@plumbus/ai-decision-laya 0.2.1 → 0.2.3

package/instructions/README.md

@@ -5,8 +5,13 @@
 | [framework.md](framework.md) | Installation, public exports, adapter boundary, usage rules |
 | [testing.md](testing.md) | Offline validation and live environment setup |
 
-Keep app business logic in Plumbus primitives and `ctx.*`. These packages do not
-add `ctx.ai.decide()` or automatic provider discovery yet. Never route model
-predictions directly around capability access checks or confirmation policy.
+**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.
+
+Core 0.7.3+ provides `ctx.ai.decide()`; core 0.7.4+ 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 README](../README.md) · [Monorepo guide](https://github.com/plumbus-framework/plumbus/blob/main/docs/ai/decision-providers.md)

package/instructions/framework.md

@@ -14,7 +14,19 @@ Public exports: `createLayaDecisionAdapter` — construct an explicitly configur
 File map: `src/index.ts` is the public barrel, `src/__tests__/` exercises the public
 API, `instructions/` contains these recipes. Laya alone also ships `service/`.
 
-## Minimal usage
+## Classification and model selection (core 0.7.4+)
+
+Read `node_modules/@plumbus/core/instructions/ai-classification.md` for the complete
+registration and usage recipe. Call `ctx.ai.classify({ text, labels, provider, model,
+threshold })` inside capabilities/flows. `provider` is your registered decision map
+key; `model` is an optional endpoint-supported ID. Native `threshold` defaults to
+0.5 and returns all matching labels. Use `decide()` for richer questions.
+
+Core records one `classify` cost row, including dispatched failures, with actual
+model/usage and identity. Omitted `provider` still uses the text default. Keep
+decision adapters under `decisions.providers`, separate from text providers.
+
+## Minimal usage (infrastructure / smoke testing)
 
 ```ts
 import { createLayaDecisionAdapter } from '@plumbus/ai-decision-laya';

package/instructions/testing.md

@@ -18,6 +18,11 @@ 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
+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
 `createAIService({ decisions, costTracker, onAICostRecorded })` with injected
 provider fetch. Assert exactly one cost row, identity, actual model/usage, unknown

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@plumbus/ai-decision-laya",
-  "version": "0.2.1",
+  "version": "0.2.3",
   "description": "Self-hosted Laya typed decision adapter and Python reference service for Plumbus.",
   "type": "module",
   "main": "./dist/index.js",
@@ -43,10 +43,10 @@
     "@types/node": "^25.4.0",
     "typescript": "^5.7.0",
     "vitest": "^3.2.4",
-    "@plumbus/core": "0.7.3"
+    "@plumbus/core": "0.7.9"
   },
   "dependencies": {
-    "@plumbus/ai-decision": "~0.2.1"
+    "@plumbus/ai-decision": "~0.2.3"
   },
   "scripts": {
     "build": "tsc -b",

package/service/test_audit_round_two.py

@@ -108,7 +108,14 @@ class ServiceRoundTwo(unittest.TestCase):
         first.start()
         try:
             self.assertTrue(entered.wait(1))
-            self.assertEqual(self.send(address=server.server_address)[0], 503)
+            # Capacity is rejected before request bytes are read. Sending a body
+            # here races the server closing the rejected connection.
+            with socket.create_connection(server.server_address, timeout=2) as rejected:
+                response = http.client.HTTPResponse(rejected)
+                response.begin()
+                self.assertEqual(response.status, 503)
+                self.assertEqual(response.getheader("Retry-After"), "1")
+                self.assertEqual(json.loads(response.read()), {"error": "Service connection capacity reached"})
             finish.set()
             first.join(2)
             self.assertEqual(results, [200])