dsh-github-copilot 0.4.0-alpha.80 → 0.4.0-alpha.81
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/AGENTS.md +12 -0
- package/CHANGELOG.md +7 -0
- package/README.md +12 -8
- package/README.zh.md +12 -8
- package/deployment-baseline.json +15 -2
- package/docs/auto-task-routing.md +114 -0
- package/docs/automatic-model-routing.md +28 -21
- package/lib/client.js +97 -9
- package/lib/client.js.map +1 -1
- package/lib/index.js +446 -150
- package/lib/remote.js +53 -1
- package/lib/types/account-model-catalog.d.ts +3 -0
- package/lib/types/auto-model-host.d.ts +4 -0
- package/lib/types/auto-model-routing.d.ts +15 -3
- package/lib/types/auto-selection-explanation.d.ts +8 -0
- package/lib/types/auto-task-assessment.d.ts +45 -0
- package/lib/types/auto-task-classifier.d.ts +7 -0
- package/lib/types/config.d.ts +2 -0
- package/lib/types/preview-route.d.ts +1 -1
- package/lib/types/remote.d.ts +1 -1
- package/lib/types/turn-selection.d.ts +52 -0
- package/package.json +2 -1
package/AGENTS.md
CHANGED
|
@@ -240,6 +240,18 @@ Never say GPT-6/search works merely because settings, typecheck or a package imp
|
|
|
240
240
|
|
|
241
241
|
## Changing capabilities
|
|
242
242
|
|
|
243
|
+
Auto task routing (#258) uses current `model_picker_category` facts, never model
|
|
244
|
+
names, effort or context capacity as a quality category. Hard eligibility/input
|
|
245
|
+
fit precede task/preference policy; unknown category and uncertain task evidence
|
|
246
|
+
remain explicit. Keep suitable previous-model continuity and equal-weight
|
|
247
|
+
tie-breaking within the first available category. Capture actual reasons once
|
|
248
|
+
per turn without durable decision events or changing Usage. The optional
|
|
249
|
+
`autoSemanticAssessment` experiment is off by default: one bounded concrete
|
|
250
|
+
native-adapter request, no tools/Auto recursion/new retry, explicit failures and
|
|
251
|
+
omitted-context conservatism. Extra supplier charges are separate from Chat
|
|
252
|
+
Usage. Require labeled-corpus calibration before enabling by default; synthetic
|
|
253
|
+
tests do not prove GitHub-private routing equivalence. See `docs/auto-task-routing.md`.
|
|
254
|
+
|
|
243
255
|
The turn selection Host endpoint must use `TurnSelectionController`, extending
|
|
244
256
|
public `TypertRemoteService` with `@Remote get`. A plain `ctx.provide` object
|
|
245
257
|
cannot supply the native gateway binding or source method discovery. Test both
|
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,12 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 0.4.0-alpha.81 (prepared)
|
|
4
|
+
|
|
5
|
+
- Route Auto through current supplier Powerful/Versatile/Lightweight categories and contextual task evidence instead of advertised-capacity bands (#258). Preserve hard input/image/exclusion/account admission and native no-fit recovery.
|
|
6
|
+
- Use Lightweight for isolated greetings even with Intelligence, retain capable targets for short hard work, prefer suitable previous-model continuity, and distribute only equal-category candidates.
|
|
7
|
+
- Explain the actual captured turn choice, category fallback and continuity/tie-break in the footer; old records explicitly lack detailed reasons rather than displaying generic reconstructed text.
|
|
8
|
+
- Add an off-by-default bounded semantic-assessment experiment through the existing native adapter. Strict output, omitted-context conservatism, cancellation and diagnostic fallback remain; extra calls add latency and supplier charges outside native Chat Usage. Synthetic tests do not establish calibrated accuracy or GitHub-private parity.
|
|
9
|
+
|
|
3
10
|
## 0.4.0-alpha.80 (prepared)
|
|
4
11
|
|
|
5
12
|
- Observe real HTTP/SSE byte progress on managed requests, retaining the original five-minute byte-idle bound while allowing at most ten minutes without a native assistant chunk (#253).
|
package/README.md
CHANGED
|
@@ -108,7 +108,7 @@ The Host reads GitHub's internal quota endpoint using the existing canonical OAu
|
|
|
108
108
|
|
|
109
109
|
## Install and sign in
|
|
110
110
|
|
|
111
|
-
The commands below target the package version `0.4.0-alpha.
|
|
111
|
+
The commands below target the package version `0.4.0-alpha.81`. Versioned URLs describe the intended release artifacts, not proof that publication or local activation has completed; use them only once that Release and its checksums are available. Install into the profile you use (replace `web` when targeting another profile):
|
|
112
112
|
|
|
113
113
|
Before installing/updating, unpack the **checksum-verified** archive into a temporary directory and run its read-only composition preflight (replace all paths with absolute paths for the intended profile):
|
|
114
114
|
|
|
@@ -121,10 +121,10 @@ Include any launcher patch files with repeated `--patch /absolute/file` argument
|
|
|
121
121
|
For a standalone named profile only, the supported CLI command is:
|
|
122
122
|
|
|
123
123
|
```sh
|
|
124
|
-
dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.
|
|
124
|
+
dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.81/dsh-github-copilot-0.4.0-alpha.81.tgz
|
|
125
125
|
```
|
|
126
126
|
|
|
127
|
-
For Desktop profiles, use Desktop's native package manager with `dsh-github-copilot@0.4.0-alpha.
|
|
127
|
+
For Desktop profiles, use Desktop's native package manager with `dsh-github-copilot@0.4.0-alpha.81` after the same preflight and only when registry access is permitted. Desktop reserves its `desktop` profile from CLI management. If registry access is blocked or unavailable, stop; the documented [controlled offline CLI procedure](./docs/npm-distribution.md#controlled-offline-cli-maintenance-for-standalone-profiles) is not a Desktop workaround.
|
|
128
128
|
|
|
129
129
|
Then open the Models UI listed above, find **GitHub Copilot**, select **Sign in**, and complete the GitHub device-code flow. Plugin installation changes the selected profile; activation follows that profile's normal reload/restart policy.
|
|
130
130
|
|
|
@@ -142,10 +142,14 @@ If preferences cannot be read, available account rows remain visible but read-on
|
|
|
142
142
|
|
|
143
143
|
**One setting for subagents:** in the plugin configuration page, turn on **Subagent models → Follow parent model** and Save. It applies to existing and new supported Copilot subagents and Team mates, without Session IDs or per-child setup. A fixed parent model takes effect on each child's next turn; Auto inherits the same preference but chooses using each child's own context. Running turns stay unchanged and child-owned manual selections still win. Default Off (`github-copilot.followParentModel: false`). Enabling replaces creation-time model choices; it never clears explicit child selection history. Legacy `parentModelFollow` bindings remain active independently and are not migrated. See [requirements, mockup and boundaries](./docs/parent-model-follow.md). Native Team creation labels are not rewritten.
|
|
144
144
|
|
|
145
|
-
The managed GitHub Copilot group includes **Auto · Balance**, **Auto · Efficiency**, and **Auto · Intelligence** as flat virtual picker rows. They share one account-verified eligible pool after applying exact model exclusions
|
|
145
|
+
The managed GitHub Copilot group includes **Auto · Balance**, **Auto · Efficiency**, and **Auto · Intelligence** as flat virtual picker rows. They share one account-verified eligible pool after applying exact model exclusions and input-fit filtering. Routing now uses the account's **Powerful / Versatile / Lightweight** classification and conservative contextual task assessment, not reasoning effort or context capacity as a quality ranking. Even Intelligence uses Lightweight for an isolated greeting; short difficult reasoning stays Powerful. Unknown tasks prefer Versatile with Balance/Efficiency and Powerful with Intelligence. Suitable previous-model continuity wins before stable equal-weight category tie-breaking. Missing categories and fallback remain explicit. If no candidate fits, Auto preserves largest-input-budget native recovery; if none is eligible, it fails closed. One decision stays fixed across the turn's tool steps, retries and compaction. Images retain their independent verified admission. Search, actual model/Usage and histories remain native-owned. See the [task policy and limits](./docs/auto-task-routing.md) and [parent-inheritance boundary](./docs/automatic-model-routing.md#requested-parent-to-child-selection-inheritance). Core's picker remains flat.
|
|
146
|
+
|
|
147
|
+
The optional `github-copilot.autoSemanticAssessment: true` experiment recognizes contextual tasks with one bounded auxiliary model call; it is **off by default** until calibrated. It adds latency and supplier charges not included in native chat Usage. Failure or omitted assessment context never means the task is simple; it retains conservative local evidence. This is a local routing approximation, not GitHub's private Auto service.
|
|
146
148
|
|
|
147
149
|
Completed Copilot replies show **Auto (preference)** and an expandable recorded reason after native Usage/time, or **Manual** only with captured explicit fixed-selection evidence. A successful read with no retained evidence shows **Selection unknown**, never a guess from today's picker. Failed reads instead show **Selection unavailable → Retry**; retry only reads the same turn's record, not another model request. Explicit Session/turn arguments remain stable inside a session-bound Chat, avoiding the former native gateway argument-count failure on fresh master/lead replies. There is no repeated model name or separate Model details button: actual model display stays in native Usage, whose missing-route behavior is unchanged. New selection records are bounded and Host-local; restart, disposal or eviction loses them. Compatible historical Auto records remain readable. The public assistant-actions slot supports internal wrapping only, not changing the native fixed-height row.
|
|
148
150
|
|
|
151
|
+
The information button explains this turn's captured task/category choice, fallback and continuity/tie-breaking. Supporting assessment facts sit in a disclosure; older records without details explicitly say that the reason was not retained.
|
|
152
|
+
|
|
149
153
|
The selection footer mounts independently of optional conversation projections. Native completed-turn evidence lets retained Auto/Manual records remain visible if those projections are unavailable; incomplete attribution stays explicit in the information disclosure. This does not restore lost selection records or prove that an installed update is loaded in Desktop.
|
|
150
154
|
|
|
151
155
|
Alpha.79 also fixes the Host half of selection reads: the retained decision store is now exposed through the public Remote service binding and method marker, not a plain provided object rejected by the native gateway. Actual Client-to-Host roundtrips cover both source discovery and strict descriptors. This complements alpha.76's Client argument fix; it does not recover lost records or change Auto model selection.
|
|
@@ -179,7 +183,7 @@ Agents should treat the browser authorization as a human handoff, not as a token
|
|
|
179
183
|
5. Confirm **Signed in** and inspect the automatic discovery result before asking the user to choose a model. Already-signed-in Models opening ensures missing/stale metadata automatically; fresh ready cache makes no request. Use visible **Retry** for errors or **Manage → Refresh models** for an intentional forced update, not routine setup. Status alone does not discover, and login, metadata and successful model calls remain separate evidence.
|
|
180
184
|
6. Use **Sign out** only when the user explicitly asks to disconnect the account. It deletes the Copilot credential record but preserves route settings.
|
|
181
185
|
|
|
182
|
-
GitHub Releases and npm are the default distribution channels for each new version, using the same verified tarball. Pin the version and verify the evidence for the channel used: Release `SHA256SUMS`, and npm `dist.integrity` when installing from npm. Install into Desktop profiles only through Desktop's native package manager; the reserved `desktop` profile is not managed by the DSH CLI. After npm publication is verified, the native manager accepts `dsh-github-copilot@0.4.0-alpha.
|
|
186
|
+
GitHub Releases and npm are the default distribution channels for each new version, using the same verified tarball. Pin the version and verify the evidence for the channel used: Release `SHA256SUMS`, and npm `dist.integrity` when installing from npm. Install into Desktop profiles only through Desktop's native package manager; the reserved `desktop` profile is not managed by the DSH CLI. After npm publication is verified, the native manager accepts `dsh-github-copilot@0.4.0-alpha.81`, not a URL or file. Controlled offline CLI maintenance is documented for standalone named profiles only, never Desktop-managed profiles. Follow the mandatory search-composition preflight, backup, single-writer and post-install checks; do not bypass a corporate registry ban, disable TLS verification or restart without separate approval. See [distribution and publication requirements](./docs/npm-distribution.md).
|
|
183
187
|
|
|
184
188
|
**Desktop package-update and Web-lifecycle boundaries:** the native manager's `restart-required` result for an in-place installed-package upgrade is authoritative and distinct from plugin-bundle removal/re-add behavior. Any disable, removal, or upgrade involving service recomposition (`cordis.patch.yml`, such as the isolated routed web search layer) may leave dependent entries pending until Desktop is fully exited and cold-restarted. If the native manager reports only entries such as `pending (waiting for service: web)` while this plugin already shows **Off**, the requested disabled state has been persisted; cold-restart Desktop instead of repeatedly toggling or reinstalling the plugin. Other errors are not covered by this guidance and must still be investigated.
|
|
185
189
|
|
|
@@ -461,8 +465,8 @@ Report the published Release URL, version, tag/commit and verified asset SHA-256
|
|
|
461
465
|
`package.json` declares public npm distribution. A release tag must equal `v${package.json.version}`. Versions use standard SemVer prerelease labels (`alpha`, `beta`, or `rc`), each with its matching npm dist-tag; only stable versions use `latest`. The Release workflow performs the frozen install and complete verification gate, packs once (or recovers the original archive on retry), verifies `SHA256SUMS`, publishes the immutable GitHub Release and then publishes those same bytes to npm through OIDC. Either channel failing means delivery is incomplete. First package creation needs an authorized maintainer; staging requires an existing package and is not a first-package bootstrap. Historical releases are not republished.
|
|
462
466
|
|
|
463
467
|
```sh
|
|
464
|
-
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.
|
|
465
|
-
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.
|
|
468
|
+
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.81/dsh-github-copilot-0.4.0-alpha.81.tgz
|
|
469
|
+
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.81/SHA256SUMS
|
|
466
470
|
sha256sum --check SHA256SUMS
|
|
467
471
|
```
|
|
468
472
|
|
|
@@ -470,7 +474,7 @@ PowerShell can verify the same two downloaded files with:
|
|
|
470
474
|
|
|
471
475
|
```powershell
|
|
472
476
|
$expected = (Get-Content .\SHA256SUMS).Split()[0]
|
|
473
|
-
$actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.
|
|
477
|
+
$actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.81.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
|
|
474
478
|
if ($actual -cne $expected) { throw 'Release checksum mismatch' }
|
|
475
479
|
```
|
|
476
480
|
|
package/README.zh.md
CHANGED
|
@@ -26,7 +26,7 @@ Core 管理。详见[图片兼容性与限制](./docs/image-input-compatibility.
|
|
|
26
26
|
|
|
27
27
|
截图来自当前构建 Client 的隔离浏览器 fixture,使用合成 Provider。它只证明已发布配置界面的形态,不证明真实凭据、账号权限、搜索成功或当前 Desktop 已加载。
|
|
28
28
|
|
|
29
|
-
> 当前文档与安装命令对应版本 `0.4.0-alpha.
|
|
29
|
+
> 当前文档与安装命令对应版本 `0.4.0-alpha.81`。源码、发布制品、已安装版本和实际加载运行时需分别确认;本地升级和中断会话的重启仍需用户批准。
|
|
30
30
|
|
|
31
31
|
Web search 路由现在优先显示在插件详情页;宿主不支持详情页插槽时才回退到 **设置 → 模型**或独立 Web search section。搜索子 Fiber 仍独立等待 Remote,不影响账号控件和既有搜索安全检查。
|
|
32
32
|
|
|
@@ -123,10 +123,10 @@ node package/scripts/check-search-composition.mjs --profile-dir /absolute/profil
|
|
|
123
123
|
仅对独立的具名 profile,获准且网络可用时,可通过受支持的 CLI 命令安装:
|
|
124
124
|
|
|
125
125
|
```sh
|
|
126
|
-
dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.
|
|
126
|
+
dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.81/dsh-github-copilot-0.4.0-alpha.81.tgz
|
|
127
127
|
```
|
|
128
128
|
|
|
129
|
-
Desktop profile 请在完成同样的预检后,使用 Desktop 原生包管理器安装 `dsh-github-copilot@0.4.0-alpha.
|
|
129
|
+
Desktop profile 请在完成同样的预检后,使用 Desktop 原生包管理器安装 `dsh-github-copilot@0.4.0-alpha.81`。Desktop 保留 `desktop` profile,CLI 不负责管理。若 registry 被公司封禁或不可用,不要更换网络绕行或使用离线 CLI;请停止。[受控离线 CLI 流程](./docs/npm-distribution.md#controlled-offline-cli-maintenance-for-standalone-profiles)仅适用于独立具名 profile,不适用于 Desktop。
|
|
130
130
|
|
|
131
131
|
随后打开上表对应的 Models UI,找到 **GitHub Copilot**,点击 **Sign in** 并完成 GitHub device-code 流程。安装会修改指定 profile;是否立即激活取决于该 profile 的常规 reload/restart 策略。
|
|
132
132
|
|
|
@@ -144,10 +144,14 @@ Desktop profile 请在完成同样的预检后,使用 Desktop 原生包管理
|
|
|
144
144
|
|
|
145
145
|
**子代理只需设置一次:** 在插件配置页打开 **Subagent models → Follow parent model** 并保存,即应用于已有和新创建的受支持 Copilot 子代理及 Team mate,无需填写 Session ID 或逐个登记。父会话为固定模型时,子会话从下一轮跟随;父会话为 Auto 时,继承相同偏好并按各自上下文独立选模。正在执行的轮次不变,子会话自己的手动选择仍优先。默认关闭(`github-copilot.followParentModel: false`)。开启意味着接管创建时保存的模型选择,但不清除子会话的显式选择历史。旧 `parentModelFollow` 绑定独立保留,不自动迁移。参见[需求、mockup 与边界](./docs/parent-model-follow.md)。原生 Team 的创建时模型标签不会被改写。
|
|
146
146
|
|
|
147
|
-
托管 GitHub Copilot 分组提供三个平铺的虚拟选择:**Auto · Balance**(均衡)、**Auto · Efficiency**(效率)和 **Auto · Intelligence
|
|
147
|
+
托管 GitHub Copilot 分组提供三个平铺的虚拟选择:**Auto · Balance**(均衡)、**Auto · Efficiency**(效率)和 **Auto · Intelligence**(智能)。三档共用精确排除与输入适配后的账号合格模型池。现在依据账号返回的 **Powerful / Versatile / Lightweight** 分类和保守的上下文任务判断选择,不再把推理档位或上下文容量当作品质排名。即使 Intelligence,独立问候也用 Lightweight;简短但困难的推理仍用 Powerful。无法判断的任务,Balance/Efficiency 优先 Versatile,Intelligence 优先 Powerful。上一轮模型仍符合目标分类与输入要求时优先保持它,否则仅在同类候选间稳定等权选择。分类缺失、分类回退均明确说明。没有可容纳候选时保留最大输入预算的原生恢复;没有合格候选则明确失败。同轮工具步骤、重试和自动压缩保持同一决策。图片验证独立保留;搜索、真实模型/Usage 和历史仍由原有服务所有。参见[任务策略与边界](./docs/auto-task-routing.md)及[父子继承边界](./docs/automatic-model-routing.md#requested-parent-to-child-selection-inheritance)。Core picker 仍保持平铺。
|
|
148
|
+
|
|
149
|
+
可选实验 `github-copilot.autoSemanticAssessment: true` 通过一次有界的辅助模型请求判断上下文任务;校准前**默认关闭**。它会增加延迟和供应方费用,不计入原生 Chat Usage。失败或判断上下文不完整不会被当作简单任务,而是保留保守本地依据。这是插件本地近似策略,不是 GitHub 的私有 Auto 服务。
|
|
148
150
|
|
|
149
151
|
已完成的 Copilot 回复在原生 Usage/时间后显示 **Auto(偏好)**,点信息按钮查看本轮记录的选择原因;只有捕获到明确固定选择才显示**手动**。成功读取但没有保留记录时显示**选择方式未知**,不借当前 picker 推断历史。读取失败则显示**选择记录读取失败 → 重试**;重试只重新读取同一轮记录,不重新调用模型。显式会话 ID/轮次参数不再被 Chat 的自动会话绑定缩减,修复新 master/lead 回复遭遇原生网关参数数量错误的问题。不重复模型名、不另设 Model details 按钮:实际模型仍由原生 Usage 显示,其缺失归属行为未改变。新选择记录仅限当前 Host 内存且有容量上限,重启、释放 Agent 或淘汰后会丢失;兼容历史 Auto 记录仍可读取。公开 assistant-actions slot 只允许插件内部换行,不能改变原生固定高度尾栏。
|
|
150
152
|
|
|
153
|
+
信息按钮展示本轮实际捕获的任务/分类依据、回退和保持原模型/同类分配原因;辅助判断信息收纳在折叠区。旧记录没有详细依据时明确说明未保留原因,不用今天的设置反推。
|
|
154
|
+
|
|
151
155
|
选择标记独立于可选会话投影挂载。投影不可用时,原生已完成回合证据仍允许显示保留的 Auto/手动记录;归属证据不完整会在信息弹层中明确说明。这不会恢复丢失的选择记录,也不证明已安装的更新已在 Desktop 加载。
|
|
152
156
|
|
|
153
157
|
Alpha.79 进一步修复选模读取的 Host 端:通过官方 Remote 服务绑定与方法标记暴露现有决策存储,不再使用会被原生网关拒绝的普通对象。实际 Client→Host 连通回归覆盖源码发现和严格描述符两种方式。这补齐 alpha.76 的 Client 参数修复,不恢复已丢失记录,也不改变 Auto 的选模逻辑。
|
|
@@ -181,7 +185,7 @@ Agent 应把浏览器授权视为需要用户完成的 handoff,而不是自行
|
|
|
181
185
|
5. 确认 **Signed in** 并检查自动发现结果,再请用户选择模型。已登录时打开 Models 会自动确保缺失/过期元数据,新鲜 ready 缓存不发请求。错误可使用 **Retry**,有意强制更新时使用 **Manage → Refresh models**,不作为常规设置步骤。状态读取本身不发现;登录、元数据与真实调用成功是独立证据。
|
|
182
186
|
6. 只有用户明确要求断开账号时才使用 **Sign out**;它会删除 Copilot credential record,但保留 route settings。
|
|
183
187
|
|
|
184
|
-
每个新版本默认同时分发到 GitHub Releases 和 npm,两个渠道使用同一份已验证 tarball。应固定版本并核对所用渠道的证据:Release 的 `SHA256SUMS`;从 npm 安装时另核对 `dist.integrity`。Desktop profile 只能通过原生 Desktop 包管理器安装;获准且 registry 可用时输入 `dsh-github-copilot@0.4.0-alpha.
|
|
188
|
+
每个新版本默认同时分发到 GitHub Releases 和 npm,两个渠道使用同一份已验证 tarball。应固定版本并核对所用渠道的证据:Release 的 `SHA256SUMS`;从 npm 安装时另核对 `dist.integrity`。Desktop profile 只能通过原生 Desktop 包管理器安装;获准且 registry 可用时输入 `dsh-github-copilot@0.4.0-alpha.81`,不是 URL 或本地文件。Desktop 保留 `desktop` profile,不能通过 DSH CLI 管理。受控离线 CLI 维护仅适用于独立具名 profile,不得作为 Desktop 安装绕行方案。[双渠道发布与 OIDC 要求](./docs/npm-distribution.md)保持不变。
|
|
185
189
|
|
|
186
190
|
**Desktop package 更新与 Web 生命周期边界:**原生 manager 对已安装 package 原位升级返回的 `restart-required` 是权威结果,与移除/重加 plugin bundle 的行为是两个不同问题。涉及服务重编排补丁(`cordis.patch.yml`,如本插件所采用的隔离路由 Web 搜索层)的停用、移除或升级,可能让依赖条目保持 pending,直到完全退出并冷重启 Desktop。若原生 manager 只报告类似 `pending (waiting for service: web)` 的条目,同时本插件已经显示 **Off**,说明请求的停用状态已经落盘;请冷重启 Desktop,不要反复切换或重装插件。其它错误不属于此提示范围,仍需单独排查。
|
|
187
191
|
|
|
@@ -472,8 +476,8 @@ node scripts/agent.mjs attribution "DeepSeek Harness (DSH)"
|
|
|
472
476
|
`package.json` 声明公开 npm 分发。Release tag 必须严格等于 `v${package.json.version}`。预发布使用 `alpha`、`beta` 或 `rc` 及对应 npm dist-tag,只有稳定版使用 `latest`。Release workflow 执行 frozen install 和完整门禁,只打包一次(重试恢复原始归档),验证 `SHA256SUMS`,发布不可变 GitHub Release,再通过 OIDC 将同一份字节发布到 npm。任一渠道失败都表示交付未完成。首次建包须由获准环境中的维护者完成;staging 要求包已存在,不能代替首次建包。不会批量补发历史版本。
|
|
473
477
|
|
|
474
478
|
```sh
|
|
475
|
-
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.
|
|
476
|
-
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.
|
|
479
|
+
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.81/dsh-github-copilot-0.4.0-alpha.81.tgz
|
|
480
|
+
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.81/SHA256SUMS
|
|
477
481
|
sha256sum --check SHA256SUMS
|
|
478
482
|
```
|
|
479
483
|
|
|
@@ -481,7 +485,7 @@ PowerShell 可以对已下载的同一组文件执行:
|
|
|
481
485
|
|
|
482
486
|
```powershell
|
|
483
487
|
$expected = (Get-Content .\SHA256SUMS).Split()[0]
|
|
484
|
-
$actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.
|
|
488
|
+
$actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.81.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
|
|
485
489
|
if ($actual -cne $expected) { throw 'Release checksum mismatch' }
|
|
486
490
|
```
|
|
487
491
|
|
package/deployment-baseline.json
CHANGED
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
},
|
|
9
9
|
"package": {
|
|
10
10
|
"name": "dsh-github-copilot",
|
|
11
|
-
"version": "0.4.0-alpha.
|
|
11
|
+
"version": "0.4.0-alpha.81"
|
|
12
12
|
},
|
|
13
13
|
"evidence": {
|
|
14
14
|
"kind": "source-and-synthetic-test-inventory",
|
|
@@ -1061,6 +1061,12 @@
|
|
|
1061
1061
|
"id": "managed-copilot-auto-model-routing",
|
|
1062
1062
|
"required": true,
|
|
1063
1063
|
"sourceMarkers": [
|
|
1064
|
+
{"file": "src/account-model-catalog.ts", "marker": "model_picker_category"},
|
|
1065
|
+
{"file": "src/auto-task-assessment.ts", "marker": "COPILOT_AUTO_ASSESSMENT_CONTEXT_OMITTED"},
|
|
1066
|
+
{"file": "src/auto-task-classifier.ts", "marker": "classifyTaskWithAdapter"},
|
|
1067
|
+
{"file": "src/auto-model-routing.ts", "marker": "targetCategory"},
|
|
1068
|
+
{"file": "src/config.ts", "marker": "autoSemanticAssessment"},
|
|
1069
|
+
{"file": "src/auto-selection-explanation.ts", "marker": "No candidate fits"},
|
|
1064
1070
|
{"file": "src/preview-route.ts", "marker": "GITHUB_COPILOT_AUTO_MODEL_ID"},
|
|
1065
1071
|
{"file": "src/auto-model-host.ts", "marker": "keep attribution out of the log"},
|
|
1066
1072
|
{"file": "src/parent-model-follow.ts", "marker": "resolveParentModel"},
|
|
@@ -1081,7 +1087,14 @@
|
|
|
1081
1087
|
"tests": [
|
|
1082
1088
|
{"file": "tests/auto-model-host.spec.ts", "name": "follows fixed and Auto parents using %s without writing child selections"},
|
|
1083
1089
|
{"file": "tests/scripts/parent-model-follow.test.mjs", "name": "explicit same-model and different-model child selections both win"},
|
|
1084
|
-
{"file": "tests/auto-model-routing.spec.ts", "name": "
|
|
1090
|
+
{"file": "tests/auto-model-routing.spec.ts", "name": "retains legacy length evidence but does not use it as task or supplier category evidence"},
|
|
1091
|
+
{"file": "tests/auto-model-routing.spec.ts", "name": "uses the task/category policy with one hard-eligible pool for all preferences"},
|
|
1092
|
+
{"file": "tests/auto-model-routing.spec.ts", "name": "preserves suitable continuity but never lets it override task category or input fit"},
|
|
1093
|
+
{"file": "tests/auto-model-routing.spec.ts", "name": "discloses category fallbacks and never guesses missing category from ID or capacity"},
|
|
1094
|
+
{"file": "tests/auto-task-assessment.spec.ts", "name": "bounds context, never reads attachment/reasoning bodies, and does not downshift omitted context"},
|
|
1095
|
+
{"file": "tests/auto-task-assessment.spec.ts", "name": "preserves caller cancellation instead of using a success-shaped fallback"},
|
|
1096
|
+
{"file": "tests/preview-route.spec.ts", "name": "assesses Auto through one concrete public native adapter call and freezes the captured reason across retries"},
|
|
1097
|
+
{"file": "tests/turn-selection-card.spec.ts", "name": "explains a captured task/category decision with progressive details (%s)"},
|
|
1085
1098
|
{"file": "tests/auto-model-routing.spec.ts", "name": "does not discard a complete Core assistant message when it contains reasoning"},
|
|
1086
1099
|
{"file": "tests/auto-model-routing.spec.ts", "name": "retains the native current-surface and tool-envelope measurement as an input floor"},
|
|
1087
1100
|
{"file": "tests/fixtures/compaction-pressure-core.fixture.ts", "name": "prices Core assistant text and reasoning with the unchanged native token meter"},
|
|
@@ -0,0 +1,114 @@
|
|
|
1
|
+
# Contextual Auto routing and captured selection reasons
|
|
2
|
+
|
|
3
|
+
Tracking: [#258](https://github.com/cloga/dsh-github-copilot/issues/258).
|
|
4
|
+
|
|
5
|
+
## Requirements
|
|
6
|
+
|
|
7
|
+
Auto must explain why the initiating turn chose its actual route, not display a
|
|
8
|
+
generic description of prompt length. Intelligence prioritizes response quality
|
|
9
|
+
but can use a lightweight model for demonstrably simple work. Efficiency favors
|
|
10
|
+
economical capability without knowingly underpowering difficult work. Balance
|
|
11
|
+
trades those priorities. All preferences share the same account model pool.
|
|
12
|
+
|
|
13
|
+
The authenticated account `/models` response supplies `model_picker_category`.
|
|
14
|
+
The October 3, 2026 bounded live probe observed `powerful`, `versatile` and
|
|
15
|
+
`lightweight`; some records lacked the field. This is supplier classification,
|
|
16
|
+
not measured latency, quality, price or health. Official documentation's
|
|
17
|
+
`category` is a different source and must not override live account facts.
|
|
18
|
+
Do not derive category from IDs, names, reasoning effort or context capacity.
|
|
19
|
+
|
|
20
|
+
Hard constraints remain first: entitlement, exclusions, current proof, text/image
|
|
21
|
+
capability and actual image format, estimated input headroom and final native
|
|
22
|
+
admission. No preference overrides these. No new Core owner, adapter, credential
|
|
23
|
+
record, general transport, global model mutation or durable decision event.
|
|
24
|
+
|
|
25
|
+
## Task assessment
|
|
26
|
+
|
|
27
|
+
Assessment concerns the task in context, not the last sentence's length.
|
|
28
|
+
An isolated greeting may be low demand. A short request to prove a theorem or
|
|
29
|
+
continue an unresolved investigation is not evidence of low demand. Long input
|
|
30
|
+
can be mechanical. Prior assistant/tool work prevents a greeting/continuation
|
|
31
|
+
shortcut from claiming an isolated simple task.
|
|
32
|
+
|
|
33
|
+
Use a conservative local assessment as the default. Unknown is an explicit
|
|
34
|
+
outcome, never silently translated into simple. Optional semantic assessment is
|
|
35
|
+
an experiment until evaluated against annotated tasks; it must not claim
|
|
36
|
+
equivalence to GitHub's private router or calibrated confidence.
|
|
37
|
+
|
|
38
|
+
The semantic experiment uses one fixed concrete account candidate through the
|
|
39
|
+
existing managed native adapter, never an Auto ID and never `ctx.llm` routing
|
|
40
|
+
recursion. It has no tools, bounded text-only assessment context, bounded JSON
|
|
41
|
+
output, one deadline, cancellation and no new retry loop. Text from messages is
|
|
42
|
+
untrusted data, not router instructions. Files/images/reasoning/replay bodies
|
|
43
|
+
are not read; omitted context makes classification uncertain and cannot justify
|
|
44
|
+
downshifting. Assessment input is a separate projection: the actual chat
|
|
45
|
+
messages, system prompt, tools, attachments and history stay untouched.
|
|
46
|
+
|
|
47
|
+
The strict result contains demand (`simple`, `routine`, `complex`, `unknown`)
|
|
48
|
+
and finite evidence signals, not a model ID, raw reasoning or an uncalibrated
|
|
49
|
+
confidence percentage. Invalid/truncated/failed results retain the local
|
|
50
|
+
assessment with an explicit diagnostic. Caller cancellation aborts the turn
|
|
51
|
+
instead of falling back. Credential, metadata and account revocation remain
|
|
52
|
+
fatal through existing lease/admission guards. Extra calls incur supplier
|
|
53
|
+
charges and latency, separate from native chat Usage and without inferred cost.
|
|
54
|
+
|
|
55
|
+
## Category policy and continuity
|
|
56
|
+
|
|
57
|
+
| Task demand | Efficiency | Balance | Intelligence |
|
|
58
|
+
| --- | --- | --- | --- |
|
|
59
|
+
| Proven simple | Lightweight | Lightweight | Lightweight |
|
|
60
|
+
| Routine | Lightweight | Versatile | Powerful |
|
|
61
|
+
| Complex | Powerful | Powerful | Powerful |
|
|
62
|
+
| Unknown | Versatile | Versatile | Powerful |
|
|
63
|
+
|
|
64
|
+
These are declared routing policies, not benchmark rankings. Efficiency's
|
|
65
|
+
routine lightweight selection is an economical approximation, not proof of
|
|
66
|
+
equal output quality. Intelligence never treats short length alone as simple.
|
|
67
|
+
|
|
68
|
+
When the target has no fitting candidates, use the disclosed category fallback:
|
|
69
|
+
powerful -> versatile -> lightweight; versatile -> powerful -> lightweight;
|
|
70
|
+
lightweight -> versatile -> powerful. Unclassified candidates are a final
|
|
71
|
+
explicit fallback only, not fabricated categories. Unknown/new category values
|
|
72
|
+
remain unclassified with a bounded catalog diagnostic.
|
|
73
|
+
|
|
74
|
+
Within the first available category, retain the previous managed model only
|
|
75
|
+
when it remains eligible and suitable. Otherwise use stable equal-weight
|
|
76
|
+
Session/turn selection with deterministic ID ordering as a tie breaker. Do not
|
|
77
|
+
infer quality from that ordering or assign fabricated weights. Once admitted,
|
|
78
|
+
all steps/retries share the turn decision. Continuity reduces unnecessary
|
|
79
|
+
switches but is not a claim of supplier cache savings.
|
|
80
|
+
|
|
81
|
+
If no model fits, preserve the existing largest-admissible-input recovery
|
|
82
|
+
branch and its native compaction diagnostics. Explain that no candidate fits;
|
|
83
|
+
never label this as a successful preference match or silently trim history.
|
|
84
|
+
|
|
85
|
+
## Explanation contract
|
|
86
|
+
|
|
87
|
+
Capture task source/demand/signals, assessment diagnostic, target/selected
|
|
88
|
+
category, fitting category count, category fallback and continuity/tie-break or
|
|
89
|
+
no-fit selection at decision time. Client reads the explicit viewed Session and
|
|
90
|
+
turn through the existing strict Remote. It does not rerun classification or
|
|
91
|
+
consult today's picker. Show a decisive first sentence, bounded supporting
|
|
92
|
+
facts and optional policy detail. Do not repeat the model name or change Usage.
|
|
93
|
+
|
|
94
|
+
Legacy records without detailed evidence show that the reason was not retained.
|
|
95
|
+
Host-lifetime evidence may be lost on restart; do not invent durable history or
|
|
96
|
+
promise cold-history reconstruction.
|
|
97
|
+
|
|
98
|
+
## Acceptance and rollout
|
|
99
|
+
|
|
100
|
+
Regress category normalization (missing/new/invalid values), short difficult
|
|
101
|
+
tasks, isolated greetings, contextual continuation, long mechanical input,
|
|
102
|
+
category fallback, previous-model eligibility, deterministic tie breaking,
|
|
103
|
+
no-fit recovery, one-call semantic success/invalid/failure/timeout/cancellation,
|
|
104
|
+
omitted context, strict Remote and footer English/Chinese explanations.
|
|
105
|
+
|
|
106
|
+
Retain native gateway, parent following, manual selection, exclusion admission,
|
|
107
|
+
account proof, image admission and compaction fixture coverage. Full protected
|
|
108
|
+
Windows/Linux CI remains mandatory before merge/release. No live inference
|
|
109
|
+
calls are needed for synthetic acceptance.
|
|
110
|
+
|
|
111
|
+
Before making semantic assessment the default, evaluate a reviewed labeled
|
|
112
|
+
corpus for complex-to-simple errors, extra latency, token use and stability
|
|
113
|
+
across languages and prompt injection. Synthetic passing tests are not this
|
|
114
|
+
evaluation. Publication does not authorize profile installation or restart.
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# GitHub Copilot Auto model routing MVP
|
|
2
2
|
|
|
3
|
-
**Tracking:** [#174](https://github.com/cloga/dsh-github-copilot/issues/174), [#192](https://github.com/cloga/dsh-github-copilot/issues/192), [#199](https://github.com/cloga/dsh-github-copilot/issues/199)
|
|
3
|
+
**Tracking:** [#174](https://github.com/cloga/dsh-github-copilot/issues/174), [#192](https://github.com/cloga/dsh-github-copilot/issues/192), [#199](https://github.com/cloga/dsh-github-copilot/issues/199), [#258](https://github.com/cloga/dsh-github-copilot/issues/258)
|
|
4
4
|
|
|
5
5
|
**Target:** official DSH and Windows Desktop `0.2.0-rc.2`
|
|
6
6
|
|
|
@@ -31,7 +31,7 @@ MIME are not wire-format proof. See [image compatibility and limits](./image-inp
|
|
|
31
31
|
|
|
32
32
|
The account `/models` catalog is authoritative for entitlement and hard capabilities: protocol, context and output limits, image input, tool support, reasoning efforts, and server policy. Unknown or incomplete capability metadata fails closed.
|
|
33
33
|
|
|
34
|
-
The catalog
|
|
34
|
+
The catalog supplies `model_picker_category` (`powerful`, `versatile`, `lightweight`), but not trustworthy measured quality, latency, price, or global-health rankings. Missing, invalid and new category values remain unclassified with diagnostics. The routing policy does **not** infer category from a marketing name, model-ID prefix, reasoning effort, context capacity or token price. It does not claim to reproduce GitHub's private Auto algorithm.
|
|
35
35
|
|
|
36
36
|
### Hard input fit check before preference
|
|
37
37
|
|
|
@@ -49,28 +49,35 @@ Before applying soft preferences, routing checks whether each candidate can acco
|
|
|
49
49
|
- `compaction-eligible`: prior history is compressible and downstream dispatch will trigger compaction pressure.
|
|
50
50
|
5. **Final framing limitation:** The fresh entered-message estimate and current native envelope floor are not the final candidate-specific serialized request. Later framing, changed tools and native attachment projection can still exceed a candidate's budget. The native provider guard (`inspectRequest`) remains authoritative and truthfully rejects such a request with `COPILOT_CONTEXT_BUDGET_EXCEEDED` without bypassing safety boundaries.
|
|
51
51
|
|
|
52
|
-
###
|
|
52
|
+
### Task-aware supplier category preferences
|
|
53
53
|
|
|
54
|
-
All three
|
|
54
|
+
All three preferences use the *same* hard-eligible account pool. The default local
|
|
55
|
+
assessment recognizes isolated greetings and explicit difficult reasoning or
|
|
56
|
+
investigation; other tasks remain uncertain rather than guessing from length.
|
|
57
|
+
An optional `github-copilot.autoSemanticAssessment: true` experiment makes one
|
|
58
|
+
bounded auxiliary native-adapter call to a concrete, non-excluded supplier
|
|
59
|
+
Lightweight model. It adds latency and supplier charges not included in native
|
|
60
|
+
chat Usage. It is off by default pending labeled-corpus calibration.
|
|
55
61
|
|
|
56
|
-
|
|
57
|
-
- **Efficiency:** Biased toward lower advertised capacity across the lower candidate band, though demanding tasks allow higher capacity.
|
|
58
|
-
- **Balance:** Central candidate band.
|
|
59
|
-
|
|
60
|
-
To avoid monopolizing a single top candidate (such as Grok 4.7) across all turns and Sessions, band selection uses an in-memory deterministic seed derived from `${sessionId}:${turn}` (or turn content when Session context is absent). This guarantees:
|
|
61
|
-
|
|
62
|
-
- Selection is **100% frozen** across all steps and retries within the same turn.
|
|
63
|
-
- Unrelated Sessions or turns sample across the candidate band rather than concentrating on one model.
|
|
64
|
-
- No sensitive prompt text or seed hashes are persisted or sent over the network.
|
|
65
|
-
- When only a single candidate is eligible or fitting, it is returned unchanged.
|
|
66
|
-
|
|
67
|
-
| Latest-turn class | Efficiency | Balance (`auto`) | Intelligence |
|
|
62
|
+
| Task demand | Efficiency | Balance (`auto`) | Intelligence |
|
|
68
63
|
| --- | --- | --- | --- |
|
|
69
|
-
|
|
|
70
|
-
|
|
|
71
|
-
|
|
|
72
|
-
|
|
73
|
-
|
|
64
|
+
| Proven simple | Lightweight | Lightweight | Lightweight |
|
|
65
|
+
| Routine | Lightweight | Versatile | Powerful |
|
|
66
|
+
| Complex | Powerful | Powerful | Powerful |
|
|
67
|
+
| Unknown | Versatile | Versatile | Powerful |
|
|
68
|
+
|
|
69
|
+
If the target category has no fitting model, follow the documented category
|
|
70
|
+
fallback order, using unclassified models only last. Keep the previous managed
|
|
71
|
+
model if it remains in the first available category and fits this turn.
|
|
72
|
+
Otherwise use stable equal-weight Session/turn allocation within that category;
|
|
73
|
+
ID ordering breaks ties, not quality rankings. Capacity and reasoning-effort
|
|
74
|
+
bands no longer determine task quality. All steps/retries retain the decision.
|
|
75
|
+
|
|
76
|
+
These are declared policies, not measured quality, speed or cost guarantees.
|
|
77
|
+
Captured footer reasons show task evidence, selected/target category, fallback,
|
|
78
|
+
continuity or equal tie-breaking, and no-fit recovery. Legacy records without
|
|
79
|
+
details say the reasons were not retained; they never reconstruct history from
|
|
80
|
+
today's settings. See [requirements, assessment limits and rollout](./auto-task-routing.md).
|
|
74
81
|
|
|
75
82
|
The exact virtual preference stays in the Session's pending selection across turns, while each real request header and transport record the chosen account model. Switching to a real model ends automatic routing for subsequent turns. New turns no longer write a separate decision event; compatible historical events without a preference field remain Balance for display.
|
|
76
83
|
|
package/lib/client.js
CHANGED
|
@@ -5646,6 +5646,54 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
|
|
|
5646
5646
|
};
|
|
5647
5647
|
//#endregion
|
|
5648
5648
|
//#region lib/types/turn-selection.js
|
|
5649
|
+
const ExplanationSchema = object({
|
|
5650
|
+
assessment: object({
|
|
5651
|
+
demand: _enum([
|
|
5652
|
+
"simple",
|
|
5653
|
+
"routine",
|
|
5654
|
+
"complex",
|
|
5655
|
+
"unknown"
|
|
5656
|
+
]),
|
|
5657
|
+
signals: array(_enum([
|
|
5658
|
+
"isolated-greeting",
|
|
5659
|
+
"bounded-transformation",
|
|
5660
|
+
"reasoning",
|
|
5661
|
+
"investigation",
|
|
5662
|
+
"continuation",
|
|
5663
|
+
"context-omitted",
|
|
5664
|
+
"insufficient-evidence"
|
|
5665
|
+
])).max(7)
|
|
5666
|
+
}).strict().extend({
|
|
5667
|
+
source: _enum(["local", "semantic"]),
|
|
5668
|
+
diagnostic: _enum([
|
|
5669
|
+
"disabled",
|
|
5670
|
+
"unavailable",
|
|
5671
|
+
"invalid-result",
|
|
5672
|
+
"timeout",
|
|
5673
|
+
"failed",
|
|
5674
|
+
"context-omitted"
|
|
5675
|
+
]).optional()
|
|
5676
|
+
}).strict(),
|
|
5677
|
+
targetCategory: _enum([
|
|
5678
|
+
"powerful",
|
|
5679
|
+
"versatile",
|
|
5680
|
+
"lightweight"
|
|
5681
|
+
]),
|
|
5682
|
+
selectedCategory: _enum([
|
|
5683
|
+
"powerful",
|
|
5684
|
+
"versatile",
|
|
5685
|
+
"lightweight",
|
|
5686
|
+
"unknown"
|
|
5687
|
+
]),
|
|
5688
|
+
categoryCandidateCount: number().int().min(0).max(512),
|
|
5689
|
+
method: _enum([
|
|
5690
|
+
"continuity",
|
|
5691
|
+
"equal-distribution",
|
|
5692
|
+
"only-candidate",
|
|
5693
|
+
"no-fit"
|
|
5694
|
+
]),
|
|
5695
|
+
fallback: boolean()
|
|
5696
|
+
}).strict();
|
|
5649
5697
|
const TurnSelectionSchema = discriminatedUnion("mode", [
|
|
5650
5698
|
object({ mode: literal("unknown") }).strict(),
|
|
5651
5699
|
object({ mode: literal("manual") }).strict(),
|
|
@@ -5663,7 +5711,8 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
|
|
|
5663
5711
|
"image-capability"
|
|
5664
5712
|
]),
|
|
5665
5713
|
candidateCount: number().int().positive(),
|
|
5666
|
-
fittingCandidateCount: number().int().nonnegative().optional()
|
|
5714
|
+
fittingCandidateCount: number().int().nonnegative().optional(),
|
|
5715
|
+
explanation: ExplanationSchema.optional()
|
|
5667
5716
|
}).strict()
|
|
5668
5717
|
]);
|
|
5669
5718
|
//#endregion
|
|
@@ -6259,6 +6308,50 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
|
|
|
6259
6308
|
}
|
|
6260
6309
|
};
|
|
6261
6310
|
//#endregion
|
|
6311
|
+
//#region lib/types/auto-selection-explanation.js
|
|
6312
|
+
function selectionExplanation(explanation, locale) {
|
|
6313
|
+
const zh = locale.startsWith("zh");
|
|
6314
|
+
const category = {
|
|
6315
|
+
powerful: "Powerful",
|
|
6316
|
+
versatile: "Versatile",
|
|
6317
|
+
lightweight: "Lightweight",
|
|
6318
|
+
unknown: zh ? "分类未知" : "unclassified"
|
|
6319
|
+
};
|
|
6320
|
+
const demand = {
|
|
6321
|
+
simple: zh ? "明确简单" : "demonstrably simple",
|
|
6322
|
+
routine: zh ? "常规、边界明确" : "routine and bounded",
|
|
6323
|
+
complex: zh ? "复杂" : "complex",
|
|
6324
|
+
unknown: zh ? "需求不确定" : "uncertain"
|
|
6325
|
+
};
|
|
6326
|
+
const signals = {
|
|
6327
|
+
"isolated-greeting": zh ? "独立问候" : "isolated greeting",
|
|
6328
|
+
"bounded-transformation": zh ? "有边界的内容转换" : "bounded transformation",
|
|
6329
|
+
reasoning: zh ? "推理任务" : "reasoning task",
|
|
6330
|
+
investigation: zh ? "调查或调试" : "investigation or debugging",
|
|
6331
|
+
continuation: zh ? "继续已有工作" : "continuation of existing work",
|
|
6332
|
+
"context-omitted": zh ? "判断上下文不完整" : "incomplete assessment context",
|
|
6333
|
+
"insufficient-evidence": zh ? "缺少足够判断依据" : "insufficient evidence"
|
|
6334
|
+
};
|
|
6335
|
+
return {
|
|
6336
|
+
conclusion: explanation.method === "no-fit" ? zh ? "没有候选能直接容纳估算输入;选中输入预算最大的模型,保留原生压缩或失败处理。" : "No candidate fits the estimated input. Selected the largest input budget for native recovery or failure." : explanation.fallback ? zh ? `目标分类 ${category[explanation.targetCategory]} 没有合格的可容纳候选,回退到 ${category[explanation.selectedCategory]}。` : `No eligible fitting ${category[explanation.targetCategory]} candidate; fell back to ${category[explanation.selectedCategory]}.` : zh ? `本轮判断为${demand[explanation.assessment.demand]};按当前偏好选择 ${category[explanation.selectedCategory]} 类模型。` : `This task was assessed as ${demand[explanation.assessment.demand]}; the preference policy selected ${category[explanation.selectedCategory]}.`,
|
|
6337
|
+
choice: explanation.method === "continuity" ? zh ? "上一轮模型仍满足本轮分类和输入要求,因此保持它。" : "Kept the previous model because it still meets this turn’s category and input requirements." : explanation.method === "only-candidate" ? zh ? "该分类只有一个可容纳的合格候选。" : "Only one eligible fitting candidate remains in this category." : explanation.method === "equal-distribution" ? zh ? `该分类有 ${explanation.categoryCandidateCount} 个可容纳候选;按本轮稳定等权规则选中,不代表质量排名。` : `Selected among ${explanation.categoryCandidateCount} fitting category candidates by stable equal-weight allocation, not a quality ranking.` : zh ? "所有候选均不适配;这不是成功的偏好匹配。" : "All candidates are oversized; this is not a successful preference match.",
|
|
6338
|
+
diagnostic: explanation.assessment.diagnostic === void 0 ? void 0 : explanation.assessment.diagnostic === "disabled" ? zh ? "语义判断实验未开启,本轮使用保守本地规则。" : "Semantic assessment is disabled; this turn used conservative local rules." : zh ? `语义判断未提供完整可用依据(${{
|
|
6339
|
+
unavailable: "没有可用分类模型",
|
|
6340
|
+
"invalid-result": "结果无效",
|
|
6341
|
+
timeout: "超时",
|
|
6342
|
+
failed: "请求失败",
|
|
6343
|
+
"context-omitted": "上下文不完整"
|
|
6344
|
+
}[explanation.assessment.diagnostic]});未将失败当作简单任务。` : `Semantic assessment did not provide complete usable evidence (${{
|
|
6345
|
+
unavailable: "no classifier available",
|
|
6346
|
+
"invalid-result": "invalid result",
|
|
6347
|
+
timeout: "timeout",
|
|
6348
|
+
failed: "request failed",
|
|
6349
|
+
"context-omitted": "incomplete context"
|
|
6350
|
+
}[explanation.assessment.diagnostic]}); failure was not treated as simplicity.`,
|
|
6351
|
+
assessment: `${zh ? "判断来源:" : "Assessment: "}${explanation.assessment.source === "semantic" ? zh ? "语义分类" : "semantic classification" : zh ? "本地规则" : "local rules"}${explanation.assessment.signals.length ? ` — ${explanation.assessment.signals.map((signal) => signals[signal]).join(zh ? "、" : ", ")}` : ""}`
|
|
6352
|
+
};
|
|
6353
|
+
}
|
|
6354
|
+
//#endregion
|
|
6262
6355
|
//#region lib/types/turn-selection-card.js
|
|
6263
6356
|
function TurnSelectionCard({ selection, locale = "en", incomplete = false, readState = "ready", retry }) {
|
|
6264
6357
|
const zh = locale.startsWith("zh");
|
|
@@ -6312,12 +6405,7 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
|
|
|
6312
6405
|
};
|
|
6313
6406
|
}, [open]);
|
|
6314
6407
|
const label = selection.mode === "auto" ? `Auto (${selection.preference})` : selection.mode === "manual" ? zh ? "手动" : "Manual" : zh ? "选择方式未知" : "Selection unknown";
|
|
6315
|
-
const
|
|
6316
|
-
"short-text-turn": zh ? "短文本轮次" : "Short text turn",
|
|
6317
|
-
"standard-turn": zh ? "常规轮次" : "Standard turn",
|
|
6318
|
-
"large-structured-turn": zh ? "较大结构化轮次" : "Large structured turn",
|
|
6319
|
-
"image-capability": zh ? "需要图片能力" : "Image capability required"
|
|
6320
|
-
}[selection.reason];
|
|
6408
|
+
const explanation = selection.mode === "auto" && selection.explanation !== void 0 ? selectionExplanation(selection.explanation, locale) : void 0;
|
|
6321
6409
|
const button = {
|
|
6322
6410
|
font: "inherit",
|
|
6323
6411
|
color: "inherit",
|
|
@@ -6352,7 +6440,7 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
|
|
|
6352
6440
|
height: 24,
|
|
6353
6441
|
flexShrink: 0
|
|
6354
6442
|
},
|
|
6355
|
-
"aria-label": zh ? "
|
|
6443
|
+
"aria-label": zh ? "为什么本轮选择这个模型" : "Why this model was selected",
|
|
6356
6444
|
"aria-expanded": open,
|
|
6357
6445
|
"aria-controls": open ? id : void 0,
|
|
6358
6446
|
"aria-haspopup": "dialog",
|
|
@@ -6382,7 +6470,7 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
|
|
|
6382
6470
|
color: "var(--dsw-alias-label-primary, CanvasText)",
|
|
6383
6471
|
lineHeight: 1.6
|
|
6384
6472
|
}
|
|
6385
|
-
}, (0, react.createElement)("strong", null, zh ? "
|
|
6473
|
+
}, (0, react.createElement)("strong", null, zh ? "为什么本轮选择这个模型" : "Why this model was selected"), selection.mode === "auto" ? explanation === void 0 ? (0, react.createElement)("p", null, zh ? "本轮未保留详细选模原因;不使用当前设置反推历史。" : "Detailed selection reasons were not retained for this turn; today’s settings cannot reconstruct them.") : (0, react.createElement)("div", null, (0, react.createElement)("p", null, explanation.conclusion), (0, react.createElement)("p", null, explanation.choice), (0, react.createElement)("details", null, (0, react.createElement)("summary", null, zh ? "查看判断依据" : "Assessment details"), (0, react.createElement)("p", null, explanation.assessment), (0, react.createElement)("p", null, zh ? `${selection.candidateCount} 个合格候选;${selection.fittingCandidateCount ?? "未知"} 个可容纳估算输入。` : `${selection.candidateCount} eligible candidates; ${selection.fittingCandidateCount ?? "unknown"} fit the estimated input.`), explanation.diagnostic ? (0, react.createElement)("p", null, explanation.diagnostic) : null, (0, react.createElement)("p", null, zh ? "分类来自供应方;不保证实际速度、费用或任务质量。" : "Supplier categories do not guarantee actual speed, cost or task quality."))) : null, incomplete ? (0, react.createElement)("p", null, zh ? "模型归属不完整:部分尝试或历史未记录模型。原生 Usage 保持不变。" : "Model attribution is incomplete: some attempts or history have no recorded model. Native Usage is unchanged.") : null, (0, react.createElement)("p", null, zh ? "此记录说明选择方式,不证明执行;实际模型以原生 Usage 为准。" : "Selection evidence is not execution proof; see native Usage for recorded models."), (0, react.createElement)("button", {
|
|
6386
6474
|
ref: close,
|
|
6387
6475
|
type: "button",
|
|
6388
6476
|
style: button,
|