LiuMangMang/agent-workflow
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add web executor model configuration

Browse Source
This commit is contained in:
liujing
2026-07-20 16:59:24 +08:00
parent 4026f04b93
commit 64b3ef6c60
8 changed files with 1507 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -3
View File
@@ -174,15 +174,16 @@ agent-workflow logs --run <run-id> --tail 200
### `agent-workflow web`
Start a local read-only web server to monitor agent executions, runs, cycles, and logs in real-time.
Start a local web console to monitor agent executions, runs, cycles, and logs in real-time, and to manage host-wide executor model overrides.
```bash
agent-workflow web [--port <n>]
```
- **`--port <n>`** — specify a custom port to listen on (default: `4317`).
- **Security & Scope** — The server binds exclusively to the loopback interface (`127.0.0.1`) for local-only access. It refuses any external or remote listener configurations. Since executor logs can contain sensitive code, configuration details, or tokens/credentials, binding to `127.0.0.1` ensures that the console remains local.
- **Observability Boundaries & Limits** — The console is completely read-only and provides no endpoints to modify or control workflows. It directly parses and displays the execution progress, cycles, timeline, and stdout/stderr output. It cannot recover or display private reasoning tokens/processes of underlying models that are not output to the console.
- **Security & Scope** — The server binds exclusively to the loopback interface (`127.0.0.1`) for local-only access. It refuses any external or remote listener configurations. Since executor logs can contain sensitive code, configuration details, or tokens/credentials, binding to `127.0.0.1` ensures that the console remains local. Mutation endpoints require same-origin localhost requests, JSON content type, bounded bodies, and validated model values. Credentials are never returned to the browser.
- **Workflow monitoring remains read-only** — The console provides no endpoints to start, stop, decide, or otherwise control workflow runs. It parses and displays execution progress, cycles, timeline, and stdout/stderr output. It cannot recover or display private reasoning tokens/processes of underlying models that are not output to the console.
- **Writable global model settings** — The Chinese “全局执行器模型配置” view can independently set Claude, Agy, and Reasonix models. Discovery uses the current CLI environment: Claude via Anthropic `/v1/models` (with configured-default fallback), Agy via `agy models`, and Reasonix via `reasonix doctor --json` provider names. Discovery failures are isolated per executor, and manual entry always remains available. Saving atomically updates only `executors.<kind>.model` in `~/.agent-workflow/config.json`, preserves unrelated fields, and clears an override when the value is emptied. Active executors are not interrupted; saved models take effect on later cycles, scope remediation, extensions, and executor retries through the existing reload path. Project configuration continues to override global values.
- **Interaction with `logs --follow`** — The web server directly reads the persisted run files without taking any logs follow locks or interfering with the main executor loop, allowing you to use both the CLI `logs --follow` and the web console concurrently.
### `agent-workflow abort`