dsh-github-copilot 0.4.2-alpha.4 → 0.4.2-alpha.6

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
@@ -54,6 +54,11 @@ usage, replace Core's meter, infer current occupancy/percentages or rewrite hist
54
54
  See [quota boundaries](./docs/copilot-usage.md).
55
55
  12. Default-off local account/Checking/compaction diagnostics through public storage-domain and strict additive Remotes. Keep fixed-dimension Client/Host and logical/physical populations separate, with bounded handles/rows, 14-day retention, explicit loss/uncertainty and native commit evidence. Isolate the home-wide backend by public profile context, never account/Session identity; one writer per profile is required. No content, raw errors, identities/hashes, credential/history reads, ad-hoc files, Settings logs, upload, daily task or automatic repair. Aggregate and Auto controls remain independent. Separately consented `requestDiagnosticsEnabled` collects at most 128 content-free managed-adapter physical requests for 24 hours within the shared 2 MiB cap. Random stream groups/dispatch indices are not Session/turn identity or Core retry counts. Local body-write completion does not prove supplier receipt; abort attribution needs actual signal evidence, not EOF text. Never change transport/retries/Usage to obtain diagnostics. All controls use hidden volatile CAS leaves with exact readback; clear is a separately confirmed epoch fence. Missing/corrupt storage remains unavailable, never healthy empty data. Publication does not enable collection. See [local diagnostics](./docs/plugin-diagnostics.md).
56
56
 
57
+ Auto aggregate assessment outcomes are fixed codes only; keep legacy missing reasons
58
+ unrecorded and separate from new cohorts. Count decisions by selected/no-fit counts,
59
+ not repeated candidate opportunities. Never change assessment policy, deadline or
60
+ context safety merely to populate diagnostics; retain the shared storage/row bounds.
61
+
57
62
  ## Session-policy compaction replay consent (#349, #352)
58
63
 
59
64
  `/copilot-compact visible-history` explicitly authorizes one lossy managed Responses
@@ -128,7 +133,7 @@ Alpha.25 admits native `subagent/descriptor` v3, already v3 in the retained rc.1
128
133
  - `src/serialize.ts`, `src/sse.ts`, `src/failure.ts`: protocol conversion and bounded error handling.
129
134
  - `src/response-error-body.ts`, `src/request-body-timeout.ts`, `src/request-upload-evidence.ts`: bounded clone-only HTTP error evidence and safe managed upload-timeout guidance. Request-scoped public Node diagnostic events supply numeric local body-write/header/ALPN evidence only after an exact verified `408/user_request_timeout`; absent events, multiple native requests and work limits stay explicit. Always dispose subscriptions when Fetch settles, without changing its arguments, Response/errors, dispatcher, proxy or retry owner. Local body-write completion is not upload duration, kernel ACK, supplier receipt or execution; its absence does not prove incomplete upload. Native failure classification/retry metadata stay unchanged; final JSON bytes are not tokens or a payload limit. A separate explicit opt-in compression setting is default-off and never activated by a 408; never infer overflow, auto-compact, trim history, switch models or add retries from a 408.
130
135
  - `src/responses-request-compression.ts`: asynchronous `node:zlib` gzip at `Z_BEST_SPEED` only for exact account-proven official Copilot HTTPS `/responses` JSON POSTs through the existing public Fetch seam. `github-copilot.responsesRequestCompression` defaults false; enforce the 256 KiB minimum, 32 MiB compression-work bound and both 5%/4 KiB savings thresholds. Skips retain the original request with a fixed reason, and cancellation/account/deadline fences run before dispatch. No custom Fetch, other protocol, explicit `auto`/WebSocket, DNS/proxy/dispatcher changes, context-admission or replay changes, resend after an encoding rejection, or new retry. Gzip is wire encoding, not compaction or proof of supplier receipt.
131
- - `src/request-body-evidence.ts`: verified-408-only, bounded numeric original-JSON span accounting through the existing fetch hook. Conversation/tool definitions/top-level system/residual partition total bytes; structural image and opaque replay spans are disjoint conversation subsets, never decoded contents. Unknown/limited evidence stays explicit. Fetch-to-header time excludes clone inspection and is not upload duration. With gzip, report original JSON composition and prepared HTTP-body bytes separately; neither establishes delivered bytes. No success-path analysis, retained body, automatic mitigation or supplier-limit claim.
136
+ - `src/request-body-evidence.ts`, `src/request-body-composition.ts`: bounded numeric original-JSON spans for verified 408s and separately consented request observations. Keep replay validation/recovery at 16 MiB; only diagnostic composition may use the 32 MiB cooperative scanner with 64 Ki-character yields, a two-second monotonic deadline and four scan slots. Do not build a full payload object graph or decode image/replay values. Conversation/tool definitions/top-level system/residual partition total bytes; structural image and opaque replay spans are disjoint conversation subsets. Unknown/limited/cancelled evidence stays explicit. Opted-in large scans start after Fetch invocation without delaying ordinary native delivery; retained numeric rows may update after settlement only behind consent/clear/retention/eviction fences. Retain source strings only for bounded in-flight counting, never in storage/logs. Fetch-to-header time excludes analysis and is not upload duration. With gzip, report original JSON and prepared HTTP-body bytes separately; neither establishes delivered bytes. No automatic mitigation, timeout/retry changes or supplier-limit claim.
132
137
  - `src/copilot-stream-liveness.ts`: request-local HTTP/SSE byte-idle observation, paired with the public native adapter's bounded assistant-chunk deadline. Default five-minute byte idle and ten-minute semantic silence; no fake assistant output, private watchdog access, new retry or Core patch. Consumer think time is excluded; explicit WebSocket/auto stays native-only. `chatStreamLiveness: false` restores native-only timing. `chatMaxRequestImageBytes` retains Core's 20 MiB default; smaller explicit settings authorize only native image offload, not hidden history trimming or a guessed supplier limit. Synthetic heartbeat evidence is not production heartbeat proof.
133
138
  - `tests/`: unit and integration evidence; mirror the source area being changed.
134
139
  - `deployment-baseline.json`: declared machine-readable compatibility and capability evidence inventory.
package/CHANGELOG.md CHANGED
@@ -1,5 +1,30 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.4.2-alpha.6 (prepared)
4
+
5
+ - Retain fixed assessment outcomes in existing opted-in daily Auto allocation
6
+ aggregates and their diagnostic table: timeout, disabled, unavailable, invalid
7
+ result, failed, omitted context, and known/unknown local or semantic assessment.
8
+ - Preserve legacy missing reasons as unrecorded, keep outcome cohorts separate
9
+ through strict gateways and storage reopen, and distinguish task counts from
10
+ repeated candidate opportunities. No prompts, error bodies or Session IDs added.
11
+ - Leave classification, routing, eight-second assessment budget, conservative
12
+ context handling and collection consent unchanged. Historical unknown causes
13
+ remain unproven; review new outcome data before changing policy.
14
+
15
+ ## 0.4.2-alpha.5 (prepared)
16
+
17
+ - Measure large request JSON composition up to 32 MiB with a cooperative,
18
+ bounded span scanner instead of a full payload object graph. Preserve
19
+ disjoint image/replay byte subsets, native original spans and explicit
20
+ cancellation/time/work limits; replay validation keeps its 16 MiB boundary.
21
+ - Start opted-in large-body counting after Fetch invocation without holding
22
+ up ordinary response/stream delivery. Fence late numeric updates to their
23
+ own retained row across pause/re-enable, clear, teardown and eviction.
24
+ - Reuse bounded composition work in exact verified-408 guidance. Preserve
25
+ native bytes, response/error, retries, Usage, timeout and default-off gzip;
26
+ composition evidence does not establish a proxy or supplier fault.
27
+
3
28
  ## 0.4.2-alpha.4 (prepared)
4
29
 
5
30
  - Add independently opt-in, content-free managed-adapter physical request
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, retaining a profile-wide account default with independent Session next-turn choices; it does not patch Core or maintain a second model catalog.
10
10
 
11
- **Stable release: [`0.4.1`](https://github.com/cloga/dsh-github-copilot/releases/tag/v0.4.1); prepared prerelease: `0.4.2-alpha.4`.** `0.4.2-alpha.1` was not published: its release preflight failed, and its immutable tag will not be reused. Supported host: official DSH / Windows Desktop `0.2.0-rc.2`. The stable version is also published on npm's `latest` dist-tag; prereleases remain on their channel tags. Stability-channel promotion does not expand the qualified host baseline or prove live account, model, search or Desktop health. Earlier DSH pins are historical evidence, not supported installation targets. Published, installed in a profile and loaded by a running Host are separate states.
11
+ **Stable release: [`0.4.1`](https://github.com/cloga/dsh-github-copilot/releases/tag/v0.4.1); prepared prerelease: `0.4.2-alpha.6`.** `0.4.2-alpha.1` was not published: its release preflight failed, and its immutable tag will not be reused. Supported host: official DSH / Windows Desktop `0.2.0-rc.2`. The stable version is also published on npm's `latest` dist-tag; prereleases remain on their channel tags. Stability-channel promotion does not expand the qualified host baseline or prove live account, model, search or Desktop health. Earlier DSH pins are historical evidence, not supported installation targets. Published, installed in a profile and loaded by a running Host are separate states.
12
12
 
13
13
  **Upgrade from 0.4.0:** that first stable release can interrupt concurrent managed requests with `COPILOT_PREVIEW_CREDENTIAL_CHANGED` during normal same-account native OAuth renewal. In 0.4.1, a proven plugin-owned refresh with unchanged account, endpoint and entitlements preserves already-dispatched HTTP streams; subsequent requests use freshly validated auth and metadata. Unknown/external credential notifications, revocation, cancellation and provider rejections remain explicit—not a promise of invisible recovery or automatic retry. See [the refresh boundary](./docs/copilot-accounts.md#native-oauth-refresh-and-dispatched-requests-385).
14
14
 
@@ -49,6 +49,11 @@ for 24 hours, with model, JSON/wire byte counts, timings, HTTP status and termin
49
49
  categories. No bodies, headers, credentials or Session/turn IDs are collected.
50
50
  Local body-write completion does not prove supplier receipt; these diagnostics
51
51
  do not fix timeouts or alter retry/Usage behavior.
52
+ Large JSON bodies up to 32 MiB can receive bounded, cooperative composition
53
+ counts without a full payload parse; the approximately 20.4 MiB class no longer
54
+ necessarily hits the old 16 MiB diagnostic blind spot. Time/work/cancellation
55
+ limits remain explicit, and settled rows may acquire counts on a later read.
56
+ No gzip, history trimming or extra retry is enabled. See [request observations](./docs/plugin-diagnostics.md#content-free-physical-request-observations-392).
52
57
  The package also has an explicit offline analyzer
53
58
  for a caller-selected persisted unit or reviewed aggregate view; it writes only
54
59
  to a new local report file and never scans, uploads or changes collection. Pause
@@ -58,7 +63,11 @@ Descriptive counts are not reconstructed history, failure rates or proof of an
58
63
  improvement. The diagnostics page opens on a daily Auto allocation table by UTC
59
64
  date, policy, model and cohort, with opportunities, expected selections, selected
60
65
  counts and no-fit decisions. Compare expected and selected counts only within
61
- matching cohorts. Account/Checking and compaction reports, collection controls,
66
+ matching cohorts. New cohorts distinguish assessment timeouts, unavailable/invalid
67
+ results, omitted context, disabled assessment and genuinely unknown local/semantic
68
+ results; legacy reasons remain **not recorded**. Count tasks with Selected plus
69
+ No-fit, not candidate opportunities. This is diagnostic coverage, not a routing
70
+ change or proof of the supplier root cause. Account/Checking and compaction reports, collection controls,
62
71
  and detailed scope, limits and JSON are in collapsed disclosures; clearing still
63
72
  requires separate confirmation.
64
73
 
@@ -111,10 +120,10 @@ Supply any launcher patches with repeated `--patch /absolute/file`. Require `sup
111
120
  For a **standalone named profile**:
112
121
 
113
122
  ```sh
114
- dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.2-alpha.4/dsh-github-copilot-0.4.2-alpha.4.tgz
123
+ dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.2-alpha.6/dsh-github-copilot-0.4.2-alpha.6.tgz
115
124
  ```
116
125
 
117
- For **Desktop**, its native package manager accepts an exact npm spec, for example `dsh-github-copilot@0.4.2-alpha.4`; stable versions publish on npm's `latest` dist-tag and prereleases on their channel tags. The official rc.2 **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.
126
+ For **Desktop**, its native package manager accepts an exact npm spec, for example `dsh-github-copilot@0.4.2-alpha.6`; stable versions publish on npm's `latest` dist-tag and prereleases on their channel tags. The official rc.2 **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.
118
127
 
119
128
  After an approved reload/restart:
120
129
 
@@ -290,14 +299,14 @@ Commit attribution uses `Assisted-by` with the actual tool, never the model prov
290
299
  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.
291
300
 
292
301
  ```sh
293
- curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.2-alpha.4/dsh-github-copilot-0.4.2-alpha.4.tgz
294
- curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.2-alpha.4/SHA256SUMS
302
+ curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.2-alpha.6/dsh-github-copilot-0.4.2-alpha.6.tgz
303
+ curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.2-alpha.6/SHA256SUMS
295
304
  sha256sum --check SHA256SUMS
296
305
  ```
297
306
 
298
307
  ```powershell
299
308
  $expected = (Get-Content .\SHA256SUMS).Split()[0]
300
- $actual = (Get-FileHash .\dsh-github-copilot-0.4.2-alpha.4.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
309
+ $actual = (Get-FileHash .\dsh-github-copilot-0.4.2-alpha.6.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
301
310
  if ($actual -cne $expected) { throw 'Release checksum mismatch' }
302
311
  ```
303
312
 
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,保留 profile 全局默认账号,并支持 Session 后续 turn 指定独立账号;不修改 Core,也不维护第二套模型目录。
10
10
 
11
- **稳定版:[`0.4.1`](https://github.com/cloga/dsh-github-copilot/releases/tag/v0.4.1);待发布预览版:`0.4.2-alpha.4`。** `0.4.2-alpha.1` 的发布预检失败,因此未发布;其不可变 tag 不会复用。支持宿主:官方 DSH / Windows Desktop `0.2.0-rc.2`。稳定版也发布到 npm 的 `latest` dist-tag;预发布版本仍使用各自渠道 tag。稳定渠道不扩大已验证的宿主基线,也不证明实时账号、模型、搜索或 Desktop 健康状态。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。
11
+ **稳定版:[`0.4.1`](https://github.com/cloga/dsh-github-copilot/releases/tag/v0.4.1);待发布预览版:`0.4.2-alpha.6`。** `0.4.2-alpha.1` 的发布预检失败,因此未发布;其不可变 tag 不会复用。支持宿主:官方 DSH / Windows Desktop `0.2.0-rc.2`。稳定版也发布到 npm 的 `latest` dist-tag;预发布版本仍使用各自渠道 tag。稳定渠道不扩大已验证的宿主基线,也不证明实时账号、模型、搜索或 Desktop 健康状态。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。
12
12
 
13
13
  **从 0.4.0 升级:**首个正式版在同账号正常原生 OAuth 刷新时,可能以 `COPILOT_PREVIEW_CREDENTIAL_CHANGED` 中止并行托管请求。0.4.1 仅在插件拥有的原生刷新被精确验证,且账号、端点与权限连续时,保留已发出的 HTTP 流;后续请求重新验证认证与模型元数据。未知/外部凭据通知、撤销、取消与供应商拒绝仍明确报错,不承诺所有刷新无感,也不自动重试。参见[刷新边界](./docs/copilot-accounts.md#native-oauth-refresh-and-dispatched-requests-385)。
14
14
 
@@ -38,12 +38,19 @@ Session/turn ID、对话内容,也不推断执行/结果,不自动调参
38
38
  **Enable request observations** 开关保留最多 128 条托管适配器的物理请求观测,保留 24 小时:
39
39
  仅包含模型、JSON/传输字节数、耗时、HTTP 状态和终止分类,不记录正文、headers、
40
40
  凭据或 Session/turn ID。本地写出完成不证明供应方收到了请求;诊断不会修复超时,
41
- 也不改变重试或 Usage。包内另提供显式离线分析器,
41
+ 也不改变重试或 Usage。最高 32 MiB 的大 JSON 请求可通过有界、协作式扫描获得组成计数,
42
+ 不完整解析 payload 对象图;约 20.4 MiB 的请求不再必然落入旧 16 MiB 诊断盲区。
43
+ 耗时/工作量/取消限制仍明确可见,已结束的记录可能在之后读取时才补齐计数。
44
+ 不自动启用 gzip、截断历史或增加重试,参见[请求观测](./docs/plugin-diagnostics.md#content-free-physical-request-observations-392)。
45
+ 包内另提供显式离线分析器,
42
46
  只处理调用者指定的持久化单元或经审阅的聚合视图,并且只新建本地报告文件;不会扫描、
43
47
  上传或更改采集设置。暂停保留证据,清除需单独确认。Client/Host 分开统计,未覆盖路径、
44
48
  报告丢失与存储故障明确显示。描述性计数不是历史重建、错误率,也不表示优化效果已被验证。诊断页默认显示按 UTC 日期、
45
49
  策略、模型和 cohort 划分的 Auto 分配每日汇总表,包含候选机会、预期选择、实际选择及
46
- no-fit 决策;只能在匹配 cohort 内比较预期与实际选择。账号/Checking 和压缩报告、采集控制、
50
+ no-fit 决策;只能在匹配 cohort 内比较预期与实际选择。新 cohort 区分评估超时、不可用/无效
51
+ 结果、上下文缺失、评估关闭及本地/语义判断确实未知;旧数据原因保持 **not recorded**,
52
+ 不倒推。按 Selected 加 No-fit 计任务数,不按候选机会计数。这是诊断覆盖,不改变选模策略,
53
+ 也不证明供应商根因。账号/Checking 和压缩报告、采集控制、
47
54
  详细范围/限制/JSON 位于折叠区;清除仍需单独确认。
48
55
 
49
56
  在已构建的包或源码 checkout 内,显式分析已核验的文件:
@@ -95,10 +102,10 @@ node package/scripts/check-search-composition.mjs --profile-dir /absolute/profil
95
102
  **独立具名 profile**:
96
103
 
97
104
  ```sh
98
- dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.2-alpha.4/dsh-github-copilot-0.4.2-alpha.4.tgz
105
+ dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.2-alpha.6/dsh-github-copilot-0.4.2-alpha.6.tgz
99
106
  ```
100
107
 
101
- **Desktop** 原生包管理器接受精确 npm spec,例如 `dsh-github-copilot@0.4.2-alpha.4`;稳定版发布到 npm `latest` dist-tag,预发布版使用对应渠道 tag。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。
108
+ **Desktop** 原生包管理器接受精确 npm spec,例如 `dsh-github-copilot@0.4.2-alpha.6`;稳定版发布到 npm `latest` dist-tag,预发布版使用对应渠道 tag。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。
102
109
 
103
110
  经批准 reload/restart 后:
104
111
 
@@ -274,14 +281,14 @@ Agent 从 `node scripts/agent.mjs describe --json`、`doctor --json`及`plan <ta
274
281
  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。
275
282
 
276
283
  ```sh
277
- curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.2-alpha.4/dsh-github-copilot-0.4.2-alpha.4.tgz
278
- curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.2-alpha.4/SHA256SUMS
284
+ curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.2-alpha.6/dsh-github-copilot-0.4.2-alpha.6.tgz
285
+ curl -LO https://github.com/cloga/dsh-github-copilot/releases/download/v0.4.2-alpha.6/SHA256SUMS
279
286
  sha256sum --check SHA256SUMS
280
287
  ```
281
288
 
282
289
  ```powershell
283
290
  $expected = (Get-Content .\SHA256SUMS).Split()[0]
284
- $actual = (Get-FileHash .\dsh-github-copilot-0.4.2-alpha.4.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
291
+ $actual = (Get-FileHash .\dsh-github-copilot-0.4.2-alpha.6.tgz -Algorithm SHA256).Hash.ToLowerInvariant()
285
292
  if ($actual -cne $expected) { throw 'Release checksum mismatch' }
286
293
  ```
287
294
 
@@ -8,7 +8,7 @@
8
8
  },
9
9
  "package": {
10
10
  "name": "dsh-github-copilot",
11
- "version": "0.4.2-alpha.4"
11
+ "version": "0.4.2-alpha.6"
12
12
  },
13
13
  "evidence": {
14
14
  "kind": "source-and-synthetic-test-inventory",
@@ -296,7 +296,10 @@
296
296
  "sourceMarkers": [
297
297
  {"file": "src/diagnostics-types.ts", "marker": "DIAGNOSTICS_MAX_BYTES = 2 * 1024 * 1024"},
298
298
  {"file": "src/diagnostics-collector.ts", "marker": "noteClientGaps"},
299
+ {"file": "src/auto-allocation-diagnostics.ts", "marker": "assessmentOutcome: assessmentOutcome.optional()"},
299
300
  {"file": "src/request-diagnostics.ts", "marker": "REQUEST_DIAGNOSTICS_MAX_ROWS = 128"},
301
+ {"file": "src/request-body-composition.ts", "marker": "bytes: 32 * 1024 * 1024"},
302
+ {"file": "src/request-body-composition.ts", "marker": "concurrent: 4"},
300
303
  {"file": "src/request-diagnostics.ts", "marker": "REQUEST_DIAGNOSTICS_RETENTION_MS = 24 * 60 * 60 * 1000"},
301
304
  {"file": "src/config.ts", "marker": "requestDiagnosticsEnabled: z.boolean().default(false).hidden().volatile()"},
302
305
  {"file": "src/diagnostics-host.ts", "marker": "diagnosticsDomainForProfile"},
@@ -307,7 +310,12 @@
307
310
  ],
308
311
  "tests": [
309
312
  {"file": "tests/diagnostics-collector.spec.ts", "name": "is disabled until enabled, records success denominators and settles once"},
313
+ {"file": "tests/auto-allocation-diagnostics.spec.ts", "name": "separates assessment outcomes without changing model opportunities or exposing errors"},
314
+ {"file": "tests/auto-allocation-diagnostics.spec.ts", "name": "keeps legacy reasons unrecorded and captures no-fit and successful assessment outcomes"},
310
315
  {"file": "tests/request-diagnostics.spec.ts", "name": "requires independent consent, captures status/timing and never infers upload or retry count"},
316
+ {"file": "tests/request-body-composition.spec.ts", "name": "partitions a 20.4 MiB request without parsing its payload object graph"},
317
+ {"file": "tests/preview-transport-failures.spec.ts", "name": "does not wait for large-request composition before native success and updates the exact settled row"},
318
+ {"file": "tests/request-diagnostics.spec.ts", "name": "updates only its own retained record after native settlement, never across clear/pause/eviction"},
311
319
  {"file": "tests/preview-transport-failures.spec.ts", "name": "records verified 408 once without changing the native error, serialized input or dispatch count"},
312
320
  {"file": "tests/diagnostics-client.spec.ts", "name": "rejects stale status responses and settles an unmounted Checking operation once"},
313
321
  {"file": "tests/diagnostics-card.spec.ts", "name": "requires a confirmed durable enable and a separate destructive clear confirmation"},
@@ -1,22 +1,22 @@
1
1
  {
2
2
  "schemaVersion": 1,
3
3
  "feature": "autorouting",
4
- "status": "not-collected",
4
+ "status": "insufficient-sample",
5
5
  "policyVersion": "high-cost-v1",
6
6
  "observation": {
7
- "start": null,
8
- "end": null,
9
- "sampleCount": 0,
10
- "limitations": "No live weighted-allocation dataset collected. Initial synthetic tests do not establish real workload quality, billing, cost savings or live Desktop activation."
7
+ "start": "2026-10-08T00:00:00Z",
8
+ "end": "2026-10-09T23:59:59Z",
9
+ "sampleCount": 63,
10
+ "limitations": "Read-only strict profile-local aggregate review, daily UTC buckets rather than exact event times. Producer 0.4.2-alpha.2; not current loaded-version proof. No Session/turn IDs, sequence, lower-category pool fit or classifier diagnostic retained. completeHistory=false, restarts=1, dropped/expired/saturated=0 in this snapshot. Cannot recover failure causes, transition matrix, execution, quality, billing or savings; no raw export uploaded."
11
11
  },
12
- "previousReview": "Issue #332 workflow pilot and #333 high-cost requirements; prior category policy used unconditional continuity.",
13
- "findings": "Unconditional continuity prevents allocation opportunities. Hard-prioritizing unmarked peers nearly excludes high-cost candidates; extreme-only gating wrongly couples cost to difficulty.",
14
- "decision": "Implement positive main-turn weights ordinary=1, marked=0.2 and finite previous-model multiplier=1.5 within the fitting supplier category. Capture local bounded opportunities and expected shares. Defer advisor calls until public evidence/authorization/account seams pass their own acceptance.",
15
- "validation": "Focused tests and 19 focused tooling tests passed with a supplemental unchanged pinned resolver; exact commands/counts are in the implementation PR. Native Client/Host gateways and SettingsForms fiber/restart persistence included. Synthetic source-component browser checks passed at widths 1280/390/195 in both themes. Normal pnpm verify blocked by configured mirror HTTP 404 for exact rc.2 dependency. Required full CI/build/tarball/publication results are recorded separately in the implementation PR and Release. This is not live Desktop/model/billing evidence.",
12
+ "previousReview": "Issues #332/#333 prior allocation review and post-delivery review #334; diagnostic-only follow-up #398.",
13
+ "findings": "63 decisions: 44 local/unknown, 4 semantic/unknown and 15 semantic/complex, all powerful target/selection. Sol selected 57 and Astra 6; 47 marked previous-model retention, not a transition matrix. Local/unknown may include disabled/unavailable/timeout/failed/invalid-result fallbacks. Semantic/unknown may include omitted-context conservatism. Persisted aggregates discarded those diagnostics, so historical causes cannot be established.",
14
+ "decision": "Retain classification, category routing, positive weights, continuity, eight-second deadline, context safety and existing consent. Add only fixed content-free assessment outcomes to daily candidate/no-fit strata and their existing table. Keep legacy absent reasons explicitly unrecorded. Do not force downgrades, increase the timeout or infer classifier/network failure from unknown demand.",
15
+ "validation": "Regression-first collector tests reproduced diagnostic cohort collapse and merging fresh rows with legacy unrecorded rows. 70 focused assessment/classifier/routing/collector/UI tests, source/test types and four public gateway/storage fixture tests including reopen passed. The complete 130-file low-concurrency suite passed 2724 tests with two expected skips; the default-concurrency full gate hit an existing 5000ms allocation stress-test timeout. No timeout or assertion weakened. Tooling/package and required Windows/Linux delivery gates are recorded separately in the implementation PR; this document does not claim live activation.",
16
16
  "followUp": {
17
17
  "owner": "Maintainer or Agent assigned to post-delivery review issue #334",
18
- "trigger": "Before the next policy change, or after at least 200 eligible opportunities per compared model across at least 20 Sessions, keeping policy/candidate-set windows separate",
19
- "metric": "Opportunity-adjusted actual versus expected selections, marked replacement/retention, within-pool switching, assessment latency/failures; outcomes and costs only when independently attributable",
20
- "action": "Review local sanitized aggregates, check missing/evicted coverage, and retain/change/defer with reasons. This threshold is not statistical significance. No automatic upload, quality inference from completion, or credit inference from balance deltas."
18
+ "trigger": "Review assessment outcomes after 200 new decisions with recorded reasons, or before the next assessment policy change. Retain the prior allocation trigger of 200 opportunities per model across 20 Sessions only if independently evidenced; aggregates cannot count Sessions.",
19
+ "metric": "Selected plus no-fit counts by fixed assessment outcome, producer version, source and demand; explicit unrecorded/truncated/dropped/expired/saturated/restart coverage. Keep candidate opportunities and actual versus expected selections separate from task counts.",
20
+ "action": "Use local sanitized aggregates to fix an evidenced dominant assessment failure or retain the conservative fallback; unknown or insufficient evidence defers tuning. No automatic upload, transition reconstruction, quality inference or credit inference. Track implementation in #398 and the open post-delivery review in #334."
21
21
  }
22
22
  }
@@ -106,7 +106,7 @@ Original serialized value spans partition total bytes into `input`/`messages`, t
106
106
 
107
107
  Responses tool pictures are also image blocks: the native SDK serializes them under `function_call_output.output[]`, separately from ordinary message `content[]`. Older plugin diagnostics incorrectly classified those spans as remaining history, so an old report of zero image bytes does not establish an image-free request. The corrected diagnostic applies only to newly observed failures; stored failures and history are not rewritten. Unknown output arrays remain residual, and the fix changes neither total bytes nor native image admission, offload budgets, replay or transport.
108
108
 
109
- Analysis accepts at most 16 MiB of UTF-8 JSON, with a pre-parse depth/token bound (64 levels / 131072 tokens), followed by at most 65536 values and 128 serialized key characters. Missing, malformed, unsupported, size-limited and work-limited evidence has a named unavailable state with no partial success-shaped totals. Limits bound diagnostic cost and are **not supplier request limits or admission controls**. A reported 9 MiB body may be analyzed, but its size does not establish why a timeout occurred. If image blocks dominate, an explicitly selected smaller `chatMaxRequestImageBytes` can authorize native image offload; if compressible history dominates, explicit native compaction can help. Tool definitions and opaque replay may remain; small failing requests still warrant network/service investigation. Neither choice is performed automatically or guaranteed to reduce 408 frequency.
109
+ Analysis up to 16 MiB retains the existing span validator. Larger verified-408 JSON bodies use a cooperative span scanner up to 32 MiB without allocating a full payload object graph or decoding image/replay content. Its 65,536-character yields, two-second monotonic deadline and four concurrent scan slots bound additional work; both paths retain 64-level depth, 131072-token, 65536-value and 128-serialized-key-character limits. Separately opted-in physical request observations may already have started that same work after Fetch invocation, without holding up ordinary native response delivery. Verified-408 guidance may await it and preserves Fetch-to-header timing measured before analysis. Missing, malformed, unsupported, size/work/time-limited or cancelled evidence remains explicitly unavailable, never partial success-shaped totals. Replay validation and recovery keep the original 16 MiB limits. These limits are **not supplier request limits or admission controls**. A measured approximately 20.4 MiB body does not establish why a timeout occurred. If image blocks dominate, an explicitly selected smaller `chatMaxRequestImageBytes` can authorize native image offload; if compressible history dominates, explicit native compaction can help. Tool definitions and opaque replay may remain; small failing requests still warrant network/service investigation. Neither choice is performed automatically or guaranteed to reduce 408 frequency.
110
110
 
111
111
  This implementation is preventive, not a general rescue summarizer. A manual summary whose full input already exceeds the hard budget fails before model transport. It does not silently trim, fabricate a partial checkpoint, or claim that refusing the request recovered the history. Giant fixed prefixes or an indivisible latest unit can also prevent useful reduction.
112
112
 
@@ -46,6 +46,16 @@ attribution. Aggregate rows are capped at 1,024, retained for 14 days and
46
46
  included in the existing 2 MiB snapshot limit; expired, dropped, truncated,
47
47
  saturated and restart evidence remains explicit. There is no per-turn export,
48
48
  automatic tuning or upload. The aggregate controls can be paused independently.
49
+ New rows also distinguish fixed assessment outcomes: local-known/local-unknown,
50
+ semantic-known/semantic-unknown, disabled, unavailable, timeout, failed,
51
+ invalid-result and context-omitted. Missing legacy outcomes remain **not recorded**,
52
+ never reconstructed from demand/source. Count decisions using Selected plus
53
+ No-fit, not candidate opportunities (one decision may have many candidates).
54
+ These outcomes explain classifier settlement, not network root cause or model
55
+ execution; no error bodies, signals, prompts or Session/turn IDs are added.
56
+ Classification, its eight-second budget and conservative omitted-context guard
57
+ are unchanged. Older strict plugin versions may reject new snapshot fields on
58
+ rollback; do not delete or silently rewrite retained evidence to make them parse.
49
59
  The separate **Enable request observations** control uses the hidden volatile
50
60
  `github-copilot.requestDiagnosticsEnabled` leaf with path-level CAS and exact
51
61
  readback. Existing aggregate consent never enables request observations.
@@ -166,10 +176,26 @@ original JSON and dispatched wire byte counts, encoding, bounded composition
166
176
  partitions, local header/elapsed timing, HTTP status and fixed terminal/reason
167
177
  categories. Existing public native upload observations add ALPN, local body-write
168
178
  timing and writable-buffer bytes only when available. Unsupported/ambiguous
169
- transport evidence stays explicitly unavailable. Composition is bounded to
170
- 16 MiB and fixed parser work limits; larger bodies retain byte counts with
171
- `size-limit`, never an invented composition or unlimited body parse. These are
172
- diagnostic work limits, not provider request limits.
179
+ transport evidence stays explicitly unavailable. Bodies up to 16 MiB retain the
180
+ existing synchronous span validator. Larger JSON bodies, including the reported
181
+ approximately 20.4 MiB class, use a cooperative span scanner up to 32 MiB without
182
+ building a payload object graph or decoding image/replay values. It yields every
183
+ 65,536 scanned characters, checks a two-second monotonic work deadline and caps
184
+ concurrent scans at four. Both paths retain 64-level depth, 65,536-value,
185
+ 131,072-token and 128-serialized-key-character limits. Size, work, time and
186
+ cancellation limits remain named unavailable states without partial totals.
187
+ These are diagnostic work limits, not provider request limits.
188
+
189
+ For opted-in observations, large-body counting starts after Fetch invocation
190
+ and does not delay ordinary native response/stream delivery. A retained row can
191
+ receive its numeric composition after terminal settlement; until then its
192
+ initial `size-limit` remains explicit. Refresh/read/export obtains the currently
193
+ available evidence, not a promise of completion. Pause/re-enable, clear,
194
+ teardown, retention and eviction fence late updates, and the counting work
195
+ retains its source string only for that bounded scan. Actual caller cancellation
196
+ can stop it. Verified-408 guidance may await that same bounded work; without
197
+ request consent only an exact verified failure starts the larger scan.
198
+ Replay validation/recovery keeps its original 16 MiB boundary unchanged.
173
199
 
174
200
  Random stream UUIDs group only dispatches within one native SDK stream.
175
201
  `dispatchIndex` is physical Fetch order, **not** Core's retry number or an
@@ -177,6 +203,10 @@ end-to-end Session/turn correlation. No account/Session/turn IDs or hashes,
177
203
  URLs, headers, raw errors, prompts, tool parameters/results, attachment or replay
178
204
  content, credentials or token accounting are retained. Review timestamps/model
179
205
  metadata before explicit sharing; nothing is uploaded automatically.
206
+ Comparing JSON/wire sizes and partitions within a stream can reveal repeated
207
+ large payload sizes or growth, not duplicate contents, a Core retry count,
208
+ delivery to a proxy/supplier or the reason for a rejection. No request hashes
209
+ are collected and no automatic size-based mitigation is introduced.
180
210
 
181
211
  An exact verified HTTP408 `user_request_timeout` is classified as
182
212
  `request-body-timeout`; other provider/transport errors remain fixed unknown
package/lib/client.js CHANGED
@@ -6526,6 +6526,18 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
6526
6526
  const dayMs = 864e5;
6527
6527
  const integer$2 = number().int().min(0).max(Number.MAX_SAFE_INTEGER);
6528
6528
  const version$2 = string().max(64).regex(/^\d+\.\d+\.\d+(?:-[a-zA-Z0-9.-]+)?$/);
6529
+ const assessmentOutcome = _enum([
6530
+ "local-known",
6531
+ "local-unknown",
6532
+ "semantic-known",
6533
+ "semantic-unknown",
6534
+ "disabled",
6535
+ "unavailable",
6536
+ "invalid-result",
6537
+ "timeout",
6538
+ "failed",
6539
+ "context-omitted"
6540
+ ]);
6529
6541
  const allocationRow = object({
6530
6542
  day: integer$2.multipleOf(dayMs),
6531
6543
  version: version$2,
@@ -6549,6 +6561,7 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
6549
6561
  "unknown"
6550
6562
  ]),
6551
6563
  assessmentSource: _enum(["local", "semantic"]),
6564
+ assessmentOutcome: assessmentOutcome.optional(),
6552
6565
  method: _enum(["weighted-distribution", "only-candidate"]),
6553
6566
  fallback: boolean(),
6554
6567
  highCost: boolean(),
@@ -6580,6 +6593,7 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
6580
6593
  "unknown"
6581
6594
  ]),
6582
6595
  assessmentSource: _enum(["local", "semantic"]),
6596
+ assessmentOutcome: assessmentOutcome.optional(),
6583
6597
  decisions: integer$2.min(1)
6584
6598
  }).strict();
6585
6599
  const AutoAllocationDiagnosticsSchema = object({
@@ -6614,7 +6628,9 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
6614
6628
  "size-limit",
6615
6629
  "work-limit",
6616
6630
  "invalid-json",
6617
- "unsupported-shape"
6631
+ "unsupported-shape",
6632
+ "cancelled",
6633
+ "time-limit"
6618
6634
  ]),
6619
6635
  totalBytes: integer$1.optional()
6620
6636
  }).strict()]);
@@ -7174,7 +7190,7 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
7174
7190
  };
7175
7191
  //#endregion
7176
7192
  //#region package.json
7177
- var version = "0.4.2-alpha.4";
7193
+ var version = "0.4.2-alpha.6";
7178
7194
  //#endregion
7179
7195
  //#region lib/types/diagnostics-client.js
7180
7196
  let owner;
@@ -7420,6 +7436,7 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
7420
7436
  row.category,
7421
7437
  row.demand,
7422
7438
  row.assessmentSource,
7439
+ row.assessmentOutcome,
7423
7440
  row.method,
7424
7441
  row.fallback,
7425
7442
  row.highCost,
@@ -7428,7 +7445,7 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
7428
7445
  day: row.day,
7429
7446
  policy: row.policyVersion,
7430
7447
  model: row.modelId,
7431
- cohort: `${row.targetCategory} → ${row.category} · ${row.demand} · ${row.assessmentSource} · ${row.method}` + (row.fallback ? " · fallback" : "") + (row.highCost ? " · high-cost" : "") + (row.previous ? " · continuity" : ""),
7448
+ cohort: `${row.targetCategory} → ${row.category} · ${row.demand} · ${row.assessmentSource} · assessment: ${row.assessmentOutcome ?? "not recorded"} · ${row.method}` + (row.fallback ? " · fallback" : "") + (row.highCost ? " · high-cost" : "") + (row.previous ? " · continuity" : ""),
7432
7449
  opportunities: row.opportunities,
7433
7450
  expected: row.expectedSelections,
7434
7451
  selected: row.selections,
@@ -7441,12 +7458,13 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
7441
7458
  row.targetCategory,
7442
7459
  row.category,
7443
7460
  row.demand,
7444
- row.assessmentSource
7461
+ row.assessmentSource,
7462
+ row.assessmentOutcome
7445
7463
  ]),
7446
7464
  day: row.day,
7447
7465
  policy: row.policyVersion,
7448
7466
  model: "—",
7449
- cohort: `${row.targetCategory} → ${row.category} · ${row.demand} · ${row.assessmentSource} · no fit`,
7467
+ cohort: `${row.targetCategory} → ${row.category} · ${row.demand} · ${row.assessmentSource} · assessment: ${row.assessmentOutcome ?? "not recorded"} · no fit`,
7450
7468
  opportunities: null,
7451
7469
  expected: null,
7452
7470
  selected: null,
@@ -7528,7 +7546,7 @@ Set the \`cycles\` parameter to \`"ref"\` to resolve cyclical schemas with defs.
7528
7546
  } }, row.noFit ?? "—")))))) : null, auto?.status === "observed" && autoRows.length === 0 ? (0, react.createElement)("p", { style: { margin: 0 } }, "No retained strata in this snapshot; this does not mean there were no decisions.") : !auto ? (0, react.createElement)("p", { style: { margin: 0 } }, "Auto allocation aggregates are unavailable in this snapshot.") : view && auto.status !== "observed" && view.state !== "ready" ? (0, react.createElement)("p", { style: { margin: 0 } }, "Storage is not ready; retained Auto observation status is unknown.") : view && auto.status !== "observed" ? (0, react.createElement)("p", { style: { margin: 0 } }, "No retained observations yet.") : null, autoRows.length ? (0, react.createElement)("p", { style: {
7529
7547
  ...nativeCaptionStyle,
7530
7548
  margin: 0
7531
- } }, `${autoOpportunities} candidate opportunities · ${autoExpected.toFixed(3)} expected selections · ${autoSelections} actual selections · ${autoNoFit} no-fit decisions. Compare expected and selected counts only within matching cohorts; these are not execution, quality or billing evidence.`) : null), view ? (0, react.createElement)("details", null, (0, react.createElement)("summary", null, "Physical request observations"), (0, react.createElement)("p", { style: { margin: 0 } }, requests ? `${requests.rows.length} retained requests · ${requests.pending ?? 0} sampled pending · ${requests.dropped} dropped · ${requests.evicted} expired/evicted · ${requests.interruptedOnReopen ?? 0} interrupted on reopen` : "No retained request observations. This does not establish zero failures or enabled collection."), (0, react.createElement)("p", { style: {
7549
+ } }, `${autoOpportunities} candidate opportunities · ${autoExpected.toFixed(3)} expected selections · ${autoSelections} actual selections · ${autoNoFit} no-fit decisions. Compare expected and selected counts only within matching cohorts; these are not execution, quality or billing evidence. Assessment outcomes explain classification only, not the supplier root cause. Legacy reasons are not recorded; sum Selected or No-fit, not candidate opportunities, when counting decisions by outcome.`) : null), view ? (0, react.createElement)("details", null, (0, react.createElement)("summary", null, "Physical request observations"), (0, react.createElement)("p", { style: { margin: 0 } }, requests ? `${requests.rows.length} retained requests · ${requests.pending ?? 0} sampled pending · ${requests.dropped} dropped · ${requests.evicted} expired/evicted · ${requests.interruptedOnReopen ?? 0} interrupted on reopen` : "No retained request observations. This does not establish zero failures or enabled collection."), (0, react.createElement)("p", { style: {
7532
7550
  ...nativeCaptionStyle,
7533
7551
  margin: 0
7534
7552
  } }, "Managed native adapter dispatches only. Local body-write completion is not supplier receipt. Stream-done is a native terminal observation, not tool execution or billing success. No Core retry count or Session/turn attribution is inferred."), requests?.rows.length ? (0, react.createElement)("div", { style: {