@letta-ai/letta-code 0.27.25 → 0.27.26
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 +15 -0
- package/letta.js +2199 -964
- package/package.json +1 -1
- package/skills/messaging-agents/SKILL.md +44 -1
package/package.json
CHANGED
|
@@ -66,11 +66,24 @@ Results include `agent_id` for each matching message.
|
|
|
66
66
|
letta -p --from-agent $LETTA_AGENT_ID --agent <id> "message text"
|
|
67
67
|
```
|
|
68
68
|
|
|
69
|
+
When no `--environment` is specified, the target agent will run in the same
|
|
70
|
+
environment as the caller agent.
|
|
71
|
+
|
|
72
|
+
To route the target agent turn through a specific remote/local environment:
|
|
73
|
+
|
|
74
|
+
```bash
|
|
75
|
+
letta -p --from-agent $LETTA_AGENT_ID \
|
|
76
|
+
--agent <id> \
|
|
77
|
+
--environment <name-or-device-id-or-connection-id> \
|
|
78
|
+
"message text"
|
|
79
|
+
```
|
|
80
|
+
|
|
69
81
|
**Arguments:**
|
|
70
82
|
| Arg | Required | Description |
|
|
71
83
|
|-----|----------|-------------|
|
|
72
84
|
| `--agent <id>` | Yes | Target agent ID to message |
|
|
73
85
|
| `--from-agent <id>` | Yes | Sender agent ID (injects agent-to-agent system reminder) |
|
|
86
|
+
| `--environment <selector>` | No | Route through an online environment by connection name, device ID, or connection ID |
|
|
74
87
|
| `"message text"` | Yes | Message body (positional after flags) |
|
|
75
88
|
|
|
76
89
|
**Example:**
|
|
@@ -96,6 +109,35 @@ letta -p --from-agent $LETTA_AGENT_ID \
|
|
|
96
109
|
letta -p --from-agent $LETTA_AGENT_ID --conversation <id> "message text"
|
|
97
110
|
```
|
|
98
111
|
|
|
112
|
+
Add `--environment <selector>` to continue the conversation on a specific environment.
|
|
113
|
+
|
|
114
|
+
### Discovering Environments
|
|
115
|
+
|
|
116
|
+
```bash
|
|
117
|
+
letta environments list --online-only
|
|
118
|
+
# alias:
|
|
119
|
+
letta envs list --online-only
|
|
120
|
+
```
|
|
121
|
+
|
|
122
|
+
Use `connectionName`, `deviceId`, or `connectionId` from the JSON output as the
|
|
123
|
+
`--environment` selector. If a name is ambiguous, prefer `deviceId` or
|
|
124
|
+
`connectionId`. In `environments list`, the current local runtime is marked with
|
|
125
|
+
`"isCurrent": true`.
|
|
126
|
+
|
|
127
|
+
To force the target agent onto the current registered Letta Code environment,
|
|
128
|
+
resolve the current environment and pass its `connectionId`:
|
|
129
|
+
|
|
130
|
+
```bash
|
|
131
|
+
CURRENT_ENV=$(letta environments current | jq -r .connectionId)
|
|
132
|
+
letta -p --from-agent $LETTA_AGENT_ID \
|
|
133
|
+
--agent agent-abc123 \
|
|
134
|
+
--environment "$CURRENT_ENV" \
|
|
135
|
+
"Run on my same machine/environment."
|
|
136
|
+
```
|
|
137
|
+
|
|
138
|
+
Omit `--environment` when you want the target agent to run in the same
|
|
139
|
+
environment as the caller agent.
|
|
140
|
+
|
|
99
141
|
**Arguments:**
|
|
100
142
|
| Arg | Required | Description |
|
|
101
143
|
|-----|----------|-------------|
|
|
@@ -112,7 +154,8 @@ letta -p --from-agent $LETTA_AGENT_ID \
|
|
|
112
154
|
|
|
113
155
|
## Understanding the Response
|
|
114
156
|
|
|
115
|
-
-
|
|
157
|
+
- Text-mode scripts return only the **final assistant message** (not tool calls, reasoning, or metadata)
|
|
158
|
+
- JSON and stream-json responses include `agent_id`, `conversation_id`, and `environment.source` so you can continue the same conversation/runtime. Environment-routed turns also include `environment.id`, `connection_id`, `device_id`, and `name`.
|
|
116
159
|
- The target agent may use tools, think, and reason - but you only see their final response
|
|
117
160
|
- To see the full conversation transcript (including tool calls), use the `searching-messages` skill with `letta messages list --agent <id>` targeting the other agent
|
|
118
161
|
|