepseek-official', model: 'deepseek-chat' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const seed: LlmCallConfig = { provider: 'seed', model: 'seed', temperature: 0.2 }
|
||||
const signal = new AbortController().signal
|
||||
|
||||
@@ -226,11 +226,11 @@ describe('Web session model selection', () => {
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('reads the host default live for a session whose log names no route', async () => {
|
||||
it('reads the Agent default live for a session whose log names no selection', async () => {
|
||||
const { ctx, sessionId } = await harness()
|
||||
let stored = { provider: 'deepseek-official', model: 'deepseek-chat' }
|
||||
const api = createApiProxy(ctx, {
|
||||
defaultTarget: () => stored,
|
||||
defaultModelSelection: () => stored,
|
||||
cwd: '/tmp',
|
||||
workspaceRoot: '/tmp',
|
||||
})
|
||||
@@ -248,14 +248,14 @@ describe('Web session model selection', () => {
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('keeps a session that logged a route on it when the host default moves', async () => {
|
||||
it('keeps a session on its logged selection when the Agent default differs', async () => {
|
||||
const { ctx, sessionId } = await harness({
|
||||
provider: 'deepseek-official',
|
||||
model: 'deepseek-chat',
|
||||
})
|
||||
let stored = { provider: 'deepseek-official', model: 'deepseek-chat' }
|
||||
const api = createApiProxy(ctx, {
|
||||
defaultTarget: () => stored,
|
||||
defaultModelSelection: () => stored,
|
||||
cwd: '/tmp',
|
||||
workspaceRoot: '/tmp',
|
||||
})
|
||||
@@ -271,9 +271,9 @@ describe('Web session model selection', () => {
|
||||
const saved: unknown[] = []
|
||||
let reject = false
|
||||
const api = createApiProxy(ctx, {
|
||||
defaultTarget: () => ({ provider: 'deepseek-official', model: 'deepseek-chat' }),
|
||||
persistDefaultTarget: (target) => {
|
||||
saved.push(target)
|
||||
defaultModelSelection: () => ({ provider: 'deepseek-official', model: 'deepseek-chat' }),
|
||||
saveDefaultModelSelection: (selection) => {
|
||||
saved.push(selection)
|
||||
return reject ? Promise.reject(new Error('read-only document')) : Promise.resolve()
|
||||
},
|
||||
cwd: '/tmp',
|
||||
@@ -306,7 +306,7 @@ describe('Web session model selection', () => {
|
||||
it('refuses a prompt no adapter can route, and reports it on the directory', async () => {
|
||||
const { ctx, sessionId } = await harness()
|
||||
const api = createApiProxy(ctx, {
|
||||
defaultTarget: () => ({ provider: 'deleted-gateway', model: 'deleted-model' }),
|
||||
defaultModelSelection: () => ({ provider: 'deleted-gateway', model: 'deleted-model' }),
|
||||
cwd: '/tmp',
|
||||
workspaceRoot: '/tmp',
|
||||
})
|
||||
@@ -339,7 +339,7 @@ describe('Web session model selection', () => {
|
||||
const api = createApiProxy(ctx, {
|
||||
// What a Models-page removal leaves behind: the settings document still
|
||||
// names the route the user last picked, and nothing serves it.
|
||||
defaultTarget: () => ({ provider: 'deleted-gateway', model: 'deleted-model' }),
|
||||
defaultModelSelection: () => ({ provider: 'deleted-gateway', model: 'deleted-model' }),
|
||||
cwd: '/tmp',
|
||||
workspaceRoot: '/tmp',
|
||||
})
|
||||
|
||||
@@ -68,7 +68,7 @@ function seedMessages(session: Session, count: number): void {
|
||||
}
|
||||
}
|
||||
|
||||
const api = (ctx: Context) => createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = (ctx: Context) => createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
describe('session.history projections block', () => {
|
||||
it('serves the unit value on the tail page with asOfSeq = last event seq', async () => {
|
||||
|
||||
@@ -14,7 +14,7 @@ async function harness(): Promise<{ ctx: Context; api: ApiProxy }> {
|
||||
await ctx.plugin(UserInteractionService)
|
||||
return {
|
||||
ctx,
|
||||
api: createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }),
|
||||
api: createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }),
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -68,7 +68,7 @@ function liveAgent(ctx: Context, id: string, turns: number): Session {
|
||||
return session
|
||||
}
|
||||
|
||||
const api = (ctx: Context) => createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = (ctx: Context) => createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
|
||||
describe('sessions.rename', () => {
|
||||
it('accepts through the composed title service: normalized user-source event, echoed seq', async () => {
|
||||
|
||||
@@ -27,7 +27,7 @@ vi.mock('node:fs/promises', async (importOriginal) => {
|
||||
})
|
||||
|
||||
const sid = (value: string): SessionId => value as SessionId
|
||||
const defaults = { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }
|
||||
const defaults = { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }
|
||||
|
||||
function request(query: string): RpcRequest<{ query: string }> {
|
||||
return { rpcId: RpcId(`search-${query}`), payload: { query } }
|
||||
|
||||
@@ -95,7 +95,7 @@ function bench(options: {
|
||||
ctx.provide('sessionProjections', { snapshot, restore, onChanged: () => () => {} })
|
||||
ctx.provide('userInteraction', { registerProvider: () => () => {} })
|
||||
const api = createApiProxy(ctx, {
|
||||
defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp',
|
||||
defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp',
|
||||
})
|
||||
return { api, getAgent, listChildren, inspect, snapshot, restore, followup, interrupt, parent }
|
||||
}
|
||||
|
||||
@@ -105,7 +105,7 @@ async function collect(iterable: AsyncIterable<RpcRequest<MuxFrame>>, count: num
|
||||
describe('mux live view computation', () => {
|
||||
it('attaches the three standard card views, omits view without a presenter, soft-falls on throw', async () => {
|
||||
const { ctx } = await harness()
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const abort = new AbortController()
|
||||
const stream = api.events.mux({ rpcId: RpcId('t-mux'), payload: {} }, abort.signal)
|
||||
const collected = collect(stream, 9, abort)
|
||||
@@ -170,7 +170,7 @@ describe('mux live view computation', () => {
|
||||
|
||||
it('serves history entries with call/result views, backscan pairing, and soft-falls', async () => {
|
||||
const { ctx } = await harness()
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const session = ctx.sessions.create()
|
||||
// history resolves the agent first; a live structural stub is enough (only
|
||||
// .session is read on this path).
|
||||
@@ -238,7 +238,7 @@ describe('mux live view computation', () => {
|
||||
|
||||
it('counts only append-origin messages toward maxMessages and keeps compaction provenance whole', async () => {
|
||||
const { ctx } = await harness()
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const session = ctx.sessions.create()
|
||||
ctx.agents.register({ id: session.id, session, status: 'idle', ctx } as Agent)
|
||||
session.append('turn/start', { turn: 1 })
|
||||
@@ -287,7 +287,7 @@ describe('mux live view computation', () => {
|
||||
|
||||
it('drops a disposed session from the live open-call table (result after dispose gets no view)', async () => {
|
||||
const { ctx } = await harness()
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const abort = new AbortController()
|
||||
const stream = api.events.mux({ rpcId: RpcId('t-mux3'), payload: {} }, abort.signal)
|
||||
|
||||
@@ -308,7 +308,7 @@ describe('mux live view computation', () => {
|
||||
|
||||
it('pairs a result after turn/end via the in-memory backscan fallback', async () => {
|
||||
const { ctx } = await harness()
|
||||
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const api = createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
const abort = new AbortController()
|
||||
const stream = api.events.mux({ rpcId: RpcId('t-mux2'), payload: {} }, abort.signal)
|
||||
const collected = collect(stream, 4, abort)
|
||||
|
||||
@@ -100,7 +100,7 @@ async function harness(
|
||||
// object per harness mirrors the seam's stability contract.
|
||||
ctx.provide('directoryPicker', { capability: () => picker } as never)
|
||||
const api = createApiProxy(ctx, {
|
||||
defaultTarget: () => ({ provider: 'test', model: 'test-model' }),
|
||||
defaultModelSelection: () => ({ provider: 'test', model: 'test-model' }),
|
||||
cwd: workspaceRoot,
|
||||
workspaceRoot,
|
||||
...extras.openPath === undefined ? {} : { openPath: extras.openPath },
|
||||
|
||||
@@ -41,7 +41,7 @@ function scriptedApi(overrides: {
|
||||
history: r => ok(r, {
|
||||
events: [],
|
||||
hasMore: false,
|
||||
modelTarget: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
|
||||
modelSelection: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
|
||||
}),
|
||||
models: r => ok(r, {
|
||||
current: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
|
||||
|
||||
@@ -192,7 +192,7 @@ describe('sessions domain schemas', () => {
|
||||
expect(sessionHistoryValueSchema.parse({
|
||||
events: [],
|
||||
hasMore: false,
|
||||
modelTarget: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
|
||||
modelSelection: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
|
||||
}).hasMore).toBe(false)
|
||||
expect(sessionModelsRequestSchema.parse({ sessionId: 's1' }).sessionId).toBe('s1')
|
||||
expect(sessionModelsValueSchema.parse({
|
||||
|
||||
@@ -35,6 +35,9 @@
|
||||
{
|
||||
"path": "../../core/agent"
|
||||
},
|
||||
{
|
||||
"path": "../../core/agent-default-model"
|
||||
},
|
||||
{
|
||||
"path": "../../core/session"
|
||||
},
|
||||
|
||||
Reference in New Issue
Block a user