@codemation/core-nodes 0.4.3 → 1.0.1

package/CHANGELOG.md

@@ -1,5 +1,72 @@
 # @codemation/core-nodes
 
+## 1.0.1
+
+### Patch Changes
+
+- [#95](https://github.com/MadeRelevant/codemation/pull/95) [`328c975`](https://github.com/MadeRelevant/codemation/commit/328c9759d45b711c177ea9a360ed4960ffdf5ffa) Thanks [@cblokland90](https://github.com/cblokland90)! - Workflow-canvas icon system redesign: LTR-oriented control-flow icons, pixel-perfect Split / Aggregate SVGs, and a single icon renderer shared by the canvas and the execution tree panel.
+
+  **Why**
+
+  The canvas reads left-to-right, but Lucide's `split`, `merge`, and `git-*` family are oriented vertically (top-to-bottom git-graph convention), so `If` and `Merge` nodes rendered 90° off from the flow direction. The execution-tree panel also ran a parallel icon-rendering path that only understood Lucide names — every time a plugin node set an icon as `builtin:<id>`, `si:<slug>`, or a URL, the tree panel silently fell back to a type-substring-guessed Lucide glyph (e.g. `"wait".includes("ai")` → the agent Bot icon). That duplication is gone.
+
+  **What changed**
+  - **Rotation suffix**: `NodeConfigBase.icon` now accepts an optional `@rot=<0|90|180|270>` tail modifier on any icon token (`lucide:`, `builtin:`, `si:`, or URL). Parsed by a strict tail regex so URLs with `@` (for example `http://user@host/icon.svg`) are unaffected, and non-orthogonal angles are rejected so glyphs stay pixel-crisp.
+  - **LTR control-flow icons**:
+    - `If`: `lucide:split@rot=90` — Y-fork with the single leg on the left and two arms fanning right.
+    - `Merge`: `lucide:merge@rot=90` — chevron pointing right, two arms merging from the left.
+  - **Pixel-perfect builtin SVGs** shipped under `packages/next-host/public/canvas-icons/builtin/`:
+    - `builtin:split-rows`: 1 source square on the left, tree trunk / spine, 3 output lines on the right.
+    - `builtin:aggregate-rows`: mirror — 3 input lines on the left converging through a spine into 1 summary square on the right.
+    - Stroke-based SVGs (matching Lucide stroke weight next to them on the canvas).
+  - **`@codemation/core-nodes` built-in node icon updates** that plug into the above: `If` (rotated split), `Merge` (rotated merge), `Split` (`builtin:split-rows`), `Aggregate` (`builtin:aggregate-rows`), `Wait` (`lucide:hourglass`), `MapData` (`lucide:square-pen`), `HttpRequest` (`lucide:globe`), `WebhookTrigger` (`lucide:webhook`), `NoOp` (`lucide:circle-dashed`).
+  - **One renderer, role-only fallback**: `WorkflowExecutionInspectorTreePanelContent` now renders `<WorkflowCanvasNodeIcon />` so `builtin:`, `si:`, URLs, and `@rot=…` resolve identically in the execution tree panel and on the canvas. `WorkflowNodeIconResolver.resolveFallback` shrank from 11 branches of type-substring guessing to 4 role mappings (`agent` / `nestedAgent` → `Bot`, `languageModel` → `Brain`, `tool` → `Wrench`, else → `Boxes`). Plugin nodes that forget to set an icon now get a generic `Boxes` — a clear visual signal rather than a silent substring mismatch.
+  - **New test file** `test/canvas/workflowCanvasNodeIcon.test.tsx` pins 12 behaviours across the rotation parser and the role-only fallback, including a regression case that the pre-fix `"wait".includes("ai")` mis-mapping is impossible now.
+
+## 1.0.0
+
+### Major Changes
+
+- [#93](https://github.com/MadeRelevant/codemation/pull/93) [`640e303`](https://github.com/MadeRelevant/codemation/commit/640e3032b1386568df725980a27761b6e230302c) Thanks [@cblokland90](https://github.com/cblokland90)! - Replace LangChain with the Vercel AI SDK for all AIAgent flows.
+
+  Codemation no longer depends on `@langchain/core` or `@langchain/openai`. Chat model providers, the turn loop, structured output, and tool calls now run on top of the Vercel **AI SDK** (`ai`, `@ai-sdk/openai`, `@ai-sdk/provider`). Custom Codemation behaviors that LangChain did not cover — the **tool-args repair loop**, the **structured-output repair loop**, **connection-invocation tracking**, and our **telemetry / cost-tracking spans** — are preserved and built on top of the new primitives.
+
+  ### Dependency changes
+  - **Removed**: `@langchain/core`, `@langchain/openai` (from `@codemation/core-nodes`).
+  - **Added**: `ai` `^6.0.168`, `@ai-sdk/openai` `^3.0.53`, `@ai-sdk/provider` `^3.0.8` (to `@codemation/core-nodes`). `@codemation/host` picks up `ai` + `@ai-sdk/provider` for its test harness only.
+
+  ### Public API renames (`@codemation/core`)
+
+  | Before                                               | After                                                                                                             |
+  | ---------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------- |
+  | `LangChainChatModelLike`                             | `ChatLanguageModel`                                                                                               |
+  | `LangChainStructuredOutputModelLike`                 | _(removed — replaced by `StructuredOutputOptions` + `generateText({ experimental_output: Output.object(...) })`)_ |
+  | `ChatModelFactory.create` → `LangChainChatModelLike` | `ChatModelFactory.create` → `ChatLanguageModel` (thin wrapper around an AI SDK `LanguageModelV2`)                 |
+
+  `ChatLanguageModel` exposes the underlying AI SDK `LanguageModel` via `languageModel` plus `modelName`, `provider`, and optional `defaultCallOptions` (`maxOutputTokens`, `temperature`, `providerOptions`). `StructuredOutputOptions` mirrors `generateText({ output: Output.object(...) })` and carries an optional `schemaName` plus `strict` flag.
+
+  ### Custom behavior preserved (not delegated to the AI SDK)
+  - **Tool dispatch + tool-args repair**: tools are passed to `generateText` **without `execute`** so tool calls surface back to Codemation; `AgentToolExecutionCoordinator` still drives parallel execution, per-tool Zod-input validation, repair prompts, and retry accounting via `repairAttemptsByToolName`.
+  - **Structured output repair**: `AgentStructuredOutputRunner` still runs the `OpenAiStrictJsonSchemaFactory` + `AgentStructuredOutputRepairPromptFactory` loop; AI SDK's `Output.object(...)` is used only for the **first** structured attempt when the provider supports it.
+  - **Connection-invocation tracking**: `ConnectionInvocationIdFactory` + synthetic `LanguageModelConnectionNode` / tool connection node states (`queued` / `running` / `completed` / `failed`) are still emitted per turn and per tool call.
+  - **Telemetry span names (intentional, short-term)**: LLM calls stay on `gen_ai.chat.completion`, tool calls on `agent.tool.call`, metrics on `codemation.ai.turns` / `codemation.ai.tool_calls` / `codemation.cost.estimated`. We disable AI SDK's built-in telemetry (`experimental_telemetry`) for this cut so host-side telemetry aggregations keep working unchanged. Migrating to AI SDK native span names is intentionally deferred.
+  - **Engine-level retry control**: every `generateText` call uses `maxRetries: 0` so Codemation's own retry / repair policy is the single source of truth.
+
+  ### New test utilities
+
+  Tests that previously scripted `LangChainChatModelLike` now script AI SDK `LanguageModelV3` via `MockLanguageModelV3` from `ai/test`. `@codemation/core-nodes` and `@codemation/host` test files ship small adapters (`ScriptedResponseConverter`, `ScriptedDoGenerateFactory`, `TelemetryResponseConverter`) that translate Codemation's legacy `{ content, tool_calls, usage_metadata }` fixtures into `LanguageModelV3GenerateResult`.
+
+  ### Migration notes for consumers
+  - If you implemented a **custom `ChatModelFactory`**, return a `ChatLanguageModel` (wrap an AI SDK `LanguageModelV2`) instead of a LangChain-shaped chat model. The `name` / `modelName` / `provider` on your config still drive cost tracking.
+  - If you imported the type `LangChainChatModelLike` (or `LangChainStructuredOutputModelLike`) from `@codemation/core`, switch to `ChatLanguageModel` (and drop structured-output-method imports — `generateText({ experimental_output })` covers it).
+  - `OpenAIChatModelFactory` now builds an AI SDK OpenAI provider under the hood; behavior for end users (model presets, credential resolution, token accounting, structured output against strict mode) is unchanged.
+  - Telemetry dashboards, trace views, and cost-tracking queries continue to work against the existing Codemation span / metric names.
+
+### Patch Changes
+
+- Updated dependencies [[`640e303`](https://github.com/MadeRelevant/codemation/commit/640e3032b1386568df725980a27761b6e230302c), [`640e303`](https://github.com/MadeRelevant/codemation/commit/640e3032b1386568df725980a27761b6e230302c)]:
+  - @codemation/core@1.0.0
+
 ## 0.4.3
 
 ### Patch Changes