@aexhq/sdk 0.13.7 → 0.13.8

package/docs/skills.md

@@ -18,20 +18,18 @@ Skill inputs accepted by the platform:
   persist on aex as workspace skills with auto-suffixed names,
   one row per submission (see "Inline supply" below).
 
-**Routing at session create:** bundles that contain `SKILL.md` at the
-bundle root are registered with Anthropic's Skills API
-(`POST /v1/skills`) and surface to the agent as auto-discoverable
-skills. Bundles without `SKILL.md` mount under
-`/mnt/session/uploads/aex/assets/<skl_id>/<rel-path>` in the agent
-container — the agent reads them by explicit path reference in the
-prompt.
-
-The platform also mounts the `aex` CLI at
-`/mnt/session/uploads/aex/aex` and a per-run manifest at
-`/mnt/session/uploads/aex/index.json` on **every** run. Skills
-invoke the managed HTTP proxy via
-`node /mnt/session/uploads/aex/aex proxy …` — see
-`credentials.md` for the policy/auth model.
+**How skills reach the agent:** every skill bundle is materialized into
+the run's workspace under `skills/<name>/` before the first agent turn.
+A bundle's `SKILL.md` is composed into the agent's instructions, so the
+agent is told the skill exists and what it does without the model having
+to discover it. Bundles without `SKILL.md` are still mounted as files at
+`skills/<name>/`, but nothing prompts the agent to read them — reference
+them explicitly from the prompt or your `AGENTS.md`.
+
+The platform also mounts the `aex` CLI and a per-run manifest into the
+workspace on **every** run. Skills invoke the managed HTTP proxy via the
+mounted CLI (`aex proxy …`) — see `credentials.md` for the policy/auth
+model.
 
 ## Inline supply at `submitRun`
 
@@ -40,20 +38,20 @@ build an **unstaged** `Skill`. The instance carries the canonicalised
 zip bytes and the `sha256:<hex>` content hash:
 
 ```ts
-import { AexClient, Skill } from "@aexhq/sdk";
+import { AgentExecutor, Skill } from "@aexhq/sdk";
 
-const client = new AexClient({ apiToken });
+const aex = new AgentExecutor({ apiToken });
 
-await client.submitRun({
+await aex.submitRun({
   model, prompt,
   skills: [await Skill.fromFiles({ name: "rules", files })],
   secrets: { anthropic: { apiKey } }
 });
 ```
 
-`client.submitRun` walks the `skills` array, sends a multipart body
+`aex.submitRun` walks the `skills` array, sends a multipart body
 alongside the JSON submission, and materializes the bytes to
-content-addressable, workspace-scoped R2 storage before the run lands.
+content-addressable, workspace-scoped asset storage before the run lands.
 The BFF re-canonicalises the bundle, verifies the advisory hash, and
 persists it as a workspace skill — but with an **auto-suffixed name**
 (`rules-x8q7lk2`) so repeated supplies of the same logical skill across
@@ -79,11 +77,11 @@ rules-az3lkmt
 
 Same prefix, different suffix. Each is a real workspace skill — you
 can list, get, download, and delete it through the regular
-`client.skills.*` verbs.
+`aex.skills.*` verbs.
 
 ### Deletion semantics
 
-Soft-deleting a skill (`client.skills.delete(skl_id)` or the
+Soft-deleting a skill (`aex.skills.delete(skl_id)` or the
 dashboard's Delete button) marks the row tombstoned. Existing runs
 that pinned a snapshot of the skill keep working — they read from
 `run_skill_snapshots` which preserves the name, hash, size, and
@@ -103,11 +101,11 @@ bundle skill bytes with it. Host the skill yourself as a **zip archive**
 URL — e.g. an S3 presigned URL:
 
 ```ts
-import { AexClient, Skill } from "@aexhq/sdk";
+import { AgentExecutor, Skill } from "@aexhq/sdk";
 
-const client = new AexClient({ apiToken });
+const aex = new AgentExecutor({ apiToken });
 
-await client.submitRun({
+await aex.submitRun({
   model, prompt,
   skills: [
     await Skill.fromUrl(signedUrl, { name: "rules", sha256: "sha256:<hex>" })
@@ -125,7 +123,7 @@ produce the **same canonical asset** and dedup against each other.
 - The archive must contain `SKILL.md` at its root, or inside a single
   top-level folder, which is stripped automatically. Anything else is
   rejected with an error listing the archive's actual top-level entries.
-- The signed URL only needs to be valid **for this call**. `client.submitRun`
+- The signed URL only needs to be valid **for this call**. `aex.submitRun`
   snapshots the bytes into the run immediately, so the URL can expire
   afterwards with no effect on the run.
 - `sha256` is an optional source-integrity check on the downloaded archive

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aexhq/sdk",
-  "version": "0.13.7",
+  "version": "0.13.8",
   "description": "TypeScript SDK for running autonomous agent sessions across providers (Anthropic, OpenAI, DeepSeek, Gemini, Mistral) behind one interface.",
   "license": "Apache-2.0",
   "repository": {
@@ -26,7 +26,7 @@
     "examples"
   ],
   "devDependencies": {
-    "@aexhq/contracts": "0.13.7"
+    "@aexhq/contracts": "0.13.8"
   },
   "engines": {
     "node": ">=20"