dsh-github-copilot 0.4.0-alpha.85 → 0.4.0-alpha.87

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
@@ -43,7 +43,7 @@ This repository owns eleven narrow surfaces:
43
43
  8. Optional, provider-scoped Chat presentation for completed empty reasoning disclosures; durable content and encrypted replay metadata remain Core-owned.
44
44
  9. Compatibility-only policy restoration and request recovery for existing dedicated planner/executor Sessions. Model roles UI, settings writes and new dedicated roots are retired (#158); never reintroduce them or migrate histories implicitly.
45
45
  10. Managed-route estimated input/output admission, optional exact-request pressure signalling through official compaction recovery, and supported low summary effort only when no effort is already resolved. See [compaction budgets](./docs/copilot-compaction.md). Preserve truthful capacities, requested output caps, native errors/replay and transaction ownership; no hidden history trimming, chunking, new retry loop, competing compaction service or automatic model switch. The separately selected, single-service [manual recovery engine](./docs/manual-compaction-recovery.md) may use bounded, explicit intermediate summaries through the public subclass hook; the preventive default never claims recovery of an already oversized manual summary.
46
- 11. Optional account quota reads and a session-scoped composer usage control through public credentials, strict Remotes and additive slots. Keep account billing-cycle credits separate from context tokens and session cost. Missing, pooled, legacy and stale data must retain their real semantics; never infer credits from token estimates or account deltas. Managed terminal failed-zero usage protection and a separate plugin-owned historical context projection may diagnose invalid readings, never replace Core's meter, infer current occupancy/percentages or rewrite history. See [quota boundaries](./docs/copilot-usage.md).
46
+ 11. Optional account quota reads and a session-scoped composer usage control through public credentials, strict Remotes and additive slots. Keep account billing-cycle credits separate from context tokens and session cost. Missing, pooled, legacy and stale data must retain their real semantics; never infer credits from token estimates or account deltas. A separate plugin-owned historical context projection may diagnose failed-zero readings, never filter shared native usage, replace Core's meter, infer current occupancy/percentages or rewrite history. See [quota boundaries](./docs/copilot-usage.md).
47
47
 
48
48
  ## Retired model-role compatibility boundary (#158)
49
49
 
@@ -61,7 +61,7 @@ Alpha.25 admits native `subagent/descriptor` v3, already v3 in the retained rc.1
61
61
  - `src/reasoning-presentation.ts`: guarded native Chat delegation and historical Copilot provenance; filters temporary view props only, never messages, signatures, replay indexes or usage.
62
62
  - `src/remote.ts`: Typert Remote contribution. Never add credential payloads here.
63
63
  - `src/copilot-usage-host.ts`, `src/copilot-usage-remote.ts`, `src/copilot-usage-card.ts`, `src/copilot-usage-ui.ts`: bounded Host quota snapshots, an independent strict namespace and reversible composer presentation. No real account fetches in tests, private Client store/DOM injection, new credential owner or general model wire.
64
- - `src/context-usage-guard.ts`, `src/context-evidence.ts`, `src/context-evidence-ui.ts`: managed-only terminal failed-zero protection and bounded numeric historical evidence through a plugin-owned public projection and additive composer disclosure. Historical counts never become current occupancy; Core pressure, billing and durable events stay unchanged.
64
+ - `src/context-usage.ts`, `src/context-evidence.ts`, `src/context-evidence-ui.ts`: diagnostic-only failed-zero classification and bounded numeric historical evidence through a plugin-owned public projection and additive composer disclosure. Never filter native usage chunks to protect context readings: shared samples also feed Core's turn and cumulative accounting. Historical counts never become current occupancy; Core pressure, billing and durable events stay under Core ownership.
65
65
  - `src/current-provider.ts`: selected DSH route plus installed pi-ai catalog facts.
66
66
  - `src/temporary-models.ts`: exact, account-gated corrections with semantic protocol/capability retirement.
67
67
  - `src/model-protocol.ts`: explicit Core capability detection and conservative legacy fallback.
@@ -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 +1,17 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.4.0-alpha.87 (prepared)
4
+
5
+ - Remove managed terminal-zero usage filtering so native failure/cancellation samples remain available to Core's shared turn and cumulative accounting (#270).
6
+ - Retain unreliable failed-zero classification only in the independent historical context disclosure. Native zero pressure remains a known limitation, not a reason to remove shared usage or invent supplier receipts.
7
+ - Add native Responses zero/Anthropic nonzero cancellation and unchanged Core whole-turn regressions. Preserve errors, cancellation, retry and old histories; genuinely missing usage/lifecycle and timeout limitations remain explicit.
8
+
9
+ ## 0.4.0-alpha.86 (prepared)
10
+
11
+ - 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.
12
+ - 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.
13
+ - Disclose additional supplier charges outside native Chat Usage. Default rollout does not claim labeled-corpus calibration, change native history or perform profile installation/restart.
14
+
3
15
  ## 0.4.0-alpha.84 (prepared)
4
16
 
5
17
  - 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
@@ -19,7 +19,7 @@ Core still owns image conversion and history. See [image compatibility limits](.
19
19
  - **Account and models:** sign in, inspect account-discovered models, refresh metadata, and manage the account from the native GitHub Copilot row under **Settings → Models**. **Manage → Model preferences** can exclude exact models from both the managed picker and Auto without changing Core's flat picker.
20
20
  - **Search routing:** choose the primary and fallback search providers under **Plugins → dsh-github-copilot → Details**. The page intentionally exposes only those user-facing choices; protocol probes, timeouts, allowlists, and transport switches are not presented as routine UI. It also keeps the rc.2 lifecycle warning visible before disable/remove/upgrade actions. If the updated routed service is not active yet, the card reports **Restart required** instead of presenting a broken form.
21
21
  - **Usage:** eligible Copilot sessions get an optional **Credits** control beside the composer, with provider-reported billing-cycle data and explicit unavailable/stale states. The quota request alone combines Node default and OS trust roots without disabling certificate verification or relying on Desktop launcher environment inheritance.
22
- - **Context evidence:** managed requests suppress terminal all-zero usage on failure or cancellation. A separate composer disclosure can identify historical failed-zero readings and show the last applicable input sample, including cache. This is not current occupancy, does not replace the native `0%` meter, and does not rewrite history. See [context evidence boundaries](./docs/copilot-usage.md#historical-context-evidence).
22
+ - **Context evidence:** managed requests preserve native usage, including terminal zero on failure/cancellation, so context diagnostics cannot remove shared accounting evidence. A separate composer disclosure recognizes unreliable failed-zero samples and shows the last applicable historical input-plus-cache reading; it is not current occupancy, replaces no native `0%` meter and rewrites no history. See [context evidence boundaries](./docs/copilot-usage.md#historical-context-evidence).
23
23
  - **Missing Turn Usage:** a completed Copilot reply without a native total can show **Turn Usage incomplete**. Its read-only explanation distinguishes recorded local pre-dispatch budget blocks, same-attempt HTTP 408 diagnoses, other missing samples and incomplete history. Bounded step/record references and proven same-step retry completion explain what happened, not missing token amounts or billing; it never invents zero usage or a partial turn total. [Observation and boundaries](./docs/copilot-usage.md#missing-completed-turn-usage).
24
24
  - **Compatibility:** the plugin applies Copilot-only tool-schema, reasoning-presentation, request-budget, and account-model compatibility through published DSH APIs. It does not patch Core or maintain a second model catalog.
25
25
 
@@ -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.87`. 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.87/dsh-github-copilot-0.4.0-alpha.87.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.87` 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.87`, 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.87/dsh-github-copilot-0.4.0-alpha.87.tgz
472
+ curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.87/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
+ $actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.87.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
481
481
  if ($actual -cne $expected) { throw 'Release checksum mismatch' }
482
482
  ```
483
483
 
package/README.zh.md CHANGED
@@ -19,7 +19,7 @@ Core 管理。详见[图片兼容性与限制](./docs/image-input-compatibility.
19
19
  - **账号与模型:**在 **设置 → 模型** 的原生 GitHub Copilot 行内完成登录、查看账号发现模型、刷新元数据及账号管理。可在 **Manage → Model preferences** 中按精确 ID 排除模型,使其同时退出托管 picker 与 Auto 候选池;Core 原生 picker 仍保持平铺。
20
20
  - **搜索路由:**在 **插件 → dsh-github-copilot → 详情**选择主搜索 Provider 与兜底 Provider。页面只保留用户真正需要的两项选择,不再把协议探测、超时、白名单或传输开关作为日常配置暴露;同时会在停用/移除/升级前常驻显示 rc.2 生命周期提示。更新后的路由服务尚未激活时,卡片会明确显示 **需要重启生效(Restart required)**,而不是继续展示无法使用的表单。
21
21
  - **用量:**符合条件的 Copilot 会话会在输入框旁显示可选的 **Credits / 额度** 控件,展示供应方明确返回的计费周期数据,并如实区分不可用与历史快照。仅额度请求组合 Node 默认证书与系统信任根,无需依赖 Desktop launcher 的环境变量继承,且保持 TLS 验签。
22
- - **上下文证据:**托管请求失败或取消时,不再传递终止前的全零用量。独立的输入框提示可识别历史失败零值,并显示仍适用的最后输入采样(含缓存);它不是当前占用率,不替换原生 `0%` 表盘,也不改写历史。详见[上下文证据边界](./docs/copilot-usage.md#historical-context-evidence)。
22
+ - **上下文证据:**托管请求完整保留原生用量,包括失败或取消时的终止零值,避免上下文诊断删除共享统计证据。独立的输入框提示可识别不可信的失败零值,并显示仍适用的最后历史输入采样(含缓存);它不是当前占用率,不替换原生 `0%` 表盘,也不改写历史。详见[上下文证据边界](./docs/copilot-usage.md#historical-context-evidence)。
23
23
  - **整轮 Usage 缺失:**已完成的 Copilot 回复没有原生总量时,可显示**本轮用量统计不完整**。只读说明区分已记录的插件发出前预算拦截、同次尝试的 HTTP 408 诊断、其他缺失采样和不完整历史。有限的步骤/记录定位及有证据的同一步骤重试成功只解释经过,不推断缺失 token 数或计费;不会补造零用量或把部分步骤合计当成整轮总量。详见[观察与边界](./docs/copilot-usage.md#missing-completed-turn-usage)。
24
24
  - **兼容处理:**插件通过 DSH 已发布公开接口提供 Copilot 专用 Tool Schema、Thinking 展示、请求预算及账号模型兼容,不修改 Core,也不维护第二套模型目录。
25
25
 
@@ -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.87`。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.87/dsh-github-copilot-0.4.0-alpha.87.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.87`。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.87`,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.87/dsh-github-copilot-0.4.0-alpha.87.tgz
483
+ curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.87/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
+ $actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.87.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
492
492
  if ($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.87"
12
12
  },
13
13
  "evidence": {
14
14
  "kind": "source-and-synthetic-test-inventory",
@@ -317,18 +317,20 @@
317
317
  "required": true,
318
318
  "evidenceScope": "synthetic-stream-replay-and-additive-ui-not-current-occupancy-or-live-desktop",
319
319
  "sourceMarkers": [
320
- {"file": "src/preview-route.ts", "marker": "guardContextUsage"},
320
+ {"file": "src/context-usage.ts", "marker": "isZeroContextUsage"},
321
321
  {"file": "src/index.ts", "marker": "installContextEvidence(ctx)"},
322
322
  {"file": "src/client.ts", "marker": "registerContextEvidenceUi"},
323
323
  {"file": "src/context-evidence.ts", "marker": "githubCopilotContextEvidence"},
324
324
  {"file": "docs/copilot-usage.md", "marker": "historical input sample, not current occupancy"}
325
325
  ],
326
326
  "tests": [
327
- {"file": "tests/context-usage-guard.spec.ts", "name": "does not report failed zero usage on %s"},
327
+ {"file": "tests/context-usage.spec.ts", "name": "classifies zero only for separate historical evidence without changing the sample"},
328
328
  {"file": "tests/context-evidence.spec.ts", "name": "replays failed zero samples without discarding the last valid input sample"},
329
329
  {"file": "tests/context-evidence-ui.spec.ts", "name": "labels counts as historical rather than current occupancy in %s"},
330
330
  {"file": "tests/fixtures/session-context-core.fixture.ts", "name": "cold-folds native model selections independently without replacing the controller projection"},
331
- {"file": "tests/preview-route.spec.ts", "name": "does not let native SDK failed zero usage reset context evidence or fabricate settled usage"}
331
+ {"file": "tests/preview-route.spec.ts", "name": "forwards native SDK failed zero usage without changing the shared accounting stream"},
332
+ {"file": "tests/preview-route.spec.ts", "name": "preserves native cancellation usage on %s (%s input tokens)"},
333
+ {"file": "tests/fixtures/turn-usage-core.fixture.ts", "name": "retains native whole-turn accounting for a sampled %s attempt after successful steps"}
332
334
  ]
333
335
  },
334
336
  {
@@ -1124,7 +1126,8 @@
1124
1126
  {"file": "tests/auto-task-assessment.spec.ts", "name": "preserves valid bounded rows and prioritizes the current user and nearest task over verbose output"},
1125
1127
  {"file": "tests/auto-selection-explanation.spec.ts", "name": "distinguishes local rule coverage from absent conversation context in both languages"},
1126
1128
  {"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"},
1129
+ {"file": "tests/config.spec.ts", "name": "defaults semantic Auto assessment on while preserving explicit opt-out"},
1130
+ {"file": "tests/preview-route.spec.ts", "name": "assesses Auto with setting %s and freezes the captured reason across retries"},
1128
1131
  {"file": "tests/turn-selection-card.spec.ts", "name": "explains a captured task/category decision with progressive details (%s)"},
1129
1132
  {"file": "tests/auto-model-routing.spec.ts", "name": "does not discard a complete Core assistant message when it contains reasoning"},
1130
1133
  {"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
  | --- | --- | --- | --- |
@@ -22,13 +22,13 @@ Provider or Session changes, unmounting and missing supported runtime seams revo
22
22
 
23
23
  Official rc.2 can replace the native context-pressure sample with the adapter's all-zero usage on a failed attempt. The message breakdown is a separate heuristic projection, so a native `0%` reading can coexist with substantial message tokens. Neither that zero nor the breakdown proves the current exact occupancy.
24
24
 
25
- The managed route delays one terminal all-zero usage chunk. An adjacent error or aborted finish discards that sample while preserving the finish; a thrown error or truncated stream also cannot certify that zero. Successful stop, max-tokens and tool-calls finishes preserve reported zero usage. Nonzero samples, billing counts, content ordering and failure semantics remain unchanged. This guard applies only to `github-copilot-preview`, not the Core-owned canonical adapter. It adds no retry, compaction, trimming or model switch.
25
+ The managed route preserves native usage chunks immediately, including all-zero samples before error or aborted finishes. Usage is shared accounting evidence, not a context-only signal. The former terminal-zero filter was removed in alpha.87 (#270): dropping a sample to protect context pressure also made Core's whole-turn accounting unavailable. Numeric zero alone cannot distinguish the SDK's default from an explicit supplier report, so the plugin neither deletes it nor certifies it as a billing receipt. Native context pressure may consequently show zero after failure; the separate disclosure explains uncertainty instead of modifying Core's meter. No retry, compaction, trimming or model switch is added.
26
26
 
27
27
  The separate, strict `githubCopilotContextEvidence` session projection reads only routing and numeric usage from ordinary durable events. It keeps the last applicable input-plus-cache sample when a failed all-zero attempt is replayed. Model changes, compaction, surface replacement, conflicting source attribution and invalid metadata revoke the sample. It never reads message content or opaque replay, registers under a Core key, changes the native pressure projection, or rewrites durable history.
28
28
 
29
29
  An additive composer disclosure identifies missing or unreliable context evidence for the current open Copilot Session. Any retained count is explicitly a **historical input sample, not current occupancy**; no capacity or percentage is inferred. The native context ring and account Credits control remain separate and unchanged. Missing public projection/slot/runtime seams produce named diagnostics rather than guessed counts. Old histories can therefore still show native `0%`; the disclosure explains the uncertainty instead of claiming an in-place native-meter repair.
30
30
 
31
- Local synthetic tests establish guarded-stream, historical-fold and presentation behavior only. Exact published-adapter and public-registry acceptance, complete CI, publication and loaded Desktop state must be verified separately. No live provider call or Session restart is needed for these tests.
31
+ Local synthetic tests establish native-stream preservation, historical-fold and presentation behavior only. Exact published-adapter and public-registry acceptance, complete CI, publication and loaded Desktop state must be verified separately. No live provider call or Session restart is needed for these tests.
32
32
 
33
33
  ## Missing completed-turn Usage
34
34
 
@@ -38,6 +38,12 @@ One observed completed turn contained 57 successful assistant messages with repo
38
38
 
39
39
  Official rc.2 `deriveTurnTokenUsage` requires complete lifecycle and exact usage for every attempt. One attempt without a sample makes its whole-turn result unavailable, so `TurnTailNodeView` omits native Usage. This is Core's existing fail-closed accounting rule triggered by our preventive pressure path, not evidence that all requests had no usage and not a regression in single-model exclusion saves.
40
40
 
41
+ ### Cancelled and failed terminal samples (#270)
42
+
43
+ Cancellation does not inherently disable official rc.2 turn accounting: a complete lifecycle with a valid sampled aborted attempt remains eligible. Before alpha.87, the managed terminal-zero filter removed such samples. For example, a successful 120-token step followed by a zero-sampled cancelled step retained Session cumulative counts but lost the entire turn total after filtering. The route now forwards native samples unchanged; historical context evidence still treats failed zero as unreliable, independently of accounting.
44
+
45
+ This is not a promise that every cancelled turn has complete or exact supplier usage. Responses may end before the supplier's final receipt and the SDK may emit its initialized zero. Missing lifecycle, unsampled attempts, pre-dispatch budget failures and native/plugin timeout interruption remain distinct limitations. No prior history is rewritten and no missing sample, partial total or billing amount is invented. Existing native usage already emitted before an error must not be removed for context-only diagnostics.
46
+
41
47
  ### Plugin-local explanation
42
48
 
43
49
  A plugin-owned public conversation definition retains bounded counts of settlements without reported samples and finish-only attempts with the exact recorded local diagnostic. On a completed Copilot reply whose native tail has no `tokenUsage`, the additive assistant-actions control opens **Turn Usage incomplete** (previously **Turn Usage unavailable**). It uses the incumbent nonmodal popover pattern rather than expanding the native fixed-height footer.