@plumbus/ai-decision-typesafe 0.2.3 → 0.3.0-beta.1

package/instructions/README.md

@@ -7,9 +7,9 @@
 
 **Classification, categorization, provider/model selection, TypeSafe/Jev or Laya:**
 read `node_modules/@plumbus/core/instructions/ai-classification.md` first (core
-**0.7.4+**), then [framework.md](framework.md) for this package.
+**0.8.0-beta.6+**), then [framework.md](framework.md) for this package.
 
-Core 0.7.3+ provides `ctx.ai.decide()`; core 0.7.4+ also routes `ctx.ai.classify()`
+Core 0.8.0-beta.6+ provides `ctx.ai.decide()` and also routes `ctx.ai.classify()`
 to explicitly registered decision adapters. Keep app business logic in Plumbus
 primitives and `ctx.*`. Never route predictions around capability access checks
 or confirmation policy. Provider registration is explicit in `app/server.ts`.

package/instructions/framework.md

@@ -4,7 +4,7 @@ TypeSafe/Jev provider for typed choices, scores, and probabilities.
 
 ## Install and ownership
 
-Install `@plumbus/ai-decision-typesafe` explicitly. Its core peer is exactly `"0.7.x"`.
+Install `@plumbus/ai-decision-typesafe` explicitly. Its core peer is exactly `">=0.8.0-beta.0 <0.9.0"` (core 0.8 beta family).
 Consumers reuse Zod/testing utilities from core; do not install them separately.
 Use this package for bounded typed decisions. Use core generation and embeddings
 for text responses and vector inference.
@@ -14,7 +14,7 @@ Public exports: `createTypeSafeDecisionAdapter` — construct an explicitly conf
 File map: `src/index.ts` is the public barrel, `src/__tests__/` exercises the public
 API, `instructions/` contains these recipes. Laya alone also ships `service/`.
 
-## Classification and model selection (core 0.7.4+)
+## Classification and model selection (core 0.8.0-beta.6+)
 
 Read `node_modules/@plumbus/core/instructions/ai-classification.md` for the complete
 registration and usage recipe. Call `ctx.ai.classify({ text, labels, provider, model,
@@ -45,7 +45,7 @@ console.log(result.answers.refund.probability);
 1. Keep capabilities, flows, access policy and `ctx.*` as the application implementation path.
 2. Construct adapters at a server-owned infrastructure boundary and inject them. Keep keys on the server.
 3. Treat direct adapter usage as protocol integration, not a replacement for core's security/budget/audit lifecycle.
-4. With core 0.7.3+, use `ctx.ai.decide()` in capabilities/flows. Export `decisions = { providers, defaultProvider }` from `app/server.ts`; API and workers share it. Do not register decision adapters as completion providers.
+4. With core 0.8.0-beta.6+, use `ctx.ai.decide()` in capabilities/flows. Export `decisions = { providers, defaultProvider }` from `app/server.ts`; API and workers share it. Do not register decision adapters as completion providers.
 5. Preserve distributions and provider confidence separately. A high confidence value is not authorization or proof of correctness.
 6. Validate thresholds on the actual task/model/language. Unknown cost is `null`, not free.
 7. Pass `signal: ctx.signal` and `timeoutMs` where needed. Flow steps supply their signal by default.

package/instructions/testing.md

@@ -18,12 +18,12 @@ Validate choices, scores, probabilities, actual model/routing, usage and unknown
 cost handling. Measure live accuracy and calibration separately from connection
 success. Do not assert a universal confidence cutoff or guaranteed live label.
 
-For core 0.7.4+ classification, use `mockAI({ classify: ['billing'] })` and test
+For core 0.8.0-beta.6+ classification, use `mockAI({ classify: ['billing'] })` and test
 through `runCapability()` / `simulateFlow()`. Integration tests should assert
 provider/model forwarding, zero/multiple matches, inclusive thresholds, and one
 `classify` cost row. Use injected fetch; routine tests do not require live Laya.
 
-For core 0.7.3+ integration tests, configure `mockAI({ decide: result })` or a real
+For core 0.8.0-beta.6+ integration tests, configure `mockAI({ decide: result })` or a real
 `createAIService({ decisions, costTracker, onAICostRecorded })` with injected
 provider fetch. Assert exactly one cost row, identity, actual model/usage, unknown
 cost handling, billed validation failures, and budget rejection before dispatch.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@plumbus/ai-decision-typesafe",
-  "version": "0.2.3",
+  "version": "0.3.0-beta.1",
   "description": "TypeSafe/Jev typed decision provider adapter for Plumbus.",
   "type": "module",
   "main": "./dist/index.js",
@@ -35,17 +35,17 @@
     "node": ">=20.6.0"
   },
   "peerDependencies": {
-    "@plumbus/core": "0.7.x"
+    "@plumbus/core": ">=0.8.0-beta.0 <0.9.0"
   },
   "devDependencies": {
     "@biomejs/biome": "^2.4.6",
     "@types/node": "^25.4.0",
     "typescript": "^5.7.0",
     "vitest": "^3.2.4",
-    "@plumbus/core": "0.7.9"
+    "@plumbus/core": "0.8.0-beta.10"
   },
   "dependencies": {
-    "@plumbus/ai-decision": "~0.2.3"
+    "@plumbus/ai-decision": "~0.3.0-beta.1"
   },
   "scripts": {
     "build": "tsc -b",