@agentworkforce/workload-router 0.14.0 → 0.15.1

package/CHANGELOG.md

@@ -7,11 +7,19 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.15.1] - 2026-05-08
+
 ### Added
 
 - Personas can declare prompt-visible runtime `inputs`, which are parsed,
   validated, and propagated through resolved selections.
 
+## [0.15.0] - 2026-05-08
+
+### Released
+
+- v0.15.0
+
 ## [0.14.0] - 2026-05-08
 
 ### Released

package/README.md

@@ -18,6 +18,12 @@ resolved persona and grouped install metadata. Nothing is installed,
 spawned, or written to disk — run `install.commandString` yourself when
 you are ready to materialize the persona's skills.
 
+`usePersona` resolves only the internal built-in catalog (`persona-maker` /
+`persona-authoring`). Optional personas such as `code-reviewer` and
+`frontend-implementer` are distributed through installable persona packs and
+should be loaded through the CLI/source cascade, then passed to `useSelection`
+or `materializeSkillsFor`.
+
 ```ts
 import { usePersona } from '@agentworkforce/workload-router';
 ```
@@ -25,7 +31,7 @@ import { usePersona } from '@agentworkforce/workload-router';
 #### Return shape
 
 ```ts
-const { selection, install } = usePersona('npm-provenance');
+const { selection, install } = usePersona('persona-authoring');
 ```
 
 - `selection`: the resolved persona choice for the given intent/profile. Includes `personaId`, `tier`, `runtime`, `skills`, `inputs`, `mount`, and `rationale`.
@@ -41,7 +47,7 @@ const { selection, install } = usePersona('npm-provenance');
 import { spawnSync } from 'node:child_process';
 import { usePersona } from '@agentworkforce/workload-router';
 
-const { selection, install } = usePersona('npm-provenance');
+const { selection, install } = usePersona('persona-authoring');
 
 spawnSync(install.commandString, { shell: true, stdio: 'inherit' });
 // hand `selection` to your harness launcher of choice.
@@ -74,7 +80,12 @@ Personas may declare prompt-visible runtime inputs:
       "harness": "codex",
       "model": "openai-codex/gpt-5.3-codex",
       "systemPrompt": "Check $PACKAGE_NAME and write ${REPORT_PATH}.",
-      "harnessSettings": { "reasoning": "high", "timeoutSeconds": 1200 }
+      "harnessSettings": {
+        "reasoning": "high",
+        "timeoutSeconds": 1200,
+        "sandboxMode": "workspace-write",
+        "workspaceWriteNetworkAccess": true
+      }
     }
     // best-value and minimum omitted in this fragment
   }
@@ -86,6 +97,11 @@ the declarations through `PersonaSpec` and `PersonaSelection`; launchers decide
 how to resolve and render them. The standard harness-kit policy is explicit
 value, env var, default, then fail.
 
+Codex runtimes may also set `harnessSettings.sandboxMode`,
+`harnessSettings.approvalPolicy`,
+`harnessSettings.workspaceWriteNetworkAccess`, and
+`harnessSettings.webSearch`; harness-kit maps those to Codex launch flags.
+
 ## Development
 
 ```bash