@xera-ai/skills 0.4.4 → 0.5.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@xera-ai/skills",
-  "version": "0.4.4",
+  "version": "0.5.0",
   "files": [
     "*.md",
     "version.json"

package/version.json

@@ -1,6 +1,6 @@
 {
-  "skills": "0.4.4",
-  "compatible_prompts": "^2.3.0",
+  "skills": "0.5.0",
+  "compatible_prompts": "^2.4.0",
   "skill_files": [
     "xera-run.md",
     "xera-fetch.md",

package/xera-exec.md

@@ -8,6 +8,7 @@ The user invoked `/xera-exec <TICKET>`. If no key, ask.
 1. Verify `.xera/{{TICKET}}/spec.ts` exists. If not: "Generate the spec first with `/xera-script {{TICKET}}`." STOP.
 
 2. Run: `bun run xera:exec {{TICKET}}`
+   `bun run xera:exec` automatically picks the runner based on `meta.json.adapter` (web or http).
    - Exit 0 → all scenarios passed.
    - Exit 1 → user/config error (lock held, missing env var). Show the error verbatim and STOP.
    - Exit 3 → test failure. This is expected; continue.

package/xera-script.md

@@ -12,7 +12,19 @@ The user invoked `/xera-script <TICKET>`. If no key, ask.
 
 3. List existing shared POMs by reading `shared/page-objects/` (every `.ts` file, parse exported class names). Pass this list to yourself as context for reuse decisions.
 
-4. Read `node_modules/@xera-ai/prompts/script-from-feature.md`. Follow its hard rules.
+4. Read `.xera/{{TICKET}}/meta.json` to get the adapter (`adapter` field). Then read the appropriate prompt template:
+
+   - If `adapter === "web"` (or missing): use `node_modules/@xera-ai/prompts/script-from-feature-web.md`.
+   - If `adapter === "http"`: use `node_modules/@xera-ai/prompts/script-from-feature-http.md`.
+
+   Follow that prompt's hard rules.
+
+   When `adapter === "http"` AND `xera.config.ts` has `http.spec` configured, additionally:
+   - Load the OpenAPI spec at `http.spec` (path or URL).
+   - Find the operation referenced by the failing Gherkin step (matching method + path).
+   - Pass the dereferenced operation schema to your generation context as the `openapi` input.
+
+   When `adapter === "http"` and no `http.spec`: pass `openapi: null` to your generation context.
 
 5. Before reading the test.feature + story.md content into your generation context, mint a fresh per-invocation nonce by running: