@codemation/agent-skills 0.1.7 → 0.1.8

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @codemation/agent-skills
 
+## 0.1.8
+
+### Patch Changes
+
+- [#78](https://github.com/MadeRelevant/codemation/pull/78) [`f451b1b`](https://github.com/MadeRelevant/codemation/commit/f451b1b4657b59406e15ce5f50b243e487ff99ed) Thanks [@cblokland90](https://github.com/cblokland90)! - Normalize fluent workflow DSL callback helpers around the runtime item contract.
+
+  `.map(...)`, `.if(...)`, and `.switch({ resolveCaseKey })` now receive `(item, ctx)` so workflow authors can use `item.json` consistently and read prior completed outputs through `ctx.data` without dropping down to direct node configs.
+
 ## 0.1.7
 
 ### Patch Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@codemation/agent-skills",
-  "version": "0.1.7",
+  "version": "0.1.8",
   "description": "Reusable agent skills for Codemation projects and plugin development.",
   "publishConfig": {
     "access": "public"

package/skills/codemation-workflow-dsl/SKILL.md

@@ -18,6 +18,7 @@ Do not use this skill for CLI-only troubleshooting or deep host architecture que
 2. The fluent authoring chain is the normal starting point for Codemation apps.
 3. Finish fluent workflow definitions with `.build()`.
 4. Activations are **batch-shaped** (`Items`); many steps use **per-item** execution (`execute`, including helper **`defineNode`**) with optional **`inputSchema`** and **`itemValue`** on config fields. Batch reshape steps (split/filter/aggregate, **`defineBatchNode`**) work on the whole batch.
+5. Fluent callback helpers follow the runtime item contract: `.map(...)`, `.if(...)`, and `.switch({ resolveCaseKey })` receive `(item, ctx)`, so row fields live under `item.json` and earlier completed outputs are available through `ctx.data`.
 
 ## Authoring rules
 
@@ -45,6 +46,7 @@ Do not use this skill for CLI-only troubleshooting or deep host architecture que
 - Define agent messages with `messages`, not a workflow-specific prompt shortcut.
 - Use a static `messages` array for fixed prompts.
 - Use `itemValue(...)` when agent messages depend on the current item.
+- Use fluent `.map((item, ctx) => ...)` when workflow data itself needs reshaping before the agent step.
 - `model` may be a provider string such as `"openai:gpt-4o-mini"` or a `ChatModelConfig`.
 
 ## Read next when needed

package/skills/codemation-workflow-dsl/references/builder-patterns.md

@@ -8,8 +8,8 @@ export default workflow("wf.example.id")
   .manualTrigger("Start", {
     step: "start",
   })
-  .map("Transform", (item) => ({
-    ...item,
+  .map("Transform", (item, _ctx) => ({
+    ...item.json,
     transformed: true,
   }))
   .build();
@@ -27,6 +27,8 @@ export default workflow("wf.example.id")
 - items usually carry `json` data and optional `binary` data
 - runtime nodes receive batches of items, not just one record
 - author workflow steps with batching in mind
+- fluent `.map(...)`, `.if(...)`, and `.switch({ resolveCaseKey })` callbacks receive `(item, ctx)`
+- read row fields from `item.json` and earlier completed outputs from `ctx.data`
 
 ## When to move beyond callbacks