@letta-ai/letta-code 0.1.12 → 0.1.15

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.
Files changed (3) hide show
  1. package/README.md +5 -0
  2. package/letta.js +18776 -17058
  3. package/package.json +7 -6
package/README.md CHANGED
@@ -83,9 +83,13 @@ Join our [Discord](https://discord.gg/letta) to share feedback on persistence pa
83
83
  letta # Auto-resume project agent (or create new if first time)
84
84
  letta --new # Force create new agent
85
85
  letta --agent <id> # Use specific agent ID
86
+ letta --model <model> # Specify model (e.g., claude-sonnet-4.5, gpt-4o)
87
+ letta -m <model> # Short form of --model
86
88
  letta --continue # Resume global last agent (deprecated, use project-based)
87
89
  ```
88
90
 
91
+ > **Note:** The `--model` flag is inconsistent when resuming sessions. We recommend using the `/model` command instead to change models in interactive mode.
92
+
89
93
  ### Headless Mode
90
94
  ```bash
91
95
  letta -p "Run bun lint and correct errors" # Auto-resumes project agent
@@ -93,6 +97,7 @@ letta -p "Pick up where you left off" # Same - auto-resumes by
93
97
  letta -p "Start fresh" --new # Force new agent
94
98
  letta -p "Run all the test" --allowedTools "Bash" # Control tool permissions
95
99
  letta -p "Just read the code" --disallowedTools "Bash" # Control tool permissions
100
+ letta -p "Explain this code" -m gpt-4o # Use specific model
96
101
 
97
102
  # Pipe input from stdin
98
103
  echo "Explain this code" | letta -p