dsh-github-copilot 0.4.0-alpha.94 → 0.4.0-alpha.96
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 +1 -1
- package/CHANGELOG.md +12 -0
- package/README.md +9 -7
- package/README.zh.md +9 -7
- package/deployment-baseline.json +7 -3
- package/docs/copilot-usage.md +113 -107
- package/docs/model-compatibility-acceptance.md +26 -7
- package/lib/client.js +168 -58
- package/lib/client.js.map +1 -1
- package/lib/index.js +48 -8
- package/lib/remote.js +61 -32
- package/lib/types/replay-recovery-host.d.ts +2 -1
- package/lib/types/replay-recovery-remote.d.ts +2 -1
- package/lib/types/replay-recovery-types.d.ts +10 -0
- package/lib/types/replay-recovery-ui.d.ts +9 -2
- package/lib/types/replay-recovery.d.ts +4 -2
- package/package.json +1 -1
package/AGENTS.md
CHANGED
|
@@ -83,7 +83,7 @@ Alpha.25 admits native `subagent/descriptor` v3, already v3 in the retained rc.1
|
|
|
83
83
|
|
|
84
84
|
## Non-negotiable invariants
|
|
85
85
|
|
|
86
|
-
- Explicit replay recovery (#279) is default-off and bound to the initiating native request signal, Session, model and current account proof. Only exact verified scope failures capture bounded full-item fingerprints; no replay bytes reach Client or storage. Two-stage confirmation
|
|
86
|
+
- Explicit replay recovery (#279, #289) is default-off and bound to the initiating native request signal, Session, model and current account proof. Only exact verified scope failures capture bounded full-item fingerprints; no replay bytes reach Client or storage. Public Session running/error snapshots trigger read-only notices on open/settled turns, never polling or durable recovery events. Two-stage confirmation chooses next matching turn (all steps/retries until turn/end) or bounded Session consent, omitting matching old encrypted items and their item summaries only on outgoing requests, never durable history or new reasoning. Preserve get/setEnabled descriptor identities and legacy session-consent semantics; authorize is additive. Active-turn writes, ambient-scope calls and automatic retries are forbidden. Expiry, disposal and proof discontinuity revoke evidence. See `docs/model-compatibility-acceptance.md`.
|
|
87
87
|
|
|
88
88
|
- Do not implement a second general wire adapter or independently maintained static Copilot model catalog. The account-scoped route composes the published adapter and SDK with validated supplier metadata.
|
|
89
89
|
- Protocol and capability corrections must follow authenticated, current account metadata; new model IDs must not need new implementation tables. Native pi metadata may be reused only where it agrees with advertised endpoints and capabilities. Matching IDs alone do not prove correctness or authorize migration back into another Core catalog. Preserve old bounded ownership journals solely for verified restoration of legacy writes, never for new global protocol overrides.
|
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,17 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 0.4.0-alpha.96 (prepared)
|
|
4
|
+
|
|
5
|
+
- Surface verified replay-recovery evidence automatically when an eligible Session opens or its native turn settles; ordinary conversations remain uncluttered (#289).
|
|
6
|
+
- Add explicit next-matching-turn or bounded Session consent, defaulting the choice to one turn. All native steps/retries share that turn's authorization, which is consumed at turn end. Confirmation never sends or retries a message.
|
|
7
|
+
- Preserve exact-item/proof guards, old Remote identities and native history ownership. Add native gateway and desktop/mobile component coverage, local dismissal, explicit read failures and expiry updates. This is not a supplier 408 fix.
|
|
8
|
+
|
|
9
|
+
## 0.4.0-alpha.95 (prepared)
|
|
10
|
+
|
|
11
|
+
- Preserve native usage and chunk order before restoring dispatch-local byte-idle or replay errors (#285). Previously the owned error could be thrown before the SDK's terminal usage, discarding both failed-zero and real nonzero samples.
|
|
12
|
+
- Prove the correction with unchanged native Responses and Anthropic timeout regressions. Preserve structured errors, cancellation, retry policy and wire/history ownership.
|
|
13
|
+
- Document the separate native failed-zero context-pressure limitation and retry backoff timing. This is an accounting correction, not a cure for supplier HTTP 408 or a replacement native context meter; loaded Desktop acceptance remains unverified.
|
|
14
|
+
|
|
3
15
|
## 0.4.0-alpha.94 (prepared)
|
|
4
16
|
|
|
5
17
|
- Count native Responses tool-output image spans under `function_call_output.output[]` in bounded timeout diagnostics (#287), rather than misclassifying them as remaining history.
|
package/README.md
CHANGED
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
|
|
9
9
|
GitHub Copilot account discovery, contextual Auto routing and hosted search for DSH. The plugin reuses DSH's published native adapter and one Host-owned OAuth account; it does not patch Core or maintain a second model catalog.
|
|
10
10
|
|
|
11
|
-
**Source candidate: `0.4.0-alpha.
|
|
11
|
+
**Source candidate: `0.4.0-alpha.96` (unreleased). Supported host: official DSH / Windows Desktop `0.2.0-rc.2`.** Earlier DSH pins are historical evidence, not supported installation targets. Publication, profile installation and the version loaded by a running Host are separate states. The versioned commands below are for this candidate after publication, not evidence that its assets exist.
|
|
12
12
|
|
|
13
13
|
## What you can do
|
|
14
14
|
|
|
@@ -40,10 +40,10 @@ Supply any launcher patches with repeated `--patch /absolute/file`. Require `sup
|
|
|
40
40
|
For a **standalone named profile**:
|
|
41
41
|
|
|
42
42
|
```sh
|
|
43
|
-
dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.
|
|
43
|
+
dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.96/dsh-github-copilot-0.4.0-alpha.96.tgz
|
|
44
44
|
```
|
|
45
45
|
|
|
46
|
-
For **Desktop**, its native package manager accepts `dsh-github-copilot@0.4.0-alpha.
|
|
46
|
+
For **Desktop**, its native package manager accepts `dsh-github-copilot@0.4.0-alpha.96` after publication. Official rc.2's **Desktop-bundled CLI** also supports reserved-profile plugin management; a global/generic `dsh` shim is not equivalent. Qualify the installed entry before use. See [Desktop CLI qualification](./docs/npm-distribution.md#desktop-bundled-cli-on-official-rc2) and the distinct [standalone offline procedure](./docs/npm-distribution.md#controlled-offline-cli-maintenance-for-standalone-profiles). Neither path authorizes registry-policy bypass, peer patches or configuration deletion.
|
|
47
47
|
|
|
48
48
|
After an approved reload/restart:
|
|
49
49
|
|
|
@@ -94,6 +94,8 @@ canonical inline path; it is not a third routed fallback. Fetch is unchanged.
|
|
|
94
94
|
|
|
95
95
|
Native context occupancy and Turn Usage remain Core-owned. The plugin forwards usage unchanged, including zero samples on failure/cancellation. Its separate context disclosure reports historical evidence, never current occupancy or a replacement `0%` meter. **Turn Usage incomplete** explains missing samples/lifecycle and recorded local blocks; it invents neither zero usage nor partial totals. Cancellation can retain usage, but does not guarantee a final supplier receipt. [Usage boundaries](./docs/copilot-usage.md).
|
|
96
96
|
|
|
97
|
+
Owned timeout/replay errors preserve native usage before terminal failure restoration, including nonzero samples. A failed zero can still make the native ring show `0%`; this is not proof of an empty request. Retry-entry times describe backoff, not the failed request's duration. These accounting fixes do not cure supplier HTTP 408 or change retry policy.
|
|
98
|
+
|
|
97
99
|
Managed request admission preserves truthful input/output limits and native transactions. Automatic pressure uses the initiating Agent's actual bound compaction service; a preset without an engine cannot borrow global recovery. Already oversized manual summaries require separately selected [manual recovery](./docs/manual-compaction-recovery.md), not a promise that preventive admission can rescue them.
|
|
98
100
|
|
|
99
101
|
For continuing steps with a committed managed route and no pending model change, known input pressure is reduced before Core opens the next model attempt. Successful native reduction avoids an unsampled local-pressure attempt that would make whole-turn Usage unavailable. First steps, pending selections, new fixed-prefix growth and final hard-budget refusals retain existing admission; this does not repair historical totals or invent missing usage.
|
|
@@ -132,7 +134,7 @@ Configuration is under `github-copilot`. Credentials, endpoint definitions and a
|
|
|
132
134
|
| Selection unknown/unavailable | Distinguish lost evidence from read failure; Retry only rereads |
|
|
133
135
|
| Missing/cancelled Turn Usage | Read [usage limitations](./docs/copilot-usage.md); do not infer zero billing |
|
|
134
136
|
| History fails on `github-copilot/auto-model-decision` | Use [detached, check-first recovery](./docs/automatic-model-routing.md#recovering-affected-histories); never replace live history without stopped writers and approval |
|
|
135
|
-
| AUTH, Responses replay-scope or TLS failure | Review [request diagnostics](./docs/model-compatibility-acceptance.md#authentication-replay-and-request-diagnostics) and [usage TLS boundaries](./docs/copilot-usage.md#account-data-boundary). After an exact scope rejection, the session's
|
|
137
|
+
| AUTH, Responses replay-scope or TLS failure | Review [request diagnostics](./docs/model-compatibility-acceptance.md#authentication-replay-and-request-diagnostics) and [usage TLS boundaries](./docs/copilot-usage.md#account-data-boundary). After an exact scope rejection, **Replay recovery** appears automatically when the session's turn ends or the session opens. Review the loss of matching old encrypted items and their summaries, then authorize **Next matching turn only** (default choice) or **Continue in this session**. Both expire within one hour of the evidence and require the same validation state. Recovery itself stays off until confirmed; use native Send/Retry separately. It never rewrites history or retries automatically, and is not a 408 fix. Never reset credentials or disable TLS as an automatic repair. |
|
|
136
138
|
| Hosted search unavailable | Check account/protocol/probe diagnostics; a legacy override stays authoritative until explicitly reset |
|
|
137
139
|
|
|
138
140
|
## Ownership and further reading
|
|
@@ -173,14 +175,14 @@ Commit attribution uses `Assisted-by` with the actual tool, never the model prov
|
|
|
173
175
|
GitHub Releases and npm distribute the same original verified tarball. Pin a version; verify Release SHA-256 or npm `dist.integrity`. Never repack an immutable release or move/reuse its tag.
|
|
174
176
|
|
|
175
177
|
```sh
|
|
176
|
-
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.
|
|
177
|
-
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.
|
|
178
|
+
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.96/dsh-github-copilot-0.4.0-alpha.96.tgz
|
|
179
|
+
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.96/SHA256SUMS
|
|
178
180
|
sha256sum --check SHA256SUMS
|
|
179
181
|
```
|
|
180
182
|
|
|
181
183
|
```powershell
|
|
182
184
|
$expected = (Get-Content .\SHA256SUMS).Split()[0]
|
|
183
|
-
$actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.
|
|
185
|
+
$actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.96.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
|
|
184
186
|
if ($actual -cne $expected) { throw 'Release checksum mismatch' }
|
|
185
187
|
```
|
|
186
188
|
|
package/README.zh.md
CHANGED
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
|
|
9
9
|
为 DSH 提供 GitHub Copilot 账号模型发现、上下文 Auto 选模和 hosted search。插件复用 DSH 公开的原生适配器与一个 Host 端 OAuth 账号,不修改 Core,也不维护第二套模型目录。
|
|
10
10
|
|
|
11
|
-
**源码候选版本:`0.4.0-alpha.
|
|
11
|
+
**源码候选版本:`0.4.0-alpha.96`(尚未发布)。支持宿主:官方 DSH / Windows Desktop `0.2.0-rc.2`。** 较早 DSH pin 仅是历史证据,不是当前安装目标。已发布、已安装到 profile、已被运行中的 Host 加载,是三个不同状态。下方带版本的命令适用于候选版本发布后,不代表对应资产已经存在。
|
|
12
12
|
|
|
13
13
|
## 你可以做什么
|
|
14
14
|
|
|
@@ -40,10 +40,10 @@ node package/scripts/check-search-composition.mjs --profile-dir /absolute/profil
|
|
|
40
40
|
**独立具名 profile**:
|
|
41
41
|
|
|
42
42
|
```sh
|
|
43
|
-
dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.
|
|
43
|
+
dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.96/dsh-github-copilot-0.4.0-alpha.96.tgz
|
|
44
44
|
```
|
|
45
45
|
|
|
46
|
-
**Desktop** 原生包管理器在发布后接受 `dsh-github-copilot@0.4.0-alpha.
|
|
46
|
+
**Desktop** 原生包管理器在发布后接受 `dsh-github-copilot@0.4.0-alpha.96`。官方 rc.2 **Desktop 随附的专属 CLI**也支持管理保留 profile;全局/普通 `dsh` shim 不等价。使用前核验实际安装入口,参见[Desktop CLI 核验](./docs/npm-distribution.md#desktop-bundled-cli-on-official-rc2)及独立的[具名 profile 离线流程](./docs/npm-distribution.md#controlled-offline-cli-maintenance-for-standalone-profiles)。两种路径都不授权绕过包源政策、修改 peer 或删除配置。
|
|
47
47
|
|
|
48
48
|
经批准 reload/restart 后:
|
|
49
49
|
|
|
@@ -94,6 +94,8 @@ Copilot 搜索要求当前账号/协议证据及能力 proof。固定/fallba
|
|
|
94
94
|
|
|
95
95
|
原生上下文占用与 Turn Usage 由 Core 所有。插件原样转发 usage,包括失败/取消时的零样本。独立上下文说明展示历史证据,不推断当前占用、不替换原生 `0%`。**Turn Usage incomplete**解释缺失样本/生命周期及已记录本地阻断,不编造零用量或部分总和。取消可以保留 usage,但不保证收到供应方最终回执。[用量边界](./docs/copilot-usage.md)。
|
|
96
96
|
|
|
97
|
+
插件恢复 timeout/replay 结构化错误前会保留原生 usage,包括非零采样。失败的零采样仍可能让原生圆环显示 `0%`,不代表请求上下文为空。重试条目的耗时表示退避等待,不是失败请求耗时;用量修复不等于解决供应方 HTTP 408,也不改变重试策略。
|
|
98
|
+
|
|
97
99
|
托管请求准入保留真实输入/输出上限和原生事务。自动压力使用发起 Agent 真正绑定的压缩服务;preset 无引擎时不能借用全局恢复。已超限的手动摘要需另行选择[手动恢复](./docs/manual-compaction-recovery.md),不能承诺预防性准入已解决。
|
|
98
100
|
|
|
99
101
|
同一轮后续步骤已有托管路由、且没有待切换模型时,已知输入压力会在 Core 开始下次模型尝试之前压缩。原生压缩成功可避免一次无 usage 样本的本地压力拒绝导致整轮 Usage 不可用。首次步骤、待切换模型、新增固定前缀膨胀与最终硬预算拒绝仍保留原有准入;不会修复历史总量或虚构缺失用量。
|
|
@@ -132,7 +134,7 @@ HTTP/SSE liveness 默认区分 5 分钟字节 idle 和有界的 10 分钟助手
|
|
|
132
134
|
| 选模未知/不可读 | 区分记录丢失与读取失败;Retry 只重读 |
|
|
133
135
|
| 缺失/取消后的 Turn Usage | 查看[用量限制](./docs/copilot-usage.md),不推断零计费 |
|
|
134
136
|
| 历史加载报 `github-copilot/auto-model-decision` | 使用[独立副本、先检查的恢复](./docs/automatic-model-routing.md#recovering-affected-histories);未经批准且未停写不得替换实际历史 |
|
|
135
|
-
| AUTH、Responses replay scope 或 TLS 错误 | 查看[请求诊断](./docs/model-compatibility-acceptance.md#authentication-replay-and-request-diagnostics)及[额度 TLS 边界](./docs/copilot-usage.md#account-data-boundary)。精确 scope
|
|
137
|
+
| AUTH、Responses replay scope 或 TLS 错误 | 查看[请求诊断](./docs/model-compatibility-acceptance.md#authentication-replay-and-request-diagnostics)及[额度 TLS 边界](./docs/copilot-usage.md#account-data-boundary)。精确 scope 拒绝后,**回放恢复**会在当前轮结束或打开会话时自动提示。查看旧加密项及项内摘要的损失后,可选择**仅下一轮使用恢复**(默认选项)或**在本会话内继续使用**;两者都要求验证状态不变,最长不超过证据产生后一小时。恢复默认关闭,确认授权也不发送消息,需另行使用原生发送或重试。不改磁盘历史,也不是 408 修复。不自动重置凭据或关闭 TLS。 |
|
|
136
138
|
| Hosted search 不可用 | 检查账号/协议/probe 诊断;旧 override 保留至显式 reset |
|
|
137
139
|
|
|
138
140
|
## 所有权与深入阅读
|
|
@@ -173,14 +175,14 @@ Agent 从 `node scripts/agent.mjs describe --json`、`doctor --json`及`plan <ta
|
|
|
173
175
|
GitHub Releases 和 npm 分发同一原始已校验 tarball。固定版本并核验 Release SHA-256 或 npm `dist.integrity`;不重打包不可变 Release、不移动/复用 tag。
|
|
174
176
|
|
|
175
177
|
```sh
|
|
176
|
-
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.
|
|
177
|
-
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.
|
|
178
|
+
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.96/dsh-github-copilot-0.4.0-alpha.96.tgz
|
|
179
|
+
curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.0-alpha.96/SHA256SUMS
|
|
178
180
|
sha256sum --check SHA256SUMS
|
|
179
181
|
```
|
|
180
182
|
|
|
181
183
|
```powershell
|
|
182
184
|
$expected = (Get-Content .\SHA256SUMS).Split()[0]
|
|
183
|
-
$actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.
|
|
185
|
+
$actual = (Get-FileHash .\dsh-github-copilot-0.4.0-alpha.96.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
|
|
184
186
|
if ($actual -cne $expected) { throw 'Release checksum mismatch' }
|
|
185
187
|
```
|
|
186
188
|
|
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.96"
|
|
12
12
|
},
|
|
13
13
|
"evidence": {
|
|
14
14
|
"kind": "source-and-synthetic-test-inventory",
|
|
@@ -330,6 +330,7 @@
|
|
|
330
330
|
{"file": "tests/fixtures/session-context-core.fixture.ts", "name": "cold-folds native model selections independently without replacing the controller projection"},
|
|
331
331
|
{"file": "tests/preview-route.spec.ts", "name": "forwards native SDK failed zero usage without changing the shared accounting stream"},
|
|
332
332
|
{"file": "tests/preview-route.spec.ts", "name": "preserves native cancellation usage on %s (%s input tokens)"},
|
|
333
|
+
{"file": "tests/preview-route.spec.ts", "name": "preserves native nonzero Anthropic usage before restoring an owned byte-idle failure"},
|
|
333
334
|
{"file": "tests/fixtures/turn-usage-core.fixture.ts", "name": "retains native whole-turn accounting for a sampled %s attempt after successful steps"}
|
|
334
335
|
]
|
|
335
336
|
},
|
|
@@ -689,13 +690,16 @@
|
|
|
689
690
|
{"file": "src/replay-recovery-host.ts", "marker": "extends TypertRemoteService"},
|
|
690
691
|
{"file": "src/replay-recovery-host.ts", "marker": "COPILOT_REPLAY_RECOVERY_TURN_ACTIVE"},
|
|
691
692
|
{"file": "src/replay-recovery-remote.ts", "marker": "githubCopilotReplayRecovery.setEnabled"},
|
|
692
|
-
{"file": "src/replay-recovery-
|
|
693
|
+
{"file": "src/replay-recovery-remote.ts", "marker": "githubCopilotReplayRecovery.authorize"},
|
|
694
|
+
{"file": "src/replay-recovery-ui.ts", "marker": "Accept loss and authorize"}
|
|
693
695
|
],
|
|
694
696
|
"tests": [
|
|
695
697
|
{"file": "tests/replay-recovery.spec.ts", "name": "keeps default replay and requires a revision-bound confirmation"},
|
|
696
698
|
{"file": "tests/replay-recovery.spec.ts", "name": "preserves source, fresh reasoning, tools, other models and other owners"},
|
|
697
699
|
{"file": "tests/replay-recovery-host.spec.ts", "name": "requires the native initiating session and signal, rejects active-turn writes and revokes late requests"},
|
|
698
|
-
{"file": "tests/replay-recovery
|
|
700
|
+
{"file": "tests/replay-recovery.spec.ts", "name": "admits only the next matching native turn, including its steps and retries"},
|
|
701
|
+
{"file": "tests/replay-recovery-ui.spec.ts", "name": "automatically shows evidence but requires explicit %s consent, without sending"},
|
|
702
|
+
{"file": "tests/replay-recovery-ui.spec.ts", "name": "is absent normally, reads on settled turns without polling and resets dismissal only for new evidence"},
|
|
699
703
|
{"file": "tests/preview-route.spec.ts", "name": "offers exact failed replay only to its initiating session and recovers after explicit confirmation"},
|
|
700
704
|
{"file": "tests/fixtures/remote-core.fixture.ts", "name": "binds explicit replay recovery through native Client and %s Host gateways"}
|
|
701
705
|
]
|
package/docs/copilot-usage.md
CHANGED
|
@@ -1,107 +1,113 @@
|
|
|
1
|
-
# Copilot account usage
|
|
2
|
-
|
|
3
|
-
The optional composer control separates three quantities:
|
|
4
|
-
|
|
5
|
-
| Quantity | Scope | Rule |
|
|
6
|
-
| --- | --- | --- |
|
|
7
|
-
| Context occupancy | Current native request/context window | Remains owned by DSH's native meter. |
|
|
8
|
-
| Account usage and remaining allocation | GitHub account billing cycle, across Copilot applications | Display only validated provider quota data; identify stale snapshots explicitly. |
|
|
9
|
-
| Session credits | Complete provider-reported usage attributable to this DSH Session | Not displayed because the supported adapter does not supply it. Do not infer it from tokens, cost estimates or account balance changes. |
|
|
10
|
-
|
|
11
|
-
## Presentation
|
|
12
|
-
|
|
13
|
-
The control is an additive `conversation.composer.dock` contribution for the current Copilot Session. It does not replace the composer, move native DOM nodes, modify global defaults, switch a model or enroll other Sessions. Native context occupancy and the new account budget are not interchangeable.
|
|
14
|
-
|
|
15
|
-
The compact control shows reported usage and remaining allocation where available. Its details explain the unit, budget, reset timestamp, freshness and unavailable data. Legacy premium requests must never be relabeled AI credits. A pooled organization account can have absolute credits used without a personal denominator; it does not imply unlimited use or expose a knowable organization balance. Percentage-only data must not create falsely precise absolute amounts.
|
|
16
|
-
|
|
17
|
-
Detailed amounts are rounded to two decimal places for display; a positive amount below 0.01 is shown as `<0.01`, not zero. GitHub billing remains authoritative. Known individual budgets at 90% used show a low-budget warning, not a spending restriction. The plan link uses the supported Desktop browser handoff with a selectable URL fallback. Details use the browser's native popover top layer when available and a fixed-position fallback otherwise; no additional ReactDOM copy or private Core DOM access is introduced.
|
|
18
|
-
|
|
19
|
-
Provider or Session changes, unmounting and missing supported runtime seams revoke the presentation's ownership. Optional capability failure must not disable sign-in, Models, search or ordinary chat. The installed/loaded Client determines the exact dock placement; the standalone design mockup is not proof of native placement.
|
|
20
|
-
|
|
21
|
-
## Historical context evidence
|
|
22
|
-
|
|
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
|
-
|
|
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
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
###
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
###
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
The
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
The
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
|
|
81
|
-
-
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
The
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
The
|
|
98
|
-
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
|
|
1
|
+
# Copilot account usage
|
|
2
|
+
|
|
3
|
+
The optional composer control separates three quantities:
|
|
4
|
+
|
|
5
|
+
| Quantity | Scope | Rule |
|
|
6
|
+
| --- | --- | --- |
|
|
7
|
+
| Context occupancy | Current native request/context window | Remains owned by DSH's native meter. |
|
|
8
|
+
| Account usage and remaining allocation | GitHub account billing cycle, across Copilot applications | Display only validated provider quota data; identify stale snapshots explicitly. |
|
|
9
|
+
| Session credits | Complete provider-reported usage attributable to this DSH Session | Not displayed because the supported adapter does not supply it. Do not infer it from tokens, cost estimates or account balance changes. |
|
|
10
|
+
|
|
11
|
+
## Presentation
|
|
12
|
+
|
|
13
|
+
The control is an additive `conversation.composer.dock` contribution for the current Copilot Session. It does not replace the composer, move native DOM nodes, modify global defaults, switch a model or enroll other Sessions. Native context occupancy and the new account budget are not interchangeable.
|
|
14
|
+
|
|
15
|
+
The compact control shows reported usage and remaining allocation where available. Its details explain the unit, budget, reset timestamp, freshness and unavailable data. Legacy premium requests must never be relabeled AI credits. A pooled organization account can have absolute credits used without a personal denominator; it does not imply unlimited use or expose a knowable organization balance. Percentage-only data must not create falsely precise absolute amounts.
|
|
16
|
+
|
|
17
|
+
Detailed amounts are rounded to two decimal places for display; a positive amount below 0.01 is shown as `<0.01`, not zero. GitHub billing remains authoritative. Known individual budgets at 90% used show a low-budget warning, not a spending restriction. The plan link uses the supported Desktop browser handoff with a selectable URL fallback. Details use the browser's native popover top layer when available and a fixed-position fallback otherwise; no additional ReactDOM copy or private Core DOM access is introduced.
|
|
18
|
+
|
|
19
|
+
Provider or Session changes, unmounting and missing supported runtime seams revoke the presentation's ownership. Optional capability failure must not disable sign-in, Models, search or ordinary chat. The installed/loaded Client determines the exact dock placement; the standalone design mockup is not proof of native placement.
|
|
20
|
+
|
|
21
|
+
## Historical context evidence
|
|
22
|
+
|
|
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
|
+
|
|
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
|
+
|
|
27
|
+
Owned byte-idle and replay errors must also wait until the native terminal chunk before restoring their structured failure. Throwing as soon as the provider observer identifies that error can discard the SDK's preceding usage chunk, including real nonzero prompt usage. Restoring the error must not drop that sample or change the native chunk order. This correction does not manufacture a receipt when the SDK reports only zero.
|
|
28
|
+
|
|
29
|
+
The official rc.2 `contextPressure` projection uses the latest usage from both successful messages and failed attempts. A failed all-zero sample can therefore replace its numerator with zero while earlier cumulative Session tokens remain large. This display projection is separate from `TokenMeter.measure()`: the public request estimator checks a usage anchor against the complete surface estimate and reprices when that anchor is too small. A zero ring does not prove either an empty request or a zero admission estimate. The supported public APIs do not let this plugin replace that native ring; repairing its uncertainty presentation belongs to a separately authorized Core task.
|
|
30
|
+
|
|
31
|
+
The time beside **Retried model request** is the recorded retry backoff, not the duration of the preceding network request. A verified `408 / user_request_timeout` describes a supplier request-body timeout, whereas semantic/byte-idle, transport, rate-limit and local admission errors are distinct. Count failed `assistant/attempt` settlements rather than counting their repeated `llm/retry` diagnoses as additional network attempts. No screenshot with collapsed details or unrelated Session receipt establishes the exact supplier or proxy root cause. Native retry policy is retained; see [request-body timeout guidance](./copilot-compaction.md).
|
|
32
|
+
|
|
33
|
+
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.
|
|
34
|
+
|
|
35
|
+
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.
|
|
36
|
+
|
|
37
|
+
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.
|
|
38
|
+
|
|
39
|
+
## Missing completed-turn Usage
|
|
40
|
+
|
|
41
|
+
### Observed plugin/Core integration gap (#259)
|
|
42
|
+
|
|
43
|
+
One observed completed turn contained 57 successful assistant messages with reported usage and one failed `assistant/attempt` without a usage sample. That attempt recorded the plugin's exact local estimated-input-budget diagnostic: 796299 estimated tokens exceeded a 781113-token input budget, before provider dispatch. Native compaction recovered and the subsequent steps completed. No conversation content, credentials or opaque replay is needed to explain this observation; the exact loaded plugin bytes were not independently attested.
|
|
44
|
+
|
|
45
|
+
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.
|
|
46
|
+
|
|
47
|
+
### Cancelled and failed terminal samples (#270)
|
|
48
|
+
|
|
49
|
+
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.
|
|
50
|
+
|
|
51
|
+
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.
|
|
52
|
+
|
|
53
|
+
### Plugin-local explanation
|
|
54
|
+
|
|
55
|
+
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.
|
|
56
|
+
|
|
57
|
+
The explanation distinguishes recorded local budget blocks, same-settlement request-body timeout diagnoses, other settlements without samples, and missing turn-start/projection evidence. A timeout is recognized only from the shared bounded plugin diagnostic marker on that settlement's unambiguous error finish, never from a neighboring message, generic `408` text or cancellation. The disclosure copies no raw failure text or payload. It retains at most eight timeout details containing only recorded step/event sequence numbers and a recovery boolean, while keeping the full saturating diagnostic count. These are original record coordinates, not invented attempt numbers or navigation links. Unknown coordinates remain unknown. Older count-only projections remain readable; projection state version 2 requests refolding without converting history.
|
|
58
|
+
|
|
59
|
+
A successful retry claim requires strictly increasing event sequences and the same turn/step through the failed `assistant/attempt`, `llm/retry`, matching `llm/retry-started` (same retry ID and ordinal), and an `assistant/message` with an unambiguous successful `stop` finish. Missing, interrupted or mismatched chains remain uncertain. A later arbitrary successful reply or another step is not recovery evidence. This intentionally conservative recognition does not claim that an unrecognized retry failed. Even a confirmed retry cannot fill the failed attempt's usage; the native whole-turn total stays unavailable and billing remains unknown.
|
|
60
|
+
|
|
61
|
+
Generic provider overflow is never labeled pre-dispatch. Invalid reported samples and missing lifecycle boundaries can also make native accounting unavailable; if no cause is established, the explanation remains unknown rather than reimplementing the native validator. Projection and selection Remote failures remain independent, with named diagnostics; Retry only rereads selection evidence, never inference or accounting.
|
|
62
|
+
|
|
63
|
+
The control is historical evidence, not current context occupancy, account credits, dispatch attestation or a supplier receipt. It adds no token sum or fabricated zero usage, changes no native projection key, reads no opaque replay, and rewrites no history. Native complete Usage suppresses the explanation. Ordinary pressure protection, compaction transactions, errors, cancellation and retry remain unchanged. Removing the plugin removes the explanation without a data migration.
|
|
64
|
+
|
|
65
|
+
Synthetic unit/UI tests and exact unchanged Core accounting/registry fixtures prove these boundaries, not live provider receipts or loaded Desktop behavior. A native representation for unbilled pre-dispatch attempts may eventually remove the gap, but would require a separately requested upstream scope; it is not a prerequisite for this plugin-local explanation. Retire the companion diagnostic when native public presentation communicates the same uncertainty and the supported-version acceptance is verified.
|
|
66
|
+
|
|
67
|
+
## Account data boundary
|
|
68
|
+
|
|
69
|
+
The Host uses the existing `llm-pi-ai/github-copilot` OAuth grant through public credential APIs. GitHub's `copilot_internal/user` endpoint uses the GitHub grant, not a second sign-in or a newly pasted token. Access-token renewal remains owned by pi-ai; quota inspection must not introduce a refresh implementation or credential persistence.
|
|
70
|
+
|
|
71
|
+
Quota requests are lazy, single-flight and bounded by timeout, response size and cache/failure policy. Account continuity is checked around asynchronous work and before releasing cached data. Authentication denial, sign-out, account invalidation or disposal must not release a previous account's snapshot. A same-account transient failure may expose a timestamped last-known snapshot, never a current balance. Responses and diagnostics exclude tokens, raw provider bodies and account identifiers. Requests do not follow redirects with the credential; custom enterprise hosts are not guessed.
|
|
72
|
+
|
|
73
|
+
The plugin's default quota fetch lazily creates one request-scoped Undici agent for `https://api.github.com/copilot_internal/user`. It unions and deduplicates `tls.getCACertificates('default')` (including any configured extra CA certificates) and `tls.getCACertificates('system')`, with `rejectUnauthorized: true`. Node 22.19.0 provides both CA APIs; Undici 6 supports that runtime floor. The agent is reused for refreshes and destroyed on controller disposal. Injected test fetchers bypass the agent. No global dispatcher, environment variable, Desktop trust preference, model/search transport or credential owner is changed.
|
|
74
|
+
|
|
75
|
+
This removes reliance on a Desktop launcher inheriting `NODE_USE_SYSTEM_CA=1` for **quota requests only**. On a machine where Watt Toolkit / Steam++ installs a trusted Windows root, quota worked under a correctly environmented launch, then failed when a recovery launcher omitted the process variable despite its persistence in HKCU; a normal manual relaunch restored quota. That is operational evidence for the launcher-inheritance explanation, not proof that this new plugin build has been installed or loaded. Other Desktop traffic, including sign-in and models, still follows its existing process-level trust configuration. If system CA retrieval or agent creation fails, the quota shows `COPILOT_USAGE_TRUST_UNAVAILABLE` without issuing a request or weakening TLS. Certificate verification failures still show `COPILOT_USAGE_TLS`; other fetch failures remain `COPILOT_USAGE_NETWORK`. No diagnostic alone proves proxy routing, authorization or a live balance. Inspect approved Host trust/proxy settings without disabling TLS validation. When unavailable, details show guidance instead of implying a budget. The popover background is opaque even if the host's menu token contains transparency.
|
|
76
|
+
|
|
77
|
+
The Client receives only the separate strict `githubCopilotUsage` namespace (`get` and `refresh`). Existing authorization and migration methods retain their schemas. Refresh does not change settings, budget, plan, model selection or billing policy. This meter is informational and does not authorize spending or implement a budget enforcement loop.
|
|
78
|
+
|
|
79
|
+
## Source contracts and limitations
|
|
80
|
+
|
|
81
|
+
GitHub's internal client endpoint is not a stable public third-party REST contract. The existing grant may not be permitted to read it, and its schema may change. Failure must remain visible rather than falling back to an administrator token, another account, a browser token or fabricated numbers.
|
|
82
|
+
|
|
83
|
+
Verified reference sources:
|
|
84
|
+
|
|
85
|
+
- [Official VS Code account snapshot types](https://github.com/microsoft/vscode/blob/44825207bf4389c3bd17c92d3ec28cf784c324cc/src/vs/base/common/defaultAccount.ts).
|
|
86
|
+
- [Official quota normalization and pooled-account semantics](https://github.com/microsoft/vscode/blob/44825207bf4389c3bd17c92d3ec28cf784c324cc/src/vs/workbench/services/chat/common/chatEntitlementService.ts).
|
|
87
|
+
- [Official quota fetch and per-turn credit accounting](https://github.com/microsoft/vscode/blob/44825207bf4389c3bd17c92d3ec28cf784c324cc/extensions/copilot/src/platform/chat/common/chatQuotaServiceImpl.ts).
|
|
88
|
+
- [GitHub's public organization/enterprise usage reporting API](https://docs.github.com/en/rest/copilot/copilot-usage-metrics) and [report fields](https://docs.github.com/en/copilot/reference/copilot-usage-metrics/copilot-usage-metrics). Daily administrator reports are not a live personal balance API.
|
|
89
|
+
- [GitHub's explanation of used credits with no individual budget](https://github.blog/changelog/2026-07-20-copilot-users-can-now-see-ai-credits-used-per-billing-cycle/).
|
|
90
|
+
|
|
91
|
+
The internal client observes per-turn `copilot_usage.total_nano_aiu`, but existence in another client's wire response is not evidence that the supported DSH/pi adapter exposes complete session accounting to plugins. On the exact alpha.2 source, [`mapUsage`](https://github.com/deepseek-ai/deepseek-harness/blob/ddefc45fbc7f8e46dd73185e68295696d1297887/packages/llm/llm-pi-ai/src/stream.ts) maps only token counts and cache counts into the public [`StreamChunk` usage contract](https://github.com/deepseek-ai/deepseek-harness/blob/ddefc45fbc7f8e46dd73185e68295696d1297887/packages/llm/llm/src/types.ts). Opaque replay state is not an accounting escape hatch. Until an unchanged public seam provides attributable, deduplicated receipts for ordinary calls, retries and background activity, per-session credit values are not displayed.
|
|
92
|
+
|
|
93
|
+
Synthetic tests cover parsing, lifecycle, failure states, strict transport and UI. They do not establish production quota permissions, billing latency, live OAuth/model transport, installed Desktop bytes or loaded plugin state. No real account calls are made merely to generate test evidence.
|
|
94
|
+
|
|
95
|
+
## Current Session and responsive presentation
|
|
96
|
+
|
|
97
|
+
The control uses public `useSession(selector)` for only the current open,
|
|
98
|
+
non-removed Session, with public `useProjection('modelSelection')`. Acceptance
|
|
99
|
+
must include positive rendering on canonical and managed routes, reactive
|
|
100
|
+
provider/Session changes and disposal. A registered or hidden signed-out entry
|
|
101
|
+
alone proves neither rendering nor live account permission.
|
|
102
|
+
|
|
103
|
+
The unavailable Session credits section is omitted rather than permanently displaying a placeholder. Reset metadata is optional and independent from validated quota amounts: missing, malformed, zero or elapsed values are ignored. Select a supplier-reported next reset later than the snapshot observation, preferring the snapshot timestamp before valid UTC account, account or limited-user dates; never invent the next billing date. Invalid optional date metadata does not discard otherwise valid account amounts. The Client also hides reset rows without a known observation time or a later reset.
|
|
104
|
+
|
|
105
|
+
The compact control uses the native secondary font-size and line-height tokens, tertiary text color and pill padding. It stays one line within its allocated width, with ellipsis and a full-label tooltip if a single reading is wider than the available space. The complete reading remains its accessible button text; exact supplied amounts and account-wide scope remain available in the independent details dialog. Loading and unavailable text use the same bounds without extra quota requests.
|
|
106
|
+
|
|
107
|
+
The host owns placement of the existing public dock entries. On a shared-row host, the usage entry follows the native statistics group and can appear immediately after Cache hit; on an older stacked host, it retains that host's placement. The plugin neither relocates native DOM nor overrides native statistics styles, and it does not require a modified Core to activate. A separately authorized Desktop Client layout task owns wrapping and actual assembled native-statistics geometry checks.
|
|
108
|
+
|
|
109
|
+
Official rc.2 retains the shared dock row in [`InputBar.module.css`](https://github.com/deepseek-ai/deepseek-harness/blob/639ed015397290b3745d163aafe02ffee4aa3f84/packages/client/ui-conversation/src/client/skeleton/InputBar.module.css) and intrinsic native statistics group in [`StatsPills.module.css`](https://github.com/deepseek-ai/deepseek-harness/blob/639ed015397290b3745d163aafe02ffee4aa3f84/packages/client/ui-chat/src/client/chat/StatsPills.module.css). Reuse that official presentation primitive rather than inventing another statistics Slot or copying its token calculations. Wide/narrow layout and popup acceptance must use actual native components alongside the released Client; standalone plugin tests or a synthetic sibling label are not proof of native Cache hit alignment.
|
|
110
|
+
|
|
111
|
+
## Official-first retirement
|
|
112
|
+
|
|
113
|
+
Retain this bounded companion feature only while native DSH lacks equivalent public account-usage presentation for the required scope. Migrate to native functionality once equivalent data semantics, account invalidation, session attribution, accessible presentation and supported-version acceptance are verified. Do not require a Core patch or add a parallel model transport to complete this integration.
|
|
@@ -91,11 +91,26 @@ IDs does not prove encrypted replay is portable.
|
|
|
91
91
|
### Explicit session replay recovery
|
|
92
92
|
|
|
93
93
|
After an exact verified managed Responses scope rejection, **Replay recovery**
|
|
94
|
-
in that session's composer
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
|
|
94
|
+
in that session's composer automatically offers the failed request's old
|
|
95
|
+
encrypted items on opening the eligible session, when its native `running`
|
|
96
|
+
snapshot settles, or when its `lastAgentError` changes while idle. These public
|
|
97
|
+
Session snapshot changes trigger read-only Host evidence reads, not model calls,
|
|
98
|
+
history reads, new durable events or polling. Normal sessions show no notice.
|
|
99
|
+
Dismissal is local to the mounted model/session and evidence revision; a new
|
|
100
|
+
failure can reappear. Read errors remain distinct from missing evidence.
|
|
101
|
+
|
|
102
|
+
Choose **Review recovery options**, then **Next matching turn only** (the
|
|
103
|
+
default choice) or **Continue in this session**, and **Accept loss and authorize**.
|
|
104
|
+
This does not send a message or retry the failed request. Use the native Send or
|
|
105
|
+
Retry control separately; the plugin adds no competing sender. Complete native
|
|
106
|
+
replay remains the default until explicit consent.
|
|
107
|
+
|
|
108
|
+
Next-turn consent is admitted on the next bound, matching-model native request
|
|
109
|
+
and covers all steps and native retries of that turn, not just one HTTP attempt.
|
|
110
|
+
It is consumed at that turn's `turn/end`, including cancelled/failed turns.
|
|
111
|
+
Other models, purposes and unbound requests cannot consume it. Session consent
|
|
112
|
+
survives turn endings but shares the same bounded evidence/proof lifetime.
|
|
113
|
+
Controls are disabled during a native turn; Host checks remain authoritative.
|
|
99
114
|
|
|
100
115
|
This is lossy recovery, not a supplier-scope repair. Only complete normalized
|
|
101
116
|
encrypted reasoning items whose entire serialized fingerprints match that
|
|
@@ -107,8 +122,12 @@ requires fresh confirmation rather than broadening enabled omission silently.
|
|
|
107
122
|
|
|
108
123
|
Evidence is bounded to 64 sessions, 512 distinct items per session, and one
|
|
109
124
|
hour in the current Host. Only hashes, a model label and confirmation metadata
|
|
110
|
-
are retained, never opaque payloads. The Client receives count/model/state
|
|
111
|
-
an opaque revision
|
|
125
|
+
are retained, never opaque payloads. The Client receives count/model/state,
|
|
126
|
+
an opaque revision, optional duration and evidence expiry only. The original
|
|
127
|
+
`get`/`setEnabled` descriptors retain their identities; `setEnabled(true)` still
|
|
128
|
+
means bounded session consent, and additive `authorize` selects a duration.
|
|
129
|
+
A one-shot expiry read updates the mounted notice, not a polling timer.
|
|
130
|
+
Token/account/metadata proof discontinuity, expiry,
|
|
112
131
|
session disposal or Host restart revokes evidence; an old error on disk cannot
|
|
113
132
|
create a candidate. Re-read status after these changes. Disabling affects
|
|
114
133
|
future requests and does not undo answers already generated.
|