@zonease/aiworker-cli 0.10.0 → 0.10.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +7 -3
- package/aiworker-bun.js +45 -45
- package/package.json +1 -1
- package/web/fleet/assets/index-Cs9_ieMw.css +2 -0
- package/web/fleet/index.html +2 -2
- package/web/worker/assets/index-Cs9_ieMw.css +2 -0
- package/web/worker/assets/{index-CQiYA5i6.js → index-K99vOXUf.js} +1 -1
- package/web/worker/index.html +2 -2
- package/web/fleet/assets/index-MsglqJ8f.css +0 -2
- package/web/worker/assets/index-MsglqJ8f.css +0 -2
- /package/web/fleet/assets/{index-mArguTkr.js → index-RizR7tk6.js} +0 -0
package/README.md
CHANGED
|
@@ -198,7 +198,7 @@ A new worker defaults to `executor: { engine: 'http', variant: 'default' }` and
|
|
|
198
198
|
|
|
199
199
|
```sh
|
|
200
200
|
# Local:
|
|
201
|
-
aiworker executor select --engine claude-code --variant default --apply
|
|
201
|
+
aiworker executor select --engine claude-code --variant default --timeout-ms 240000 --apply
|
|
202
202
|
aiworker executor doctor --engine claude-code
|
|
203
203
|
|
|
204
204
|
# Remote, for a worker in the fleet:
|
|
@@ -210,6 +210,10 @@ Supported engines: `http` (OpenAI / DeepSeek / SiliconFlow / any chat-completion
|
|
|
210
210
|
|
|
211
211
|
Per-engine install / auth recipes (including `claude login`, `codex auth`, secret vault writes, ACP CLI installs): [`docs/executor-engines.md`](docs/executor-engines.md).
|
|
212
212
|
|
|
213
|
+
`--timeout-ms` on `executor select` sets the executor adapter's per-turn hard
|
|
214
|
+
timeout. `aiworker run --timeout-ms` only controls how long the CLI waits for
|
|
215
|
+
the worker turn to finish.
|
|
216
|
+
|
|
213
217
|
---
|
|
214
218
|
|
|
215
219
|
## Deployment shapes
|
|
@@ -269,13 +273,13 @@ New features go through the `/pma` skill in three stages: investigate → propos
|
|
|
269
273
|
|
|
270
274
|
> Before going to production, read the conformance table and residual-boundary section in [`docs/governance-node-status.md`](docs/governance-node-status.md). Pre-1.0 the CLI / API / config does not guarantee backwards compatibility (an explicit AGENTS.md commitment).
|
|
271
275
|
|
|
272
|
-
CLI npm latest: **0.10.
|
|
276
|
+
CLI npm latest: **0.10.2**.
|
|
273
277
|
|
|
274
278
|
| Module | Status |
|
|
275
279
|
|---|---|
|
|
276
280
|
| Worker / Fleet control plane / 4 enrollment paths / 6 LLM engines / 5 channel webhooks / cron / per-tool approvals / hot reload | ✅ Production |
|
|
277
281
|
| Brain Governance Kernel (admission state machine + secret-scan defense + canonical memory boundary + truthful decision events + bypass detection) | ✅ GA |
|
|
278
|
-
| Governance Kernel regression harness (5×2 matrix on source + cli-release-local with
|
|
282
|
+
| Governance Kernel regression harness (5×2 matrix on source + cli-release-local with 800+ checks) + long-running serve multi-turn REST regression | ✅ GA |
|
|
279
283
|
| Brain admission `memory-add` materializer | ✅ MVP (other kinds return `unsupported`; post-apply rollback not yet implemented) |
|
|
280
284
|
| Heavy LLM-backed Brain decider | 🔜 opt-in; defaults to `evaluator=heuristic` `mode=observe_only` |
|
|
281
285
|
| Cross-scope hard isolation (runtime-enforced) | 🔜 currently filesystem-conventional, not runtime-isolated |
|