dsh-github-copilot 0.1.0-alpha.14.dsh.0.2.2.rc.3 → 0.1.0-alpha.16.dsh.0.2.2.rc.3
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 +159 -29
- package/CHANGELOG.md +20 -3
- package/CONTRIBUTING.md +5 -5
- package/README.md +44 -7
- package/README.zh.md +37 -5
- package/deployment-baseline.json +7 -3
- package/docs/account-management-experience.md +2 -2
- package/docs/agent-autonomy-evaluation.md +78 -0
- package/docs/agent-readiness.md +19 -3
- package/docs/auto-high-cost.md +2 -2
- package/docs/auto-review-sampling.md +10 -0
- package/docs/auto-task-routing.md +3 -3
- package/docs/automatic-model-routing.md +3 -3
- package/docs/copilot-accounts.md +31 -24
- package/docs/copilot-compaction.md +1 -1
- package/docs/image-input-compatibility.md +21 -20
- package/docs/manual-compaction-recovery.md +3 -3
- package/docs/model-compatibility-acceptance.md +12 -5
- package/docs/npm-distribution.md +11 -2
- package/docs/official-first-016-alpha2.md +3 -2
- package/docs/official-first-020-rc1.md +3 -2
- package/docs/official-first-020-rc2.md +4 -0
- package/docs/official-first-021-alpha4.md +3 -0
- package/docs/official-first-021-alpha5.md +3 -0
- package/docs/official-first-021-rc3.md +3 -0
- package/docs/plugin-diagnostics.md +2 -1
- package/docs/session-search-routing.md +9 -6
- package/docs/single-route-migration.md +16 -1
- package/lib/client.js +1 -1
- package/lib/index.js +364 -206
- package/lib/manual-compaction-recovery.js +1 -1
- package/lib/routed-web.js +1 -1
- package/lib/types/session-accounts-host.d.ts +11 -0
- package/lib/types/session-accounts.d.ts +2 -1
- package/package.json +4 -1
- package/scripts/autonomy-evaluation.mjs +313 -0
- package/scripts/release-policy.mjs +2 -1
- package/tests/fixtures/autonomy-evaluation.json +71 -0
- package/lib/{traditional-search-DP4tbmsO.js → traditional-search-6Gf2GmQW.js} +1 -1
package/AGENTS.md
CHANGED
|
@@ -36,10 +36,61 @@ Use native DSH tools for goals, background jobs and scoped subagents. Use local
|
|
|
36
36
|
|
|
37
37
|
These are agent instructions and contract-drift checks, not a filesystem sandbox or a guarantee that every session uses a worktree.
|
|
38
38
|
|
|
39
|
+
### Scoped autonomous execution (#491)
|
|
40
|
+
|
|
41
|
+
**Keep progressing within the user's authorization; ask only at a new boundary.**
|
|
42
|
+
Before asking, check the direct user instructions already available for this task.
|
|
43
|
+
Retain the approved target, purpose, side effects, limits and any revocation in
|
|
44
|
+
session-owned task state. Completing one step, receiving a continuation reminder,
|
|
45
|
+
losing a UI window or finding the user unavailable does not by itself erase that
|
|
46
|
+
authorization. A checkpoint records evidence of consent, not a new permission
|
|
47
|
+
grant; respect any tool that requires fresh direct consent or cannot recover it.
|
|
48
|
+
|
|
49
|
+
Proceed with safe inspection, isolated checks and bounded recovery without routine
|
|
50
|
+
confirmation. An explicit "restart and check" approval covers stopping the approved
|
|
51
|
+
app, starting that same target and inspecting it. If fresh discovery subsequently
|
|
52
|
+
proves it is not running before that check completes, allow at most one recovery
|
|
53
|
+
start under the same authorization, unless the user or tool limits consent to one
|
|
54
|
+
invocation. Do not stop an app that is already running for this recovery, start a
|
|
55
|
+
different target, reinstall, change settings/accounts or broaden the operation.
|
|
56
|
+
Unknown app state calls for read-only discovery, not a guessed launch. Repeated
|
|
57
|
+
exit is a concrete failure to investigate and report, not an unlimited restart loop.
|
|
58
|
+
|
|
59
|
+
Tool consent, refusal and interruption controls take precedence. Report
|
|
60
|
+
"the tool reported input interruption", not "you were operating the app";
|
|
61
|
+
the report does not independently establish human activity or intent. Reobserve
|
|
62
|
+
through the same supported tool before any permitted retry. An interrupted
|
|
63
|
+
attempt is not proof of navigation or product failure. Preserve attempt budgets
|
|
64
|
+
across continuation and compaction; do not reset them by renaming the task,
|
|
65
|
+
switching tools to evade refusal, or receiving an automated completion reminder.
|
|
66
|
+
|
|
67
|
+
At a genuine blocker, state the exact missing permission/capability, consequence
|
|
68
|
+
and next action once, then continue any independent authorized work. Do not repeat
|
|
69
|
+
the same question or unchanged waiting message. If no safe work remains, use the
|
|
70
|
+
host's blocked/awaiting-input mechanism when available; otherwise give one truthful
|
|
71
|
+
partial handoff and wait for changed evidence or user input. A completion reminder
|
|
72
|
+
is not new consent, a retry-budget reset or evidence of success. Never mark an
|
|
73
|
+
unverified requirement passed merely to end the loop.
|
|
74
|
+
|
|
75
|
+
| Situation | Decision |
|
|
76
|
+
|---|---|
|
|
77
|
+
| Approved restart/check; exact app is confirmed stopped | Continue the approved start/check, including the one bounded recovery start when consent permits; do not ask again solely because a previous step finished. |
|
|
78
|
+
| App is already running, target differs, or consent was revoked | Observe the running app; obtain new consent only for the new disruptive action, never infer it from prior installation approval. |
|
|
79
|
+
| Tool reports interruption; user says they did not interact | Keep both facts separate, reread UI and follow the tool's permitted recovery; do not blame the user or bypass the tool. |
|
|
80
|
+
| Genuine approval is missing and the user is absent | Keep that action blocked, do other authorized work, and do not send repeated waiting messages. |
|
|
81
|
+
| Install/import checks pass but loaded version is unknown | Preserve partial status; neither a policy check nor disk evidence proves runtime acceptance. |
|
|
82
|
+
|
|
83
|
+
This policy is exposed by `agent.mjs describe/plan` and checked for drift, not
|
|
84
|
+
enforced by a runtime permission engine. It grants no new live-profile access and
|
|
85
|
+
does not bypass tool approvals, plugin-only ownership, required reviews or CI.
|
|
86
|
+
|
|
39
87
|
## Product and architecture
|
|
40
88
|
|
|
41
89
|
### Confirmed product scope (#455, #456)
|
|
42
90
|
|
|
91
|
+
Current source target: official DSH `0.2.2-rc.3`. The exact source commit and
|
|
92
|
+
dependency versions are recorded in `deployment-baseline.json` and `package.json`.
|
|
93
|
+
|
|
43
94
|
The native enhancement request (#460/#461) adds only reviewer-scoped Responses
|
|
44
95
|
sampling compatibility and an optional canonical-account hosted-search backend.
|
|
45
96
|
Use public native ownership/configuration proof and prepared dispatch; never
|
|
@@ -71,8 +122,8 @@ change other paths or perform this sync automatically.
|
|
|
71
122
|
The user-confirmed direction on 2026-11-14 supersedes conflicting legacy feature
|
|
72
123
|
requirements below: this plugin is a lightweight GitHub Copilot model integration
|
|
73
124
|
for DSH Desktop, not a second agent product. The qualification target is the exact
|
|
74
|
-
official DSH `0.2.2-rc.3` source and published package graph
|
|
75
|
-
|
|
125
|
+
official DSH `0.2.2-rc.3` source and published package graph. Each new revision
|
|
126
|
+
requires its own CI and release evidence; a previous release does not qualify it.
|
|
76
127
|
|
|
77
128
|
DSH owns application login, AgentLoop, model selection, Auto, parent-model
|
|
78
129
|
following, subagents, tools, Web, permissions, history, context/compaction, and
|
|
@@ -122,7 +173,24 @@ subagent invocation must be verified on `github-copilot`, not inferred from
|
|
|
122
173
|
managed-route tests. Record enhancements that cannot safely attach to native
|
|
123
174
|
APIs rather than patching Core or misrepresenting support.
|
|
124
175
|
|
|
125
|
-
|
|
176
|
+
For official DSH `0.2.2-rc.3`, plugin `0.1.0-alpha.14.dsh.0.2.2.rc.3`
|
|
177
|
+
at `5d82df760683eeae7bb0413c946e4d25daef2049` passed the Windows/Linux
|
|
178
|
+
source/artifact CI in [run 43691055529](https://github.com/cloga/dsh-github-copilot/actions/runs/43691055529)
|
|
179
|
+
and was published to GitHub Releases and npm. This evidence is limited to that
|
|
180
|
+
revision; later changes require their own CI and publication evidence.
|
|
181
|
+
Desktop signatures, installation, loaded state, OAuth and supplier calls are not
|
|
182
|
+
established. The `desktopCandidateQualified: false` contract
|
|
183
|
+
tracks the unverified Desktop artifact/live-acceptance layer, not a failed CI.
|
|
184
|
+
Earlier pins are historical evidence, not current support gates. A prerelease
|
|
185
|
+
is not a production Core upgrade recommendation. DSH's built-in `llm-pi-ai`
|
|
186
|
+
owns the canonical GitHub Copilot provider, OAuth, grant format, token exchange,
|
|
187
|
+
refresh, and normal model transport.
|
|
188
|
+
|
|
189
|
+
Historical [#483](https://github.com/cloga/dsh-github-copilot/issues/483):
|
|
190
|
+
releases through alpha.12 could reject native schema-default compatibility
|
|
191
|
+
maps, blocking hosted-search proof and reviewer-only temperature omission.
|
|
192
|
+
The alpha.13 release includes a narrow fix; confirm live behavior independently.
|
|
193
|
+
Do not suggest profile edits as a workaround.
|
|
126
194
|
|
|
127
195
|
The following is a historical architecture inventory, not a requirement to keep
|
|
128
196
|
every surface as a product feature; apply the confirmed scope above when deciding
|
|
@@ -229,7 +297,8 @@ Keep the native UI and its canonical quota/search attribution. Existing
|
|
|
229
297
|
`github-copilot-preview` behavior and Session account overrides remain
|
|
230
298
|
separately plugin-owned legacy behavior; they are not required for native
|
|
231
299
|
switching. Disposal removes only plugin registrations. Native model selections
|
|
232
|
-
|
|
300
|
+
remain native; plugin-only model selections and explicit
|
|
301
|
+
`web.searchProvider=github-copilot-hosted` need user-selected
|
|
233
302
|
replacements before uninstall; missing configured Web backends return
|
|
234
303
|
`WEB_PROVIDER_CONFIGURED_MISSING`, not automatic fallback. Uninstall leaves the
|
|
235
304
|
last selected grant in the native canonical record. No automatic
|
|
@@ -239,7 +308,7 @@ Login environments (#424) use only pinned native pi-ai OAuth for GitHub.com and
|
|
|
239
308
|
validated single-label `tenant.ghe.com` Enterprise Cloud hosts. Preserve host
|
|
240
309
|
binding through identity, duplicate checks, reauthorization and native refresh/
|
|
241
310
|
discovery/request auth. Plugin identity rejects redirects; native OAuth redirect
|
|
242
|
-
control is unavailable in pi-ai 1.
|
|
311
|
+
control is unavailable in pi-ai 1.3.0 and must not be claimed or emulated with a
|
|
243
312
|
global Fetch patch/second flow. GHES and Enterprise quota remain unsupported.
|
|
244
313
|
See `src/copilot-login-environment.ts` and `docs/copilot-accounts.md`.
|
|
245
314
|
|
|
@@ -255,9 +324,9 @@ Account display names survive freshness expiry in bounded Host memory, never cre
|
|
|
255
324
|
|
|
256
325
|
Additional plugin-owned `github-copilot/account-<opaque-id>` records are written directly by official pi-ai OAuth through public account-bound stores. Only an explicit user-confirmed switch may project a selected normalized grant into the canonical record as specified above; preserve the former canonical grant before the first replacement. Never intercept Core credential reads, introduce a separate credential service, patch Core, or implement another wire/catalog. Native `Models.getAuth()` and DSH `modifyRecord()` remain the refresh and serialization owners.
|
|
257
326
|
|
|
258
|
-
Settings store only the opaque global account selector and explicit `sessionAccounts` rows. Missing/invalid selectors or records fail explicitly, without another-account fallback. Models manages
|
|
327
|
+
Settings store only the opaque global account selector and explicit `sessionAccounts` rows. Missing/invalid selectors or records fail explicitly, without another-account fallback. Models manages account authorization and the global default; Credits may select an already authorized managed-route account for this Session's subsequent turns or restore global inheritance (#305/#318). An explicit choice equal to the default remains explicit. Freeze account ownership before request admission, holding mutation fences until native `turn/end`/disposal; later Session/default changes never redirect running steps, retries or search. Account-local credentials, metadata, quota, proof cancellation and native adapter composition must remain isolated. Keep one public adapter/controller registration, with no second wire/catalog or Core changes. Reauthorization/removal of a pinned record stays blocked; global-default selection may continue independently.
|
|
259
328
|
|
|
260
|
-
Account selection shows the current account and a compact Switch dropdown with no account search, never a flat unbounded account list. Mark the current choice
|
|
329
|
+
Account selection shows the current account and a compact Switch dropdown with no account search, never a flat unbounded account list. Mark the current choice and scroll long lists internally; Add and saved-account reauthorization/removal remain in Models, not Credits. One Models Manage disclosure contains account management and cross-account exact-ID model preferences. Continuation settings belong beside account controls. Persist the initial default-on epoch and later global changes with path-level CAS; only unseeded Sessions born after a known epoch inherit it, never retroactively enroll existing/unknown/forked histories. Normal Client continuation uses only the persistent Session policy; no next-turn-only or temporary-recovery duration choices. Explicit-off account changes require persistent-enable/keep-off/cancel choices, then fresh account revision readback before CAS. Exact replay failures offer loss-disclosed persistent Enable/Cancel when off, diagnostics without repeated authorization when on. Missing policy evidence fails explicitly, never a temporary authorization fallback. Retain old next-turn/recovery strict Remote contracts and Host admission for compatibility; failure-evidence expiry does not disable the persistent policy. No automatic send/retry, history writes, private Settings navigation or inferred encrypted account origin. The approved synthetic mock and current navigation limit are documented in [account management](./docs/account-management-experience.md).
|
|
261
330
|
|
|
262
331
|
Use hidden volatile `sessionAccounts` with path-level SettingsForms CAS, readback and restart evidence. Session account Remotes use explicit viewed IDs, native Agent lookup and strict codecs, never automatic Client scope. Credits uses that Session's account for identity/quota, rejecting mismatched or late results. Historical Account is an additive assistant-actions disclosure beside native Usage, captured only after a real ordinary native chunk; bounded Host-lifetime evidence becomes unknown after restart/eviction and is never reconstructed from today's settings. No new durable events, history/default/model/Usage writes, automatic account fallback, replay deletion or message retry. See [the requirements and acceptance gates](./docs/copilot-accounts.md).
|
|
263
332
|
|
|
@@ -272,8 +341,14 @@ Alpha.25 admits native `subagent/descriptor` v3, already v3 in the retained rc.1
|
|
|
272
341
|
- `src/index.ts`: authorization bootstrap, dependency-gated Host entry, settings registration, listener, and `ctx.web` provider composition.
|
|
273
342
|
- `src/authorization-controller.ts`: sign-in/status/sign-out and route mutation.
|
|
274
343
|
- `src/copilot-grant.ts`, `src/copilot-auth.ts`: strict grant normalization and narrow pi-ai `CredentialStore` adapter; canonical compatibility and explicitly selected account records follow the account-binding contract.
|
|
275
|
-
- `src/client.ts`:
|
|
276
|
-
|
|
344
|
+
- `src/client.ts`: account and model controls, the native search-model setting,
|
|
345
|
+
and additive optional Chat integration through public slots.
|
|
346
|
+
- `src/native-copilot-access.ts`, `src/native-copilot-search.ts`,
|
|
347
|
+
`src/native-search-model-card.ts`: proof-bound canonical hosted search in
|
|
348
|
+
DSH's existing Web service and its explicit model choice.
|
|
349
|
+
- `src/web-search-routing-config.ts`, `src/web-search-routing-card.ts`: retained
|
|
350
|
+
legacy routing code and compatibility exports; the old routing UI and facade
|
|
351
|
+
are not mounted current behavior. Never reactivate them implicitly.
|
|
277
352
|
- `tests/fixtures/reasoning-presentation-core.fixture.ts`: native blank-reasoning rendering acceptance and independent Auto/Usage mount evidence. Do not restore the retired plugin renderer/provenance projection or change messages, replay indexes or Usage.
|
|
278
353
|
- `src/remote.ts`: Typert Remote contribution. Never add credential payloads here.
|
|
279
354
|
- `src/copilot-usage-host.ts`, `src/copilot-usage-remote.ts`, `src/copilot-usage-card.ts`, `src/copilot-usage-ui.ts`: bounded Host quota snapshots, an independent strict namespace and reversible composer presentation. No real account fetches in tests, private Client store/DOM injection, quota-specific credential owner or general model wire.
|
|
@@ -292,11 +367,12 @@ Alpha.25 admits native `subagent/descriptor` v3, already v3 in the retained rc.1
|
|
|
292
367
|
- `src/model-protocol.ts`: explicit Core capability detection and conservative legacy fallback.
|
|
293
368
|
- `src/responses-reasoning.ts`, `src/responses-reasoning-text.ts`: selected-model effort mapping and public summary assembly.
|
|
294
369
|
- `src/tool-schema-compat.ts`: Copilot-only prompt-assembly filter for unusable escalation arguments; Goal schemas remain native.
|
|
295
|
-
- `src/plan.ts
|
|
296
|
-
|
|
297
|
-
|
|
298
|
-
- `src/
|
|
299
|
-
-
|
|
370
|
+
- `src/plan.ts`, `src/probe.ts`, `src/wire.ts`, `src/wire-anthropic.ts`,
|
|
371
|
+
`src/traditional-search.ts`: retained historical hosted-search and routing
|
|
372
|
+
implementation; current registration is owned by `src/native-copilot-search.ts`.
|
|
373
|
+
- `src/auto-assessment-evidence.ts`: retained historical classifier evidence;
|
|
374
|
+
plugin-owned Auto assessment and routing are not mounted. Preserve bounded,
|
|
375
|
+
content-free evidence without reactivating them.
|
|
300
376
|
- `src/serialize.ts`, `src/sse.ts`, `src/failure.ts`: protocol conversion and bounded error handling.
|
|
301
377
|
- `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.
|
|
302
378
|
- `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.
|
|
@@ -310,6 +386,10 @@ Alpha.25 admits native `subagent/descriptor` v3, already v3 in the retained rc.1
|
|
|
310
386
|
|
|
311
387
|
## Non-negotiable invariants
|
|
312
388
|
|
|
389
|
+
The following two classifier and context-projection paragraphs are historical
|
|
390
|
+
constraints on retained plugin Auto code, not a current runtime feature or
|
|
391
|
+
authorization to reactivate it.
|
|
392
|
+
|
|
313
393
|
Auxiliary classifier disable proof accepts explicit supplier `off` or the
|
|
314
394
|
selected protocol's native `none` (Responses/Completions) or `disabled`
|
|
315
395
|
(Anthropic), scoped to the isolated classifier model only. Missing/empty effort
|
|
@@ -351,13 +431,18 @@ evidence is content-free and ephemeral, never a new persistent population.
|
|
|
351
431
|
- Copilot OAuth grant writes must rebuild only pi-ai's documented provider fields as a fresh plain JSON object; unrelated extension values never reach DSH credential storage.
|
|
352
432
|
- Settings changes are path-level. Never replace the whole `llm-pi-ai` section or unrelated provider profiles.
|
|
353
433
|
- Native sign-out deletes only `llm-pi-ai/github-copilot` and keeps plugin account records, the selector and route settings. A selected plugin account remains saved and must be explicitly applied again after sign-out; a missing selected slot fails explicitly, never automatic canonical fallback.
|
|
354
|
-
-
|
|
434
|
+
- The explicitly selected `github-copilot-hosted` backend uses the canonical native Copilot account and account-proven Responses models also present in the native catalog. Its configured model or deterministic first eligible model receives one fixed capability probe followed by one user query, without fallback or replay. Enforce the 25-second deadline, four-operation limit and account/configuration/disposal fences; metadata alone is not search proof. The old plugin router and custom inline transport are historical, not active alternatives. If that legacy wire is ever deliberately restored, file blocks, including nested tool-result files, must still delegate through `next()` so Core owns file projection.
|
|
355
435
|
- Misconfiguration and API drift fail loudly with a named missing seam. Do not fall back to process-local secrets or implicit machine state.
|
|
356
436
|
- Host, Client, and Remote package entries must stay independently buildable and exported.
|
|
357
437
|
- The package must self-provide authorization when Core omits it, reuse an existing service without duplicate registration, and never activate the integration body before authorization is available.
|
|
358
438
|
|
|
359
439
|
## Session and migration ownership (V3, alpha.8, #99)
|
|
360
440
|
|
|
441
|
+
The following legacy managed-route/search design is historical. The plugin
|
|
442
|
+
router and managed Auto are retired, and removing the canonical native route is
|
|
443
|
+
not the current direction. Do not execute the old migration proposal; use the
|
|
444
|
+
confirmed scope above and the [current README](./README.md).
|
|
445
|
+
|
|
361
446
|
- One global Host account supplies many models; selected/history-backed Sessions retain independent model context. Auto-mode native search derives from the captured initiating Session's effective request-header/config or explicit `GenerateOptions`, never another Session or future global default C. Fixed/fallback Copilot search uses the explicit provider-owned `searchModel` override when nonempty, otherwise bounded automatic account-owned Responses selection; it never borrows the Chat model, another Session's selection or the global chat default. `Agent.options` is the activation seed, not selected Session-model evidence; `installModelSelection` overrides request/assembly; Core records the effective `Session.requestHeader().config` before tools. Without proven request context, traditional search is unavailable. A newly selected pending model must not reuse the old request header as current prompt guidance. Per-owner plan caches prevent different-model A/B reuse/cancellation; metadata remains shared.
|
|
362
447
|
- The ordinary Web search card selects only the primary and fallback providers and saves both routing leaves in one CAS mutation in the existing `github-copilot` namespace at `['searchRouting', 'searchProvider']` and `['searchRouting', 'defaultSearchProvider']`. It must not depend on Copilot model discovery, account credentials or a model selection to save routing. Capture traced Settings/routing Remote faces once per UI registration so parent renders do not reset drafts. Preserve a legacy nonempty `searchModel` override; display it read-only and reset it only through an explicit, separate narrow CAS setting `searchModel: ''`, never as a routing-save side effect. Because routing and `searchModel` share the `github-copilot` namespace and revision, successful mutation of either updates the other's expected revision to avoid false CAS conflicts while preserving unsaved drafts. Saving settings does not prove hosted-search capability.
|
|
363
448
|
- Cold Chat picker and `/model` `listModels()` ensure the shared managed source without Settings first. Actual cold managed search non-forcing ensures metadata before deriving facts; existing 24h maximum TTL, cooldown, credential, allowlist and capability/probe gates remain.
|
|
@@ -368,6 +453,9 @@ evidence is content-free and ephemeral, never a new persistent population.
|
|
|
368
453
|
|
|
369
454
|
## Live migration readiness (alpha.9, #101)
|
|
370
455
|
|
|
456
|
+
Historical readiness evidence only: it is not an authorization or current plan
|
|
457
|
+
to remove the native provider or migrate settings.
|
|
458
|
+
|
|
371
459
|
- Use no-argument `githubCopilot.migrationStatus()` for fresh live-Agent evidence; generic `session/list` may be stale and plugin inventory alone has no loaded-version evidence. `src/migration-status.ts` reads public leaves synchronously and reports loaded build `plugin.name/version`, `protocolVersion: 1`, `observedAt`, capability flags and completeness flags. Missing/unknown/incomplete is not safe absence.
|
|
372
460
|
- Capabilities are `agentsList`, `sessionProjections`, `settingsCas`, `providerRegistry`, `defaultSelection`; `complete.sessions/defaultSelection/routes` describes evidence completeness, not migration approval. Effective selection uses pending projection, request-header config, then default only for genuinely empty Sessions with known projection state. Running `activeRequestSelection` is the latest recorded header, not proven in-flight LLM work. Native effective configuration and native/managed registration are separate flags.
|
|
373
461
|
- This read invokes no auth status/model discovery, credentials or network and mutates no settings/Sessions. No normal UI/global current-model/search card is added. Nine ordinary authorization/model-preference Remotes retain their codec; the tenth migration Remote uses a separate strict `GitHubCopilotMigrationStatus` codec.
|
|
@@ -392,9 +480,22 @@ The retained upstream baselines and current qualification target are:
|
|
|
392
480
|
- Official tag `dsh-v0.2.0-rc.2`, commit `639ed015397290b3745d163aafe02ffee4aa3f84`; the signed installed Windows Desktop descriptor identifies the rc.2 shared peer graph.
|
|
393
481
|
- Official tag `dsh-v0.2.1-alpha.4`, commit `86a402200d95fecef4529d969836f1fe13c6cb0d`; historical alpha.16 source/npm qualification only.
|
|
394
482
|
- Official tag `dsh-v0.2.1-alpha.5`, commit `1517a4dbca0a2789ff1d41ba439600f8547d23fa`; exact source/npm qualification is separate from unverified candidate Desktop artifacts/signatures.
|
|
395
|
-
- Official tag `dsh-v0.2.1-rc.3`, commit `1f81c047fc48fa190a683e469daa699857e9afe8`; prerelease
|
|
396
|
-
|
|
397
|
-
|
|
483
|
+
- Official tag `dsh-v0.2.1-rc.3`, commit `1f81c047fc48fa190a683e469daa699857e9afe8`; historical prerelease with a public `WebRuntime` Volatile-provider contract change.
|
|
484
|
+
- Official tag `dsh-v0.2.2-rc.3`, commit `38a6a5c965aa99ab525161efb7cc5cf1fe62fced`; current source and published-package qualification target.
|
|
485
|
+
|
|
486
|
+
Release admission, development dependencies and CI target the exact current
|
|
487
|
+
Core in `package.json`; prior pins are historical. The exact pi-ai,
|
|
488
|
+
Cordis, loader, schemastery and Zod versions also come from package metadata.
|
|
489
|
+
CI runs unchanged tagged-source and isolated published-artifact fixtures on
|
|
490
|
+
Windows and Linux. Fixtures await serialized `agent/created`, avoid new
|
|
491
|
+
synchronous Session-history reads, and preserve MCP/PTC/workflow/Sandbox/Shell/
|
|
492
|
+
image-offload/Team ownership. Native gateway fixtures bind an explicit public
|
|
493
|
+
owner Peer and interactive Client carrier; Session-controller fixtures register
|
|
494
|
+
native resources. Synthetic identities never authorize live access. Source or
|
|
495
|
+
synthetic tests alone do not prove live endpoints, plugin activation,
|
|
496
|
+
publication or loaded runtime state. The [0.2.1-rc.3 review](./docs/official-first-021-rc3.md)
|
|
497
|
+
is historical; passing source/artifact CI never authorizes Core rewrites or
|
|
498
|
+
experimental durable records.
|
|
398
499
|
|
|
399
500
|
These pins document compatibility evidence. They do not authorize creating another controlled Core patch or making one a prerequisite for new plugin fixes.
|
|
400
501
|
|
|
@@ -412,9 +513,9 @@ These pins document compatibility evidence. They do not authorize creating anoth
|
|
|
412
513
|
- Remote results: the nine ordinary authorization/model-preference methods retain the Zod v4 `GitHubCopilotAuthorizationView` strict codec required by rc.2 and accepted by rc.1. The tenth no-argument `migrationStatus()` method has a separate strict `GitHubCopilotMigrationStatus` codec; it does not change the ordinary auth contract.
|
|
413
514
|
- Single-model saves use the additive `setModelExcluded(modelId, excluded)` Remote with an independent strict `GitHubCopilotModelPreferencesView` result. Preserve the ten existing descriptor identities/codecs. Do not read credentials, discover models or enumerate Sessions on this mutation path; confirm native CAS persistence before returning.
|
|
414
515
|
|
|
415
|
-
When upgrading DSH or pi-ai, inspect the exact tagged public exports and update the baseline, compatibility guard, tests, and docs together. Apply the **official-first policy**: compare each customization's purpose against exact official source/contracts, classify complete/partial/unverified support, choose retain/migrate/retire, and record the remaining gap plus a concrete retirement trigger. Unverified parity is not evidence of absence. Prefer official behavior only after configuration/data migration, safety and runtime acceptance are reviewed; remove redundant paths and their obsolete tests without losing user-visible acceptance coverage. The
|
|
516
|
+
When upgrading DSH or pi-ai, inspect the exact tagged public exports and update the baseline, compatibility guard, tests, and docs together. Apply the **official-first policy**: compare each customization's purpose against exact official source/contracts, classify complete/partial/unverified support, choose retain/migrate/retire, and record the remaining gap plus a concrete retirement trigger. Unverified parity is not evidence of absence. Prefer official behavior only after configuration/data migration, safety and runtime acceptance are reviewed; remove redundant paths and their obsolete tests without losing user-visible acceptance coverage. The [alpha.2 comparison](./docs/official-first-016-alpha2.md) is historical, not the current release qualification.
|
|
416
517
|
|
|
417
|
-
For alpha.25, source markers, local rc.1-backed focused tests and fifteen scoped exact-source runtime tests passed (alpha.2 contracts 8, Remote 1 and Session-context 6). Full local `pnpm verify` passed: 1373 Vitest tests with 2 expected skips, 176 tooling tests, typechecks, build and package smoke; pack/tarball verification passed. The scoped tests
|
|
518
|
+
For historical alpha.25, source markers, local rc.1-backed focused tests and fifteen scoped exact-source runtime tests passed (alpha.2 contracts 8, Remote 1 and Session-context 6). Full local `pnpm verify` passed: 1373 Vitest tests with 2 expected skips, 176 tooling tests, typechecks, build and package smoke; pack/tarball verification passed. The scoped tests used a supplemental resolver with official TypeScript `6.0.3`, declared `mime-types@3.0.2` and `ws@8.21.0`, and shared Zod `^4.4.3`, without source/dependency patches, not the full official-root-helper closure. That historical local mirror lacked `node-addon-require-builtin@0.1.6`; the observation is not the current CI status. Keep historical limits separate from live Desktop, published-artifact, OAuth and model-call compatibility.
|
|
418
519
|
|
|
419
520
|
## Code and documentation conventions
|
|
420
521
|
|
|
@@ -467,8 +568,9 @@ plugin version. Attempt safe authorized checks on an already-running Desktop;
|
|
|
467
568
|
unreliable local npm is not a reason to skip them. Use existing computer-use
|
|
468
569
|
tools, never shell activation or a repository script as an App controller.
|
|
469
570
|
Begin with current app discovery, not a historical "already open" claim. If not
|
|
470
|
-
running, start only with explicit launch authorization
|
|
471
|
-
|
|
571
|
+
running, start only with explicit launch authorization (including an applicable
|
|
572
|
+
restart/check approval retained under scoped autonomous execution) via controlled
|
|
573
|
+
`start_app` using the exact approved target; then verify discovery and fresh UI, not merely
|
|
472
574
|
the launch receipt. Do not start an already-running app again. A welcome screen
|
|
473
575
|
is not automatically an auth blocker: inspect an official safe skip first. DSH's
|
|
474
576
|
Add API Key -> Set up later path does not submit/store a key or authenticate;
|
|
@@ -476,17 +578,22 @@ use it only when actually exposed, within tool permission rules. Never infer
|
|
|
476
578
|
Copilot account invalidity from welcome UI or bypass real authentication/warnings.
|
|
477
579
|
Welcome dismissal may replace the window: rediscover app/window and read its fresh
|
|
478
580
|
tree before acting, rather than retrying a stale window on an empty immediate diff.
|
|
479
|
-
Honor
|
|
581
|
+
Honor tool-reported input interruption without inferring human intent: reread UI
|
|
582
|
+
before retrying the same permitted action.
|
|
480
583
|
Before handoff, freshly discover the current app and inspect the target panel or
|
|
481
584
|
workspace, reporting the observation time only; past success does not establish
|
|
482
585
|
current running state or guarantee the app remains running later.
|
|
483
586
|
An action receipt or empty immediate diff is not a navigation failure: obtain
|
|
484
587
|
a fresh post-action `get_window_state` observation first. Keep one attempt per
|
|
485
|
-
supported navigation method, at most two different methods
|
|
588
|
+
supported navigation method, at most two different methods. A tool-required
|
|
589
|
+
interruption recovery may retry that same method once after fresh observation;
|
|
590
|
+
it is not a new method or an unlimited retry exemption. Then report precise
|
|
486
591
|
`automation-blocked` and request the named panel once. User absence or an
|
|
487
592
|
unanswered request never grants permission or proves the panel opened.
|
|
488
593
|
App unavailable, restart/install, account/OAuth/paid actions outside explicit
|
|
489
|
-
permission stay blocked
|
|
594
|
+
permission stay blocked; first check whether the needed action is already covered
|
|
595
|
+
by scoped authorization. Do not repeat exhausted methods on ordinary continuation
|
|
596
|
+
or repeat an unchanged blocker message.
|
|
490
597
|
Record only fixed action/outcome codes, numeric times and version/source facts;
|
|
491
598
|
never upload identities, credentials or conversation content. Unknown loaded
|
|
492
599
|
version permits qualified observations only, not a version-specific fix claim.
|
|
@@ -548,7 +655,17 @@ Then run `pnpm verify:tarball -- artifacts/dsh-github-copilot-<package-version>.
|
|
|
548
655
|
|
|
549
656
|
If a historical/approved local installation attempt is blocked solely by an enterprise registry or network policy while GitHub Actions can obtain unchanged pinned packages from an authorized official registry, record it as **local validation blocked**, not passed. Do not repeat dependency recovery, switch sources, or expand permissions. A PR may proceed with that limitation disclosed; the complete required GitHub CI matrix, including install, tests, build and package checks, is authoritative before merge. Never weaken or skip CI, substitute dependencies, bypass organizational restrictions, claim unrun local gates succeeded, or tag/release a revision whose required CI is not green. If CI has the same failure, resolve it through approved infrastructure rather than bypassing it.
|
|
550
657
|
|
|
551
|
-
The release CI matrix targets only exact
|
|
658
|
+
The release CI matrix targets only the exact current Core on Windows and Linux;
|
|
659
|
+
earlier pins are not support gates. It runs the unchanged tagged-source runtime
|
|
660
|
+
fixture, optional native Chat fixture, exact published-artifact adapter fixture
|
|
661
|
+
and the reviewer regressions required by the current CI workflow without skips.
|
|
662
|
+
This is a required gate, not evidence that an unexecuted qualification passed.
|
|
663
|
+
`verify:upstream` is static seam-marker evidence. `verify:controlled-core`
|
|
664
|
+
exclusively installs a temporary config fixture, refuses an existing target,
|
|
665
|
+
and removes only its own file; it is not full plugin activation. Published-artifact
|
|
666
|
+
synthetic adapter fixtures do not prove live provider transport. The release job
|
|
667
|
+
must wait for the complete reusable CI matrix on the tagged revision, then
|
|
668
|
+
verify its own packed bytes before publishing.
|
|
552
669
|
|
|
553
670
|
### Evidence and side effects
|
|
554
671
|
|
|
@@ -567,7 +684,7 @@ The release CI matrix targets only exact official `0.2.1-rc.3` on Windows and Li
|
|
|
567
684
|
| Last metadata display | Same-account data may display during TTL refresh/loading/error but never authorize requests; credential/account/permission invalidation or proof expiry immediately revokes evidence; TTL does not extend tokens |
|
|
568
685
|
| Last-success timestamp (alpha.7, #97) | Show `snapshot.discoveredAt` once beside count outside Manage: English relative text, full LOCAL date/time/zone tooltip and accessible semantic `time`; missing/invalid/no account hides it, future uses absolute text. Pending/error retains last success, successful refresh replaces it and sign-out clears it. One mounted 60s display-only timer makes no RPC/status/discovery calls and is disposed with timestamp/unmount; cache/discovery lifecycle unchanged |
|
|
569
686
|
| Definitive `UNKNOWN_MODEL` | One bounded metadata refresh, never message replay or automatic model switching; generic HTTP/network errors are not guessed to be unknown models |
|
|
570
|
-
|
|
|
687
|
+
| Historical routing screenshot | `copilot-search-routing.png` records a retired plugin-detail routing card with synthetic providers; it does not depict the current UI or prove live search or Desktop activation. |
|
|
571
688
|
| Host attach/restart | Does not repair or rewrite the stored native profile; search proofs stay lazy and do not start at attach |
|
|
572
689
|
| Background credential/reset notifications | Invalidate evidence and clear Client state with read-only status; no forced discovery on every token event; next Models open/use ensures metadata |
|
|
573
690
|
| Eligible model/search request | May resolve/refresh credentials and run bounded capability proof; changes during proof must fail closed rather than reuse another account's proof |
|
|
@@ -577,6 +694,10 @@ Never say GPT-6/search works merely because settings, typecheck or a package imp
|
|
|
577
694
|
|
|
578
695
|
## Changing capabilities
|
|
579
696
|
|
|
697
|
+
The plugin-owned Auto and parent-follow implementations described in historical
|
|
698
|
+
paragraphs below are not mounted current behavior. Preserve retained data and
|
|
699
|
+
compatibility code, but do not reactivate their routing or UI.
|
|
700
|
+
|
|
580
701
|
Auto routing, assessment, cost weights, continuity and assistance changes must
|
|
581
702
|
first read and validate `docs/auto-iteration-review.json` using
|
|
582
703
|
`scripts/iteration-review.mjs`. Follow `docs/evidence-driven-iteration.md`:
|
|
@@ -645,7 +766,7 @@ Retain native Host agent lookup/access checks and strict codecs. Failed reads
|
|
|
645
766
|
must remain distinct from successfully read missing evidence; Retry reads the
|
|
646
767
|
same turn only and never replays inference. See #249.
|
|
647
768
|
|
|
648
|
-
|
|
769
|
+
Historical parent-model following used the profile-wide `github-copilot.followParentModel` switch and a plugin-detail control (#234). That routing and control are retired; DSH owns current parent/child behavior. Preserve legacy `parentModelFollow` data without reactivating the plugin policy, mutating descriptors/history/defaults or silently migrating settings. See `docs/parent-model-follow.md` and `docs/automatic-model-routing.md` for historical evidence.
|
|
649
770
|
|
|
650
771
|
Model preferences must survive the Client's owned-field projection before strict decoding. `excludedModelIds` is a hidden volatile Config leaf, read via `readInlineConfig`; exercise native SettingsForms CAS, fiber preservation and restart persistence, not only map-backed settings mocks. Missing preference settings leave model rows read-only with named diagnostics and status-only Retry. Unknown exclusion state is not an empty exclusion set. Discovery diagnostics stay in a separate Manage disclosure. Selected models are excludable without scanning Sessions/defaults; the legacy `lockedModelIds` wire leaf stays empty. Check exclusion at new-turn admission through public `agent/request`, preserving only the same Session/turn/model and exact native request signal for subsequent steps/retries. Clear admission on `turn/end`. Direct/unbound requests and new turns remain excluded; never rewrite selections/history or switch models silently. Account/token/metadata/cancellation guards remain independent and revocable.
|
|
651
772
|
|
|
@@ -657,7 +778,16 @@ Auto intent continuity (#293) uses the strict `githubCopilotAutoModelIntent` pub
|
|
|
657
778
|
|
|
658
779
|
1. Identify the owning seam using `agent-contract.json`; do not duplicate an upstream owner.
|
|
659
780
|
2. Add or update focused tests before changing deployment claims.
|
|
660
|
-
3.
|
|
781
|
+
3. Review both READMEs and every affected domain document against source for
|
|
782
|
+
user behavior, setup, migration, limitations, and evidence changes. Update
|
|
783
|
+
both READMEs and the relevant `docs/*.md` in the same PR for user-facing
|
|
784
|
+
changes, beyond version-only edits. For unchanged behavior, explain why.
|
|
785
|
+
The PR `Documentation impact` declaration is checked against changed files
|
|
786
|
+
and rechecked when edited; it cannot judge semantic accuracy or relevance.
|
|
787
|
+
An agent or human reviewer must check those claims against source and retain
|
|
788
|
+
dated historical evidence. Record findings in the PR. This is not a new
|
|
789
|
+
human-only approval gate; agents may complete the review and proceed when
|
|
790
|
+
actual GitHub review/CI requirements and authorization boundaries are met.
|
|
661
791
|
4. Update `deployment-baseline.json`, `agent-contract.json` and their verifiers when the corresponding contract changes.
|
|
662
792
|
5. Build before package smoke; never hand-edit `lib/`.
|
|
663
793
|
|
package/CHANGELOG.md
CHANGED
|
@@ -1,18 +1,35 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
Status labels record what was known when each entry was written; immutable
|
|
4
|
+
release tags do not update this file after publication. Check the exact
|
|
5
|
+
[GitHub Release](https://github.com/cloga/dsh-github-copilot/releases) and npm
|
|
6
|
+
version separately rather than treating an old `prepared` label as current status.
|
|
7
|
+
|
|
8
|
+
## 0.1.0-alpha.16.dsh.0.2.2.rc.3 (prepared)
|
|
9
|
+
|
|
10
|
+
- Record native Copilot turn-account evidence only after an ordinary native stream chunk is yielded for the admitted account (#488).
|
|
11
|
+
- Exclude auxiliary calls and require native route and canonical-account proof; mismatches and credential changes leave evidence unknown.
|
|
12
|
+
- Retain bounded, Host-memory-only history; never infer older turns from current settings.
|
|
13
|
+
|
|
14
|
+
## 0.1.0-alpha.15.dsh.0.2.2.rc.3 (prepared)
|
|
15
|
+
|
|
16
|
+
- Include an optional, bounded offline multi-turn autonomy trace evaluator and synthetic examples (#494).
|
|
17
|
+
- Detect repeated approval/blocker requests, unconsented protected actions and unverified outcomes while preserving explicit task-scoped authorization across tool-state changes.
|
|
18
|
+
- Keep this as a repository analysis aid, not runtime agent enforcement or proof of improved autonomy; no profile, account or model calls are changed.
|
|
19
|
+
|
|
20
|
+
## 0.1.0-alpha.14.dsh.0.2.2.rc.3
|
|
4
21
|
|
|
5
22
|
- Add independently enabled, content-free native Copilot logical stream and hosted-search aggregates (#486).
|
|
6
23
|
- Keep native observations separate from managed physical-request diagnostics; they do not prove HTTP dispatch, supplier receipt or execution.
|
|
7
24
|
- Preserve request, retry, Usage and settings ownership; old strict versions may not read retained new operation codes on rollback.
|
|
8
25
|
|
|
9
|
-
## 0.1.0-alpha.13.dsh.0.2.2.rc.3 (
|
|
26
|
+
## 0.1.0-alpha.13.dsh.0.2.2.rc.3 (published)
|
|
10
27
|
|
|
11
28
|
- Qualify native Copilot profiles after actual Config/Settings normalization: schema-default empty template maps and boolean `supportsStrictMode` no longer disable reviewer-only temperature omission or canonical hosted-search readiness (#483).
|
|
12
29
|
- Apply the same narrow compatibility rule at provider, model and model-override levels while retaining unknown-value, credential, endpoint, headers, ownership and lifecycle refusal.
|
|
13
30
|
- Add normalized native configuration and reviewer/search regressions. No profile rewrite, Core patch, automatic restart, general sampling override or live supplier acceptance is implied.
|
|
14
31
|
|
|
15
|
-
## 0.1.0-alpha.12.dsh.0.2.2.rc.3 (
|
|
32
|
+
## 0.1.0-alpha.12.dsh.0.2.2.rc.3 (published)
|
|
16
33
|
|
|
17
34
|
- Retire the managed route's projected-image MIME preflight and Goal schema rewriting (#481). Core owns image projection and Goal schemas; supplier errors are not preempted by a plugin MIME diagnostic.
|
|
18
35
|
- Keep the managed route's permission-field filtering and the native model-sync format eligibility checks unchanged.
|
package/CONTRIBUTING.md
CHANGED
|
@@ -16,9 +16,9 @@ Core inspection is read-only. Isolated tests may use unchanged pinned Core artif
|
|
|
16
16
|
|
|
17
17
|
1. Determine `pwd`, Git status, remote and actual default branch. Preserve other people's changes. Start a feature branch such as `feature/issue-73-agent-readiness`; branch names need not contain an owner name.
|
|
18
18
|
2. Read `node scripts/agent.mjs describe --json` and run `node scripts/agent.mjs doctor --json`. These are read-only repository diagnostics, not live health checks. Plans from `node scripts/agent.mjs plan <task> --json` contain unexecuted argv lists.
|
|
19
|
-
3. Use Node 24 LTS for development (runtime floor: 22.19.0)
|
|
20
|
-
4. Add focused regression tests before changing capability claims.
|
|
21
|
-
5. State expected outcomes and scope
|
|
19
|
+
3. Use Node 24 LTS for development (runtime floor: 22.19.0) and the pinned pnpm version. Agents must follow the [environment guardrails](./docs/environment-evidence-guardrails.md): local work is limited to the guarded dependency-free scripts tests; do not install or restore dependencies locally.
|
|
20
|
+
4. Add focused regression tests before changing capability claims. Review and update both READMEs and relevant domain docs with user-facing behavior; keep deployment evidence and the Agent task map aligned.
|
|
21
|
+
5. State expected outcomes and scope. The existing GitHub Actions workflow runs:
|
|
22
22
|
|
|
23
23
|
```sh
|
|
24
24
|
pnpm install --frozen-lockfile
|
|
@@ -26,10 +26,10 @@ Core inspection is read-only. Isolated tests may use unchanged pinned Core artif
|
|
|
26
26
|
pnpm pack --pack-destination artifacts
|
|
27
27
|
```
|
|
28
28
|
|
|
29
|
-
|
|
29
|
+
CI validates the resulting exact path with `pnpm verify:tarball -- artifacts/dsh-github-copilot-<package-version>.tgz`. The release task plan supplies that path automatically. Never run broad cleanup on an existing artifacts directory just to package again. Local agent validation uses `node scripts/agent.mjs guard --task tooling --environment local-auxiliary --operation scripts-test`; it is not the complete gate.
|
|
30
30
|
6. Inspect the complete diff, compare expected versus actual results, and report what was NOT checked. Source markers, stubbed unit tests, built module imports, upstream config fixtures, authenticated API calls, installation, and loaded UI are different evidence layers.
|
|
31
31
|
7. Commit with the issue reference and accurate attribution. For work assisted by DSH use `Assisted-by: DeepSeek Harness (DSH)`. Other agents must name the actual tool; do not infer authorship from the model vendor or copy a bot identity. Add `Co-authored-by` only for real verified collaborators. No fabricated email, author replacement or published-history rewrite.
|
|
32
|
-
8. Push the feature branch and open a PR containing `Fixes #<issue>`, verification, risks and rollback. For user-requested delivery, merge without an additional approval prompt after required review/CI and branch protection; respect explicit code-only, review-only or do-not-merge restrictions.
|
|
32
|
+
8. Push the feature branch and open a PR containing `Fixes #<issue>`, verification, risks and rollback. For runtime, tooling, release-metadata, workflow or agent-contract changes, fill the PR's **Documentation impact** section with `Behavior: user-facing` or `Behavior: unchanged` and an explanation. User-facing changes must list substantively changed `README.md`, `README.zh.md` and a relevant `docs/*.md`; version-only updates are insufficient. The CI gate rechecks body edits and only checks structure/file differences, not whether the assessment is true or complete. An agent or human reviewer must check affected behavior and evidence against all relevant docs and record findings in the PR; this adds no human-only approval gate. For user-requested delivery, merge without an additional approval prompt after actual required review/CI and branch protection; respect explicit code-only, review-only or do-not-merge restrictions.
|
|
33
33
|
|
|
34
34
|
Generated `lib/` output, archives, `.env`, tokens, local credentials, machine state and production screenshots with real authorization codes must not be committed. Use synthetic fixtures for screenshots and report staged UI honestly.
|
|
35
35
|
|
package/README.md
CHANGED
|
@@ -50,6 +50,11 @@ confirm that the exact version has passed the required gates and its Release
|
|
|
50
50
|
and npm artifacts are available. Published, installed, and loaded states are
|
|
51
51
|
distinct.
|
|
52
52
|
|
|
53
|
+
Plugin `0.1.0-alpha.14.dsh.0.2.2.rc.3` passed the Windows/Linux source and
|
|
54
|
+
published-artifact [CI](https://github.com/cloga/dsh-github-copilot/actions/runs/43691055529)
|
|
55
|
+
and was published to GitHub Releases and npm. This does not verify Desktop
|
|
56
|
+
artifacts, installation, loaded state or live supplier calls.
|
|
57
|
+
|
|
53
58
|
Use the read-only exact-Core selector from a verified source checkout to check
|
|
54
59
|
the release mapping:
|
|
55
60
|
|
|
@@ -57,8 +62,9 @@ the release mapping:
|
|
|
57
62
|
node scripts/select-core-release.mjs 0.2.2-rc.3
|
|
58
63
|
```
|
|
59
64
|
|
|
60
|
-
|
|
61
|
-
|
|
65
|
+
The selector checks Release/npm metadata and named assets; it does not run CI,
|
|
66
|
+
hash downloaded bytes, or verify a loaded Desktop. Check those separately before
|
|
67
|
+
recommending installation. See [release selection and distribution](./docs/npm-distribution.md)
|
|
62
68
|
and the [model compatibility acceptance criteria](./docs/model-compatibility-acceptance.md).
|
|
63
69
|
|
|
64
70
|
## Use
|
|
@@ -67,15 +73,15 @@ After the exact compatible release is available and verified, download its
|
|
|
67
73
|
original asset and checksum in an empty directory:
|
|
68
74
|
|
|
69
75
|
```sh
|
|
70
|
-
curl -fLO https://github.com/cloga/dsh-github-copilot/releases/download/v0.1.0-alpha.
|
|
71
|
-
curl -fLO https://github.com/cloga/dsh-github-copilot/releases/download/v0.1.0-alpha.
|
|
76
|
+
curl -fLO https://github.com/cloga/dsh-github-copilot/releases/download/v0.1.0-alpha.16.dsh.0.2.2.rc.3/dsh-github-copilot-0.1.0-alpha.16.dsh.0.2.2.rc.3.tgz
|
|
77
|
+
curl -fLO https://github.com/cloga/dsh-github-copilot/releases/download/v0.1.0-alpha.16.dsh.0.2.2.rc.3/SHA256SUMS
|
|
72
78
|
sha256sum --check SHA256SUMS
|
|
73
79
|
```
|
|
74
80
|
|
|
75
81
|
For the `web` profile, install the same Release asset:
|
|
76
82
|
|
|
77
83
|
```sh
|
|
78
|
-
dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.1.0-alpha.
|
|
84
|
+
dsh plugin --profile web add https://github.com/cloga/dsh-github-copilot/releases/download/v0.1.0-alpha.16.dsh.0.2.2.rc.3/dsh-github-copilot-0.1.0-alpha.16.dsh.0.2.2.rc.3.tgz
|
|
79
85
|
```
|
|
80
86
|
|
|
81
87
|
Choose the intended profile explicitly. Then:
|
|
@@ -147,8 +153,8 @@ another model. Each search makes one fixed capability probe and, only after
|
|
|
147
153
|
proof, one user query; both may incur charges.
|
|
148
154
|
Custom endpoint, credential or transport overrides and unproven models remain
|
|
149
155
|
unavailable. There is no model retry, backend replacement or plugin routing UI.
|
|
150
|
-
|
|
151
|
-
`temperature`; ordinary Chat and native allow/deny/error/cancel behavior remain
|
|
156
|
+
When qualification succeeds, the native Auto reviewer's Copilot Responses requests
|
|
157
|
+
omit `temperature`; ordinary Chat and native allow/deny/error/cancel behavior remain
|
|
152
158
|
unchanged. Qualification uses the native adapter's pi-ai catalog even when
|
|
153
159
|
the plugin resolves a separate copy; missing protocol facts remain unavailable.
|
|
154
160
|
Native schema-default empty `chatTemplateKwargs`/`chatTemplateArgs` maps and a
|
|
@@ -157,10 +163,24 @@ configuration. Other compatibility overrides remain unqualified. No settings
|
|
|
157
163
|
rewrite is needed to remove schema defaults; do not disable review or search
|
|
158
164
|
proof as a workaround. CI acceptance and live Desktop activation are separate.
|
|
159
165
|
See [reviewer compatibility](./docs/auto-review-sampling.md).
|
|
166
|
+
|
|
167
|
+
Plugin releases through alpha.12 can reject DSH's schema-default compatibility
|
|
168
|
+
maps and disable both enhancements ([#483](https://github.com/cloga/dsh-github-copilot/issues/483)).
|
|
169
|
+
The alpha.13 release fixes that qualification; live runtime behavior still
|
|
170
|
+
requires separate verification. Registration or model metadata alone proves
|
|
171
|
+
neither works.
|
|
172
|
+
|
|
160
173
|
The native route's quota and optional identity display use only the canonical OAuth account. If the
|
|
161
174
|
provider names a credential, endpoint or nonempty headers override, or its configuration
|
|
162
175
|
cannot be verified, quota is shown as unavailable rather than attributed to a
|
|
163
176
|
different account. This is not proof of request-level billing attribution.
|
|
177
|
+
Completed-turn Account evidence is also captured for the native provider, but
|
|
178
|
+
only after an actual native stream chunk for that admitted request. It reflects
|
|
179
|
+
the profile-wide account bound to the canonical credential, not a Session
|
|
180
|
+
override, billing attribution or subagent rollup. A mismatched account,
|
|
181
|
+
unproven native route or credential change before delivery leaves it unknown.
|
|
182
|
+
Evidence is Host-memory-only;
|
|
183
|
+
older turns and turns missing after a restart or eviction remain unknown.
|
|
164
184
|
Native context-incident diagnostics remain available without the optional
|
|
165
185
|
managed continuation service; they do not replace DSH's context meter.
|
|
166
186
|
Local diagnostics also offers separately opt-in, content-free logical
|
|
@@ -168,6 +188,18 @@ observations for native Copilot streams and the optional Copilot search backend.
|
|
|
168
188
|
They do not expose HTTP details or prove supplier receipt or execution.
|
|
169
189
|
See [local diagnostics](./docs/plugin-diagnostics.md).
|
|
170
190
|
|
|
191
|
+
### Other optional capabilities
|
|
192
|
+
|
|
193
|
+
- On the managed route, Credits can select an already saved account for a
|
|
194
|
+
Session's subsequent turns. [Visible-history continuation](./docs/session-continuation.md)
|
|
195
|
+
is a disclosed, lossy Responses policy; existing Sessions are not silently
|
|
196
|
+
enrolled, and enabling it never sends or retries a message.
|
|
197
|
+
- [Segmented compaction recovery](./docs/manual-compaction-recovery.md) requires
|
|
198
|
+
explicit engine selection; installing the plugin does not replace Core's engine.
|
|
199
|
+
- [Local diagnostics](./docs/plugin-diagnostics.md) and managed Responses gzip
|
|
200
|
+
are default-off; enabling diagnostics does not upload data. GitHub Enterprise
|
|
201
|
+
Cloud tenant login is supported, while GHES and Enterprise quota are not.
|
|
202
|
+
|
|
171
203
|
### Removing the enhancement
|
|
172
204
|
|
|
173
205
|
Unloading the plugin removes its own routes, UI and listeners, not native
|
|
@@ -202,6 +234,11 @@ The exact development target is in `deployment-baseline.json`; follow
|
|
|
202
234
|
and package/release gates run in GitHub Actions. A successful local source
|
|
203
235
|
check, synthetic fixture, release publication, profile installation, and loaded
|
|
204
236
|
Desktop runtime are different evidence layers; report each accurately.
|
|
237
|
+
The optional [offline autonomy evaluator](./docs/agent-autonomy-evaluation.md)
|
|
238
|
+
analyzes explicitly supplied sanitized traces; it does not run or control agents.
|
|
239
|
+
PRs declare documentation impact; agent or human reviewers still verify semantic
|
|
240
|
+
accuracy and coverage. This adds no human-only approval gate. See
|
|
241
|
+
[contributing](./CONTRIBUTING.md#change-workflow).
|
|
205
242
|
Commit attribution must use an `Assisted-by` trailer for the actual assisting
|
|
206
243
|
tool; do not invent a co-author identity.
|
|
207
244
|
|