@plumbus/core 0.7.3 → 0.7.5

package/CHANGELOG.md

@@ -1,13 +1,21 @@
 # @plumbus/core changelog
 
-## 0.7.3 — Unreleased
+## 0.7.5 — 2026-09-24
+
+- Fix GPT-6 OpenAI request compatibility: Chat Completions use `max_completion_tokens`, active/default reasoning omits unsupported sampling temperature, and tool calls with GPT-6 default reasoning use the Responses API. Explicitly disabled reasoning stays on Chat Completions and retains configured temperature.
+
+## 0.7.4 — 2026-09-23
+
+- Bump agent wiring to v17 and add a packaged classification recipe covering explicit provider/model selection, defaults, thresholds, and cost recording. All agent formats link the recipe and decision provider instruction indexes; refresh existing apps with `plumbus init --patch --agent all`.
+
+- Let `ctx.ai.classify()` select a registered text or decision provider with optional `provider`/`model`. TypeSafe/Laya classification batches probability questions and returns labels meeting `threshold` (default 0.5), sharing decision validation, security, budgets, cancellation, and one `classify` cost record. Existing calls keep their generative default.
 
 - Audit 20 decision integration failure scenarios with 30 unit/integration/real-HTTP regression cases. Snapshot billing context and isolate ledger observers from caller results. Share one cost-record ID/timestamp between the tracker and persistence hook.
 
 - Add `ctx.ai.decide()` over the shared decision contract, with per-call cost/usage records, tenant/actor attribution, named definitions, security checks over state and questions, budgets, and cancellation forwarding.
 - Wire explicit `app/server.ts` decision registration and `app/decisions/` discovery into API and workers. Preserve decision feature flags through service wrappers and add decision responses to `mockAI`.
 - Reuse `onAICostRecorded` for successful and failed decision calls, preserving unknown cost as null and retaining known billed metadata after invalid provider answers.
-- Depend on `@plumbus/ai-decision@~0.2.1`; vendor adapters remain optional. Keep typecheck fixtures out of production compilation.
+- Depend on `@plumbus/ai-decision@~0.2.2`; vendor adapters remain optional. Keep typecheck fixtures out of production compilation.
 
 ## 0.7.2 — 2026-09-23
 

package/README.md

@@ -1,6 +1,6 @@
 # @plumbus/core
 
-Release notes: [changelog](./CHANGELOG.md) and [version/upgrade guide](../../docs/upgrading-voice-and-decision-release.md).
+Release notes: [changelog](./CHANGELOG.md) and [version/upgrade guide](../../docs/upgrading-classification.md).
 
 **AI-native, contract-driven TypeScript application framework.**
 
@@ -152,6 +152,7 @@ node_modules/@plumbus/core/instructions/
 ├── flows.md                       # Workflow steps and retry logic
 ├── prompts.md                     # Prompt content, system/description, model config
 ├── ai.md                          # ctx.ai operations, RAG, cost tracking
+├── ai-classification.md           # Provider/model selection, TypeSafe/Jev, Laya
 ├── translations.md                # i18n catalogs and ctx.translations
 ├── security.md                    # Access policies and tenant isolation
 ├── governance.md                  # Advisory rules and compliance
@@ -165,7 +166,9 @@ node_modules/@plumbus/core/instructions/
 └── upgrading-0.5-capabilities.md  # 0.5.x capability invocation migration
 ```
 
-Wire them up with `plumbus init --agent all`.
+Wire them up with `plumbus init --agent all`. After upgrading to core 0.7.4+, run
+`plumbus init --patch --agent all` for wiring v17. For classification, provider/model
+selection, or TypeSafe/Jev and Laya, start with [the classification recipe](instructions/ai-classification.md).
 
 ## Documentation