@plumbus/ai-bedrock 0.3.0-beta.0 → 0.3.0

package/CHANGELOG.md

@@ -1,10 +1,23 @@
 # @plumbus/ai-bedrock
 
-## 0.3.0-beta.0 — 2026-09-11 — core 0.8 beta family
+## 0.3.0 — Stabilization compatibility family
 
-### Upgrade boundary
+- Upgrade the framework test toolchain to **Vitest 5.0.4** and require Node 22.12+ on the 22.x line, Node 24.x, or Node 26+.
+
+Requires the coordinated core 0.8 family. Follow the [stabilization upgrade guide](../../docs/upgrading-stabilization.md) and the installed `node_modules/@plumbus/core/instructions/stabilization.md`; update installed Plumbus packages together.
+
+- Update Plumbus peers to `@plumbus/core` `0.8.x`. This minor line makes the compatibility change an explicit upgrade.
+- Refresh package instructions and compatibility guidance for core 0.8 and agent wiring v21. Runtime APIs in this add-on are unchanged.
+
+## 0.2.2 — 2026-10-08
+
+### Added
+
+- Prompt caching on Converse / ConverseStream (#63). When a request sets `cache` (core 0.7.9+ passes it from `ctx.ai`, `runToolLoop`, and `AI_PROMPT_CACHE`), the adapter appends `cachePoint` after the system text, at the end of `toolConfig.tools`, and on the last message when requested. Only Claude model ids get marks, with or without an inference-profile prefix (`us.`, `jp.`, `us-gov.`, …); a model ARN gets none. Claude 3 Haiku, Claude 3 Sonnet, Claude 3 Opus, and Claude 3.5 Sonnet `20240620` get no marks because Bedrock rejects `cachePoint` for them with a ValidationException, and neither does Claude 3.5 Sonnet v2 (`20241022`), whose explicit caching AWS lists as Preview; other model families get none either, so those requests still succeed.
+
+### Compatibility
 
-- Beta prerelease of the coordinated core 0.8 family (core 0.8.x, UI 0.9.x, MCP 0.7.x, voice 0.6.x, other add-ons 0.3.x), published under the branch-named npm dist-tag `plumbus-next` (`latest` stays on the 0.7 family). Previous caret ranges exclude it; install the whole family together and follow the [0.8 upgrade notes](../../docs/upgrading-core-0.8.md). Internal peers use prerelease-inclusive ranges (for example `>=0.8.0-beta.0 <0.9.0`) until the family goes stable.
+- Loads and runs on any core 0.7.x. The `cache` option is resolved inside this package, which imports nothing from `@plumbus/core` that 0.7.0 lacks. On cores before 0.7.9, `ctx.ai` never sets `cache`, so requests are unchanged. The peer range stays `0.7.x`.
 
 ## 0.2.1 — 2026-09-10
 

package/README.md

@@ -1,5 +1,7 @@
 # @plumbus/ai-bedrock
 
+Release **0.3.0** belongs to the core 0.8 stabilization family. See the [changelog](./CHANGELOG.md) and [upgrade guide](../../docs/upgrading-stabilization.md) before updating an existing app.
+
 > **Amazon Bedrock for [Plumbus](https://github.com/plumbus-framework/plumbus) AI.** Optional AWS SDK adapter for Converse chat, ConverseStream, Titan embeddings, and **package-owned USD cost** from the AWS Price List (or a mounted pricing file).
 
 [![npm](https://img.shields.io/npm/v/@plumbus/ai-bedrock.svg)](https://www.npmjs.com/package/@plumbus/ai-bedrock)
@@ -46,7 +48,7 @@ An opt-in peer keeps core lean while giving AWS shops a first-class `provider: '
 
 ## Status
 
-Optional peer of `@plumbus/core` (version-locked **`0.2.x`**; required peer `@plumbus/core` **`0.8.x`**). **Runtime floor:** `@plumbus/core` **≥ 0.6.16** (Bedrock provider slot, env discovery, adapter-supplied `cost`, agent wiring v13). Install alone is not enough until the adapter is registered (env discovery or `createBedrockAdapter`).
+Optional peer of `@plumbus/core` (version-locked **`0.3.x`**; required peer `@plumbus/core` **`0.8.x`**). **Runtime floor:** `@plumbus/core` **≥ 0.7.0**; prompt caching through `ctx.ai` needs **≥ 0.7.9**. Install alone is not enough until the adapter is registered (env discovery or `createBedrockAdapter`).
 
 ## Install
 
@@ -129,11 +131,12 @@ Full curl, normalize script, ConfigMap sketch: **[instructions/pricing.md](./ins
 - **Model access** — Converse fails with `AccessDenied` until the account enables the model (and Anthropic use-case forms where required).
 - **Embeddings** — Converse does not embed; use InvokeModel (Titan) via `createRAGPipeline({ provider })` + `ctx.ai.retrieve` / `ragPipeline.ingest`. There is no `ctx.ai.embed`. `plumbus rag ingest` does not auto-select Bedrock. Mantle typically has no embeddings.
 - **Tools** — use `runToolLoop` / `generateWithUsage({ tools })`; do not call the Bedrock SDK. Stream accumulates partial tool JSON. Parallel tool results are coalesced into the single user turn Converse requires.
+- **Prompt caching** — set `cache` on `ctx.ai.*` / `runToolLoop`, or `AI_PROMPT_CACHE=true` (core ≥ 0.7.9). Claude models get Converse `cachePoint` marks, except Claude 3 Haiku / Sonnet / Opus and Claude 3.5 Sonnet `20240620`, which reject them, and Claude 3.5 Sonnet v2 (Preview-only on Bedrock); other families get none.
 - **`toolChoice: 'none'`** — Bedrock has no true none; Plumbus omits `toolConfig` entirely. `'auto'` omits just the `toolChoice` field (model-dependent support).
 - **Missing pricing file** — file mode throws on first call; auto-download failure warns, leaves cost unknown, and backs off 5 minutes before retrying.
 - **Unmapped / unkeyed models** — inference works; **no `cost` field** is set until the pricing file has an explicit family-key row (auto-download is best-effort, not a complete AWS catalog). Core then falls back to its own catalog rather than recording the call as free.
 - **IAM** — Converse itself requires `bedrock:InvokeModel`; do not scope that action to embedding models only.
-- **Wiring** — after install, `plumbus init --patch` (core ≥ 0.6.16 / wiring v13) so agents see `instructions/`.
+- **Wiring** — after install, `plumbus init --patch` (wiring v13+, any core 0.8.x) so agents see `instructions/`.
 
 ## Documentation / Agent recipes