@awak-app/simy-cli 0.6.23 → 0.6.26

package/README.md

@@ -1,5 +1,7 @@
 # SIMY CLI
 
+ローカルDelivery Loopの0.6.24候補を版固定で実行するには、[ローカル候補版のインストール・実行](docs/local-delivery-runtime.md)を参照してください。
+
 Local execution agent for SIMY Local Tasks and Agentic Loop runs.
 
 Action candidate search runs once for each authenticated live conversation context,
@@ -927,6 +929,19 @@ To-Be and PR reviews, plus explicitly opted-in SQM before and after PR creation.
 The [workflow reference](src/orchestrator/delivery/references/shared-system-specifications.md)
 explains baseline updates, historical regression coverage and evidence limits.
 
+## Purpose-driven automatic continuation
+
+The desktop **Continue automatically / 自動で続ける** switch enables purpose-driven
+search: hypotheses, research, experiments, minimal implementation and independent
+outcome review. Failed methods trigger replanning; review findings return to repair.
+Independent authorized work can continue while a controller-tracked operation waits.
+The existing Codex auto-continue switch enables read-only diagnosis for uncertain or
+information-waiting conversations, then assessed work. No default time/turn cap is
+added; explicitly enrolled purpose budgets and user stops are preserved. Native
+provider approval waits still require the original provider boundary to settle.
+Workflow rules are reassessed throughout. Turning the switch off pauses work.
+Actual permissions, user stops and total budgets remain enforced. See the
+[contract and limitations](docs/purpose-driven-continuation.md).
 
 ### Desktop SQM history
 
@@ -1009,3 +1024,41 @@ Scope mismatch diagnostics identify the changed account, organization, device
 or Web host and tell the caller to restore the original identity. Launch and
 recovery operations do not switch identity automatically. The private
 `/v1/connection` endpoint rejects browser requests and never returns tokens.
+
+自律判断の改定方針と人間判断候補の一覧: [AI判断を基本にする改定](docs/ai-decision-policy.md)。LLMの文脈理解・推論・調査を基本にし、HC-01〜HC-102を判断の批判視点として適用します。
+
+### Local autonomous recovery (0.6.25)
+
+`simy delivery runtime install` pins a hash-verified snapshot. `runtime desktop-install`
+prepares a separately signed **SIMY Local** app from the installed native app; the
+public application and installer selection remain unchanged. After the previous
+app has finished its normal quit, `runtime desktop-activate` launches that candidate.
+`runtime watchdog-install` installs a per-user macOS observer that may relaunch only
+that explicitly activated candidate when no live desktop owns the state directory.
+A live unknown/mismatched owner is preserved and reported. `runtime doctor` reports
+expected versus observed host identity, the all-state consistency monitor, and
+remaining task findings. `runtime legacy-hooks` routes only the exact shipped
+0.6.23/0.6.24 Codex hook entrypoints to the verified pin, retaining originals;
+customized hooks and trust settings remain unchanged. `runtime workflows` refreshes
+existing provider workflows without enabling them.
+
+For existing opted-in Codex tasks, the controller verifies original session, cwd,
+model, provider link and consent epoch before an idempotent policy migration.
+Frozen goal, criteria, grants, budgets and failure history are retained. Observable
+legacy manual criteria receive a separate independent verification route; explicit
+human/customer acceptance remains manual. Known system no-progress pauses queue
+read-only diagnosis before any replay. OFF, archive, explicit pause/stop, rejection,
+unknown effects and original budgets remain boundaries.
+
+The consistency monitor scans every managed state separately from the execution
+queue. Its independent AI reads original user instructions/corrections and primary
+evidence in a distinct read-only Codex context. Durable findings/outbox receipts,
+retry backoff, separate lease, measured token usage and failed/stale heartbeats are
+recorded; an audit receipt does not complete a task. SQM evidence stays bound to its
+repository/commit/diff scope and does not prove the whole user outcome. Git output
+no longer uses a 10 MiB `execFile` buffer; the full diff is still retained in memory.
+
+Codex cold recovery and independent audit are supported. Claude retains its
+original live-hook boundary; cold recovery and detached independent audit are not
+implemented in this release and are exposed as a capability gap. Neither an
+unverified original model nor a different provider is substituted automatically.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@awak-app/simy-cli",
-  "version": "0.6.23",
+  "version": "0.6.26",
   "description": "Local SIMY executor for non-coding Local Tasks and Agentic Loop runs.",
   "type": "module",
   "bin": {
@@ -12,7 +12,7 @@
   ],
   "scripts": {
     "start": "node ./src/index.js",
-    "test": "node --test",
+    "test": "node --test --test-concurrency=2",
     "test:e2e:console": "node ./scripts/console-e2e.js",
     "test:e2e:work-activity": "node ./scripts/work-activity-e2e.js",
     "test:e2e:sqm-complete-loop": "node ./scripts/sqm-complete-loop-e2e.js",
@@ -38,7 +38,7 @@
     "test:e2e:console:real-provider": "node ./scripts/real-provider-console-e2e.js",
     "test:e2e:console:fullstack": "node ./scripts/fullstack-cli-smoke.js",
     "check": "npm run check:auto-update && node --check ./src/desktop-executor.js && node --check ./src/local-task.js && node --check ./scripts/desktop-executor-e2e.js && node --check ./scripts/pre-guardrail-e2e.js && node --check ./scripts/fixtures/fake-desktop-provider.js && npm run check:syntax && npm run check:session-supervision-syntax && npm run check:real-provider-syntax && npm test && npm run check:package",
-    "check:session-supervision-syntax": "node --check ./src/session-supervision/index.js && node --check ./src/session-supervision/discovery-window.js && node --check ./src/session-supervision/codex-app-server.js && node --check ./src/session-supervision/claude-sessions.js && node --check ./src/session-supervision/original-session-target.js && node --check ./src/session-supervision/action-association.js && node --check ./src/session-supervision/action-association-host.js && node --check ./src/session-supervision/action-association-api.js && node --check ./src/session-supervision/association-store.js && node --check ./src/session-supervision/action-deadline.js && node --check ./src/session-supervision/action-deadline-store.js && node --check ./src/codex-plugins/simy/hooks/action-association.mjs",
+    "check:session-supervision-syntax": "node --check ./src/session-supervision/index.js && node --check ./src/session-supervision/discovery-window.js && node --check ./src/session-supervision/codex-app-server.js && node --check ./src/session-supervision/claude-sessions.js && node --check ./src/session-supervision/original-session-target.js && node --check ./src/session-supervision/action-association.js && node --check ./src/session-supervision/action-association-host.js && node --check ./src/session-supervision/action-association-api.js && node --check ./src/session-supervision/association-store.js && node --check ./src/session-supervision/action-deadline.js && node --check ./src/session-supervision/action-deadline-store.js && node --check ./src/codex-plugins/simy/hooks/action-association.mjs && node --check ./src/session-supervision/purpose-instruction.js && node --check ./src/session-supervision/purpose-recovery.js && node --check ./src/session-supervision/purpose-candidate.js && node --check ./src/codex-plugins/simy/hooks/purpose-cycle.mjs && node --check ./src/codex-plugins/simy/hooks/purpose-rule-review.mjs && node --check ./src/codex-plugins/simy/hooks/purpose-search.mjs && node --check ./src/codex-plugins/simy/hooks/purpose-evidence.mjs && node --check ./src/session-supervision/purpose-observer.js && node --check ./src/session-supervision/purpose-verification.js && node --check ./src/codex-plugins/simy/hooks/purpose-workspace.mjs && node --check ./scripts/purpose-search-live-e2e.js",
     "check:auto-update": "node --check ./src/auto-update.js && node --check ./scripts/auto-update-e2e.js && npm run check:sqm",
     "check:workflow-observation-sender": "node --check ./src/workflow-observation-sender.js",
     "check:sqm": "node --check ./src/sqm/canonical.js && node --check ./src/sqm/validation.js && node --check ./src/sqm/reliability.js && node --check ./src/sqm/repository.js && node --check ./src/sqm/checkers.js && node --check ./src/sqm/bundle-store.js && node --check ./src/sqm/proof.js && node --check ./src/sqm/evidence-client.js && node --check ./src/sqm/session.js && node --check ./src/sqm/index.js && node --check ./src/sqm/command.js && node --check ./src/sqm/agent-skill.js && node --check ./src/sqm/workflow-onboarding.js && node --check ./src/sqm/workflow-update.js && node --check ./src/sqm/history-store.js && node --check ./src/sqm/review-worker.js && node --check ./scripts/sqm-complete-loop-e2e.js && node --check ./scripts/sqm-local-review-e2e.js",

package/src/cli-contract.js

@@ -13,9 +13,16 @@ import {
 } from "./durable-local-task-steps-contract.js";
 import { buildExecutionCapabilityContract } from "./execution-capability-contract.js";
 
-export const CLI_VERSION = "0.6.23";
+export const CLI_VERSION = "0.6.26";
 export const CLI_API_CONTRACT_VERSION = 10;
 
+export function narrativeImageCapabilityMetadata() {
+  return {
+    schema_version: "fp_narrative_image.v1",
+    receipt_schema_version: "fp_native_image_receipt.v1",
+  };
+}
+
 export function withCliContract(
   capabilities = {},
   installMode = null,
@@ -25,6 +32,7 @@ export function withCliContract(
     ...capabilities,
     cli_version: CLI_VERSION,
     api_contract_version: CLI_API_CONTRACT_VERSION,
+    fp_narrative_image: narrativeImageCapabilityMetadata(),
     local_task_file_capabilities: localTaskFileCapabilityMetadata(),
     local_task_scenario_packs: localTaskScenarioPackMetadata(),
     bounded_local_task_subtasks:

package/src/codex-plugins/simy/hooks/acceptance-policy.mjs

@@ -0,0 +1,5 @@
+// Frozen manual acceptance is an explicit enrollment boundary. Its description
+// or an old auto-continue switch cannot authorize a different verifier.
+export function effectiveAcceptanceCriteria(managed) {
+  return managed?.acceptanceCriteria || [];
+}