dsh-github-copilot 0.4.0-alpha.85 → 0.4.0-alpha.86

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 CHANGED
@@ -248,12 +248,14 @@ names, effort or context capacity as a quality category. Hard eligibility/input
248
248
  fit precede task/preference policy; unknown category and uncertain task evidence
249
249
  remain explicit. Keep suitable previous-model continuity and equal-weight
250
250
  tie-breaking within the first available category. Capture actual reasons once
251
- per turn without durable decision events or changing Usage. The optional
252
- `autoSemanticAssessment` experiment is off by default: one bounded concrete
251
+ per turn without durable decision events or changing Usage.
252
+ `autoSemanticAssessment` is default-on by explicit user rollout request (#267),
253
+ only for locally unknown demand; preserve explicit false opt-out. One bounded concrete
253
254
  native-adapter request, no tools/Auto recursion/new retry, explicit failures and
254
255
  omitted-context conservatism. Extra supplier charges are separate from Chat
255
- Usage. Require labeled-corpus calibration before enabling by default; synthetic
256
- tests do not prove GitHub-private routing equivalence. See `docs/auto-task-routing.md`.
256
+ Usage. Default rollout is not labeled-corpus calibration; require that evaluation
257
+ before claiming calibrated performance. Synthetic tests do not prove GitHub-private
258
+ routing equivalence. See `docs/auto-task-routing.md`.
257
259
 
258
260
  The turn selection Host endpoint must use `TurnSelectionController`, extending
259
261
  public `TypertRemoteService` with `@Remote get`. A plain `ctx.provide` object
package/CHANGELOG.md CHANGED
@@ -1,5 +1,11 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.4.0-alpha.86 (prepared)
4
+
5
+ - Enable bounded semantic Auto assessment by default for locally unknown tasks at the user's explicit request (#267). Preserve existing explicit false settings and document the opt-out.
6
+ - Apply the same default to unset managed-route settings, while retaining local known-task short-circuiting, one auxiliary call per admitted turn, strict output, timeout/cancellation/account guards and omitted-context protection.
7
+ - Disclose additional supplier charges outside native Chat Usage. Default rollout does not claim labeled-corpus calibration, change native history or perform profile installation/restart.
8
+
3
9
  ## 0.4.0-alpha.84 (prepared)
4
10
 
5
11
  - Add bounded numeric composition of the actual final request for verified Copilot `408 / user_request_timeout`, distinguishing conversation, tool definitions, protocol-owned system/instructions and residual framing (#263).
package/README.md CHANGED
@@ -109,7 +109,7 @@ The Host reads GitHub's internal quota endpoint using the existing canonical OAu
109
109
 
110
110
  ## Install and sign in
111
111
 
112
- The commands below target the package version `0.4.0-alpha.85`. 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
+ The commands below target the package version `0.4.0-alpha.86`. 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):
113
113
 
114
114
  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):
115
115
 
@@ -122,10 +122,10 @@ Include any launcher patch files with repeated `--patch /absolute/file` argument
122
122
  For a standalone named profile only, the supported CLI command is:
123
123
 
124
124
  ```sh
125
- dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.85/dsh-github-copilot-0.4.0-alpha.85.tgz
125
+ dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.86/dsh-github-copilot-0.4.0-alpha.86.tgz
126
126
  ```
127
127
 
128
- For Desktop profiles, use Desktop's native package manager with `dsh-github-copilot@0.4.0-alpha.85` 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
+ For Desktop profiles, use Desktop's native package manager with `dsh-github-copilot@0.4.0-alpha.86` 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.
129
129
 
130
130
  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.
131
131
 
@@ -147,7 +147,7 @@ The managed GitHub Copilot group includes **Auto · Balance**, **Auto · Efficie
147
147
 
148
148
  Local rules also recognize isolated fenced JSON/CSV conversions and line sorting as routine, and exact continuations of a recent explicit difficult task as complex. New tasks break continuation inheritance. `uncertain` means demand is unresolved; insufficient local evidence is not proof that the conversation has no context.
149
149
 
150
- The optional `github-copilot.autoSemanticAssessment: true` experiment recognizes contextual tasks with one bounded auxiliary model call **only when local demand is unknown**; it is **off by default** until calibrated. Its bounded input prioritizes current and preceding user requests without dismissing omitted context. 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.
150
+ Semantic assessment is **enabled by default**, using one bounded auxiliary model call **only when local demand is unknown**. Set `github-copilot.autoSemanticAssessment: false` to opt out; existing explicit false settings remain respected and are not migrated. Its bounded input prioritizes current and preceding user requests without dismissing omitted context. 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 user-authorized rollout is not labeled-corpus calibration or GitHub's private Auto service.
151
151
 
152
152
  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.
153
153
 
@@ -186,7 +186,7 @@ Agents should treat the browser authorization as a human handoff, not as a token
186
186
  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.
187
187
  6. Use **Sign out** only when the user explicitly asks to disconnect the account. It deletes the Copilot credential record but preserves route settings.
188
188
 
189
- 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.85`, 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).
189
+ 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.86`, 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).
190
190
 
191
191
  **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.
192
192
 
@@ -468,8 +468,8 @@ Report the published Release URL, version, tag/commit and verified asset SHA-256
468
468
  `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.
469
469
 
470
470
  ```sh
471
- curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.85/dsh-github-copilot-0.4.0-alpha.85.tgz
472
- curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.85/SHA256SUMS
471
+ curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.86/dsh-github-copilot-0.4.0-alpha.86.tgz
472
+ curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.86/SHA256SUMS
473
473
  sha256sum --check SHA256SUMS
474
474
  ```
475
475
 
@@ -477,7 +477,7 @@ PowerShell can verify the same two downloaded files with:
477
477
 
478
478
  ```powershell
479
479
  $expected = (Get-Content .\SHA256SUMS).Split()[0]
480
- $actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.85.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
480
+ $actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.86.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
481
481
  if ($actual -cne $expected) { throw 'Release checksum mismatch' }
482
482
  ```
483
483
 
package/README.zh.md CHANGED
@@ -27,7 +27,7 @@ Core 管理。详见[图片兼容性与限制](./docs/image-input-compatibility.
27
27
 
28
28
  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。
29
29
 
30
- > 当前文档与安装命令对应版本 `0.4.0-alpha.85`。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
+ > 当前文档与安装命令对应版本 `0.4.0-alpha.86`。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。
31
31
 
32
32
  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。
33
33
 
@@ -124,10 +124,10 @@ node package/scripts/check-search-composition.mjs --profile-dir /absolute/profil
124
124
  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:
125
125
 
126
126
  ```sh
127
- dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.85/dsh-github-copilot-0.4.0-alpha.85.tgz
127
+ dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.86/dsh-github-copilot-0.4.0-alpha.86.tgz
128
128
  ```
129
129
 
130
- 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.85`。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
+ 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.86`。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。
131
131
 
132
132
  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。
133
133
 
@@ -149,7 +149,7 @@ Desktop profile 请在完成同样的预检后,使用 Desktop 原生包管理
149
149
 
150
150
  本地规则也会将独立、单一代码围栏内的 JSON/CSV 转换和行排序识别为常规任务,将近期明确困难任务的精确续接识别为复杂任务;新任务会切断继承。`uncertain` 表示需求尚无法确定,本地依据不足不代表会话没有上下文。
151
151
 
152
- 可选实验 `github-copilot.autoSemanticAssessment: true` **仅在本地需求未知时**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**。有界输入优先保留当前和前一条用户请求,但不会忽略上下文省略。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。
152
+ 语义判断**默认开启**,**仅在本地需求未知时**通过一次有界的辅助模型请求判断上下文任务。可设置 `github-copilot.autoSemanticAssessment: false` 关闭;已有的显式 false 配置会保留,不自动迁移。有界输入优先保留当前和前一条用户请求,但不会忽略上下文省略。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。这次默认开启由用户明确授权,不代表已完成标注语料校准,也不是 GitHub 的私有 Auto 服务。
153
153
 
154
154
  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。
155
155
 
@@ -188,7 +188,7 @@ Agent 应把浏览器授权视为需要用户完成的 handoff,而不是自行
188
188
  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。
189
189
  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。
190
190
 
191
- 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.85`,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。
191
+ 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.86`,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。
192
192
 
193
193
  **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。
194
194
 
@@ -479,8 +479,8 @@ node scripts/agent.mjs attribution "DeepSeek Harness (DSH)"
479
479
  `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。
480
480
 
481
481
  ```sh
482
- curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.85/dsh-github-copilot-0.4.0-alpha.85.tgz
483
- curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.85/SHA256SUMS
482
+ curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.86/dsh-github-copilot-0.4.0-alpha.86.tgz
483
+ curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.86/SHA256SUMS
484
484
  sha256sum --check SHA256SUMS
485
485
  ```
486
486
 
@@ -488,7 +488,7 @@ PowerShell 可以对已下载的同一组文件执行:
488
488
 
489
489
  ```powershell
490
490
  $expected = (Get-Content .\SHA256SUMS).Split()[0]
491
- $actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.85.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
491
+ $actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.86.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
492
492
  if ($actual -cne $expected) { throw 'Release checksum mismatch' }
493
493
  ```
494
494
 
@@ -8,7 +8,7 @@
8
8
  },
9
9
  "package": {
10
10
  "name": "dsh-github-copilot",
11
- "version": "0.4.0-alpha.85"
11
+ "version": "0.4.0-alpha.86"
12
12
  },
13
13
  "evidence": {
14
14
  "kind": "source-and-synthetic-test-inventory",
@@ -1124,7 +1124,8 @@
1124
1124
  {"file": "tests/auto-task-assessment.spec.ts", "name": "preserves valid bounded rows and prioritizes the current user and nearest task over verbose output"},
1125
1125
  {"file": "tests/auto-selection-explanation.spec.ts", "name": "distinguishes local rule coverage from absent conversation context in both languages"},
1126
1126
  {"file": "tests/auto-task-assessment.spec.ts", "name": "preserves caller cancellation instead of using a success-shaped fallback"},
1127
- {"file": "tests/preview-route.spec.ts", "name": "assesses Auto through one concrete public native adapter call and freezes the captured reason across retries"},
1127
+ {"file": "tests/config.spec.ts", "name": "defaults semantic Auto assessment on while preserving explicit opt-out"},
1128
+ {"file": "tests/preview-route.spec.ts", "name": "assesses Auto with setting %s and freezes the captured reason across retries"},
1128
1129
  {"file": "tests/turn-selection-card.spec.ts", "name": "explains a captured task/category decision with progressive details (%s)"},
1129
1130
  {"file": "tests/auto-model-routing.spec.ts", "name": "does not discard a complete Core assistant message when it contains reasoning"},
1130
1131
  {"file": "tests/auto-model-routing.spec.ts", "name": "retains the native current-surface and tool-envelope measurement as an input floor"},
@@ -31,10 +31,13 @@ continue an unresolved investigation is not evidence of low demand. Long input
31
31
  can be mechanical. Prior assistant/tool work prevents a greeting/continuation
32
32
  shortcut from claiming an isolated simple task.
33
33
 
34
- Use a conservative local assessment as the default. Unknown is an explicit
35
- outcome, never silently translated into simple. Optional semantic assessment is
36
- an experiment until evaluated against annotated tasks; it must not claim
37
- equivalence to GitHub's private router or calibrated confidence.
34
+ Use conservative local assessment first. Unknown is an explicit outcome, never
35
+ silently translated into simple. Semantic assessment is enabled by default for
36
+ locally unknown demand at the user's explicit rollout request (#267), not
37
+ because labeled-corpus calibration has completed. Set
38
+ `github-copilot.autoSemanticAssessment: false` to disable auxiliary inference;
39
+ an existing explicit false remains respected. It must not claim equivalence to
40
+ GitHub's private router or calibrated confidence.
38
41
 
39
42
  Local rules recognize an isolated, explicit JSON-to-CSV/CSV-to-JSON conversion
40
43
  or line sort only when the entire request is at most 1600 characters, contains
@@ -48,7 +51,7 @@ inheritance; simple/routine demand is never inherited.
48
51
  rules cannot establish demand, not that the conversation has no context.
49
52
  Attachments, unfamiliar instructions and genuinely ambiguous continuations can
50
53
  still remain unknown. These refinements do not change category preference,
51
- previous-model eligibility or the default-disabled semantic experiment.
54
+ previous-model eligibility or semantic safeguards.
52
55
 
53
56
  The semantic experiment uses one fixed concrete account candidate through the
54
57
  existing managed native adapter, never an Auto ID and never `ctx.llm` routing
@@ -131,7 +134,10 @@ account proof, image admission and compaction fixture coverage. Full protected
131
134
  Windows/Linux CI remains mandatory before merge/release. No live inference
132
135
  calls are needed for synthetic acceptance.
133
136
 
134
- Before making semantic assessment the default, evaluate a reviewed labeled
135
- corpus for complex-to-simple errors, extra latency, token use and stability
136
- across languages and prompt injection. Synthetic passing tests are not this
137
- evaluation. Publication does not authorize profile installation or restart.
137
+ Default enablement is a user-authorized rollout, not an accuracy qualification.
138
+ Evaluate a reviewed labeled corpus for complex-to-simple errors, extra latency,
139
+ token use and stability across languages and prompt injection before claiming
140
+ calibrated performance. Synthetic passing tests are not this evaluation.
141
+ Missing settings adopt the enabled default after upgrade; explicit false is
142
+ not overwritten and no profile migration is performed. Publication does not
143
+ authorize profile installation or restart.
@@ -57,12 +57,13 @@ investigation, bounded explicit continuations of those difficult tasks, and
57
57
  isolated fenced mechanical transformations. Other tasks remain uncertain rather
58
58
  than guessing from length; insufficient local evidence does not mean the
59
59
  conversation lacks context.
60
- An optional `github-copilot.autoSemanticAssessment: true` experiment makes one
60
+ Default-enabled `github-copilot.autoSemanticAssessment` makes one
61
61
  bounded auxiliary native-adapter call to a concrete, non-excluded supplier
62
62
  Lightweight model only for locally unknown demand. It prioritizes the current
63
63
  and preceding user requests without removing omitted-context safeguards. It
64
64
  adds latency and supplier charges not included in native
65
- chat Usage. It is off by default pending labeled-corpus calibration.
65
+ chat Usage. Set it to `false` to opt out; existing explicit false is preserved.
66
+ This user-authorized default rollout does not claim labeled-corpus calibration.
66
67
 
67
68
  | Task demand | Efficiency | Balance (`auto`) | Intelligence |
68
69
  | --- | --- | --- | --- |
package/lib/index.js CHANGED
@@ -1847,7 +1847,7 @@ function installContextEvidence(ctx) {
1847
1847
  //#endregion
1848
1848
  //#region package.json
1849
1849
  var name$1 = "dsh-github-copilot";
1850
- var version = "0.4.0-alpha.85";
1850
+ var version = "0.4.0-alpha.86";
1851
1851
  //#endregion
1852
1852
  //#region lib/types/probe.js
1853
1853
  /**
@@ -2214,7 +2214,7 @@ const Config = z.object({
2214
2214
  accountModelFailureCooldownMs: z.number().step(1).min(0).max(MAX_TIMEOUT_MS).default(3e5),
2215
2215
  excludedModelIds: z.array(z.string()).default([]).hidden().volatile(),
2216
2216
  followParentModel: z.boolean().default(false).volatile(),
2217
- autoSemanticAssessment: z.boolean().default(false),
2217
+ autoSemanticAssessment: z.boolean().default(true),
2218
2218
  parentModelFollow: z.array(z.object({
2219
2219
  childSessionId: z.string().min(1),
2220
2220
  parentSessionId: z.string().min(1)
@@ -8857,7 +8857,7 @@ function apply$1(ctx, config = {}) {
8857
8857
  budgetPolicy: () => budgetSettings(),
8858
8858
  parentModelBindings: () => cacheSettings().parentModelFollow ?? [],
8859
8859
  followParentModel: () => cacheSettings().followParentModel === true,
8860
- semanticAssessment: () => cacheSettings().autoSemanticAssessment === true,
8860
+ semanticAssessment: () => cacheSettings().autoSemanticAssessment ?? true,
8861
8861
  assessmentDiagnostic: (code) => ctx.logger.warn(code),
8862
8862
  async classifyTask(input, signal) {
8863
8863
  const snapshot = await discoverSnapshot({ signal });
@@ -43,7 +43,7 @@ export interface InlineConfig {
43
43
  parentModelFollow?: ParentModelBinding[];
44
44
  /** Profile-wide next-turn policy for supported native children. */
45
45
  followParentModel?: boolean;
46
- /** Optional extra bounded inference for task assessment; uncalibrated experiment, off by default. */
46
+ /** Default-on bounded task assessment; explicit false opts out of auxiliary inference. */
47
47
  autoSemanticAssessment?: boolean;
48
48
  /** Estimated managed-route input headroom, separate from truthful catalog capacities. */
49
49
  requestBudgetSafetyTokens?: number;
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "dsh-github-copilot",
3
3
  "description": "DSH companion for GitHub Copilot sign-in, account-aware model profiles, tool compatibility, and provider-hosted search.",
4
- "version": "0.4.0-alpha.85",
4
+ "version": "0.4.0-alpha.86",
5
5
  "publishConfig": {
6
6
  "access": "public",
7
7
  "registry": "https://registry.npmjs.org/",