dsh-github-copilot 0.4.0-alpha.87 → 0.4.0-alpha.91

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
@@ -68,6 +68,7 @@ Alpha.25 admits native `subagent/descriptor` v3, already v3 in the retained rc.1
68
68
  - `src/responses-reasoning.ts`, `src/responses-reasoning-text.ts`: selected-model effort mapping and public summary assembly.
69
69
  - `src/tool-schema-compat.ts`: Copilot-only prompt-assembly filter for unusable escalation arguments and action-specific Goal update schemas.
70
70
  - `src/plan.ts`: Copilot-only, fail-closed hosted-search candidate lifecycle.
71
+ - `src/auto-assessment-evidence.ts`: bounded request-local semantic classifier milestones copied into strict ephemeral turn evidence; no prompts, replay, credentials or error bodies. Total includes preparation; adapter start and first text are not HTTP dispatch/byte timings. Keep one 8s deadline and 128-token compact output. Request reasoning-off only when supplier and public prepared-model effort agree; unsupported native controls stay unchanged. No guessed latency ranking, adaptive timeout, cooldown or cross-turn cache without reviewed observations.
71
72
  - `src/probe.ts`: bounded native-search capability proof.
72
73
  - `src/wire.ts`, `src/wire-anthropic.ts`: inline hosted-search streaming.
73
74
  - `src/traditional-search.ts`: `github-copilot-hosted` `ctx.web` provider.
@@ -265,6 +266,8 @@ reachability. Preserve native Agent lookup and bounded store ownership (#254).
265
266
 
266
267
  Automatic pressure and Auto recovery availability resolve the initiating Agent's bound preset through public `agentPresets.composedPreset()` / `serviceFor(agent, 'compaction')`. A bound preset without an engine must not borrow global recovery. Only non-preset Agents use their own `agent.ctx.get('compaction')`; never scan Core's private registry or cache an engine across preset replacement. Native transactions, cancellation, retry policy and manual-only segmented recovery remain unchanged.
267
268
 
269
+ Continuing-step pressure prevention uses public `agent/pre-step` before `step/start`, only with a committed managed header, no selection notice, and known `modelSelection.pending: null`. Capacity lookup is not request estimation. Use the native surface meter and one currently bound native transaction; preserve final converted hard admission and stream-pressure fallback. First-step/pending/unknown evidence delegates. Native compaction failures propagate before attempt admission. Never claim all missing turn Usage is repaired, filter native samples, invent zero usage or rewrite historical totals. Native turn-tail accounting groups events by recorded turn, not compaction replacement sequence range.
270
+
268
271
  Selection footer Remote calls carry an explicit viewed Session ID and turn.
269
272
  Do not add an automatic Client `scope` projection: rc.2 prefers the scoped
270
273
  variant and removes the ID argument, breaking the footer's two-argument call.
package/CHANGELOG.md CHANGED
@@ -1,5 +1,17 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.4.0-alpha.91 (prepared)
4
+
5
+ - Prevent known continuing-step managed input pressure before native model-attempt admission through the public `agent/pre-step` seam (#280), using the initiating Agent's current compaction service and one native transaction.
6
+ - Require a committed owned route and a proven absent pending model change. Respect disabled auto, overflow policy, cancellation and native failures; retain final converted admission and stream-pressure fallback.
7
+ - Prove the before/after accounting boundary with the unchanged rc.2 AgentLoop: successful early reduction removes the unsampled pressure attempt and preserves complete native two-step Usage. First-step/pending selections, new prefix growth and final hard refusals remain limitations; no historical totals, usage samples, retry counters or model selections are rewritten.
8
+
9
+ ## 0.4.0-alpha.88 (prepared)
10
+
11
+ - Capture bounded classifier model, total elapsed/budget, adapter-start, first-text, native finish and validation milestones in immutable ephemeral Auto turn evidence (#272). No prompts, raw outputs, credentials, replay or usage are recorded.
12
+ - Reduce auxiliary classification to 128 output tokens with compact demand/fixed-signal JSON. Request off reasoning only when supplier metadata and the published prepared-model capabilities agree; unsupported controls retain native policy.
13
+ - Explain semantic timeout as unknown-demand preference fallback and expose auxiliary milestones inside the existing bilingual disclosure. Preserve the 8s end-to-end deadline, cancellation/revocation, omitted-context guards and single attempt; no longer timeout, retries, guessed model-health ranking or measured improvement claim.
14
+
3
15
  ## 0.4.0-alpha.87 (prepared)
4
16
 
5
17
  - Remove managed terminal-zero usage filtering so native failure/cancellation samples remain available to Core's shared turn and cumulative accounting (#270).