@octavus/agent 0.1.0 → 0.3.0
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 +32 -0
- package/dist/index.js +97 -86
- package/dist/screen-publisher/index.js +4 -0
- package/package.json +4 -1
package/README.md
CHANGED
|
@@ -43,6 +43,11 @@ The working directory you launch in is the agent's workspace (override with `--w
|
|
|
43
43
|
- `--platform-url <url>` - override the platform base URL.
|
|
44
44
|
- `--env <name>` - environment to use (default: `production`; see below).
|
|
45
45
|
- `--chrome-path <path>` - path to Chrome for Testing (else resolved from `PATH`).
|
|
46
|
+
- `--model <provider/model-id>` - model for this run only (else the agent's default).
|
|
47
|
+
- `--backup-model <provider/model-id>` - backup model for this run only.
|
|
48
|
+
- `--capability <slug>=<on|off>` - toggle one capability for this run (repeatable).
|
|
49
|
+
- `--config <file>` - JSON run config for scripted sweeps (see below).
|
|
50
|
+
- `--json` - print one machine-readable JSON result to stdout.
|
|
46
51
|
- `--force` - allow running with the workspace at `$HOME` or `/`.
|
|
47
52
|
- `--verbose` - print diagnostics to stderr.
|
|
48
53
|
- `octoagent auth --api-key <oct_agt_...> [--platform-url <url>] [--env <name>]` - store credentials.
|
|
@@ -51,6 +56,33 @@ The working directory you launch in is the agent's workspace (override with `--w
|
|
|
51
56
|
|
|
52
57
|
Exit codes: `0` completed, `1` failed, `2` bad usage, `3` update required.
|
|
53
58
|
|
|
59
|
+
### Run configuration
|
|
60
|
+
|
|
61
|
+
Configure how the agent runs for a single invocation, without changing its dashboard settings. Any field you omit inherits the agent's configured default; the agent's stored configuration is never modified by a run.
|
|
62
|
+
|
|
63
|
+
```bash
|
|
64
|
+
# Choose the model + backup model for this run only.
|
|
65
|
+
octoagent run --model openrouter/moonshotai/kimi-k2 --backup-model anthropic/claude-sonnet-5 "..."
|
|
66
|
+
|
|
67
|
+
# Toggle capabilities for this run (repeatable). Unlisted capabilities inherit the agent default.
|
|
68
|
+
octoagent run --capability memory=off --capability handbook=on "..."
|
|
69
|
+
|
|
70
|
+
# Or carry it all in a JSON file for scripted/repeatable sweeps.
|
|
71
|
+
octoagent run --config run.json "..."
|
|
72
|
+
```
|
|
73
|
+
|
|
74
|
+
`run.json`:
|
|
75
|
+
|
|
76
|
+
```json
|
|
77
|
+
{ "model": "openrouter/moonshotai/kimi-k2", "backupModel": "anthropic/claude-sonnet-5", "capabilities": { "memory": false } }
|
|
78
|
+
```
|
|
79
|
+
|
|
80
|
+
Precedence: explicit flags > `--config` file > the agent's dashboard defaults. Any model is allowed as long as a key resolves for its provider (your project/org BYOK or the platform default); an unrunnable or malformed model is rejected up front, before the run starts. Capability toggles are bounded to the capabilities the agent's protocol declares. A run with no run config behaves exactly as before.
|
|
81
|
+
|
|
82
|
+
### Machine-readable output
|
|
83
|
+
|
|
84
|
+
`--json` prints exactly one JSON object to stdout - `{ "threadId", "sessionId", "status", "threadUrl" }` - with all human/progress output routed to stderr, so a benchmark harness can capture and correlate a run without scraping text. The exit code still signals completed (`0`) vs failed (`1`). Read the full transcript and a per-run cost/usage summary from `GET /api/v1/workforce/agents/{agentId}/threads/{threadId}` with the same agent key.
|
|
85
|
+
|
|
54
86
|
### Environments
|
|
55
87
|
|
|
56
88
|
`--env <name>` (or `OCTAVUS_ENV`, default `production`) selects an environment. Each keeps its own credentials and browser profile under `~/.octavus/<env>/`, so you can configure and run more than one side by side without them clobbering each other:
|