@harperfast/agent 0.13.7 → 0.13.8-ink

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 +8 -8
  2. package/dist/agent.js +4681 -1482
  3. package/package.json +10 -1
package/README.md CHANGED
@@ -74,24 +74,24 @@ By default, `harper-agent` uses OpenAI. You can switch to other models using the
74
74
 
75
75
  ```bash
76
76
  # Use Claude 3.5 Sonnet
77
- harper-agent --model claude-3-5-sonnet-20241022
77
+ harper-agent --model claude-4-6-opus-latest
78
78
 
79
79
  # Use Gemini 1.5 Pro
80
- harper-agent --model gemini-1.5-pro
80
+ harper-agent --model gemini-3-pro
81
81
 
82
82
  # Use a specific OpenAI model
83
- harper-agent --model gpt-4o-mini
83
+ harper-agent --model gpt-5.2
84
84
  ```
85
85
 
86
86
  You can also set the default model via the `HARPER_AGENT_MODEL` environment variable.
87
87
 
88
88
  ### Compaction Model
89
89
 
90
- By default, `harper-agent` uses `gpt-4o-mini` for session memory compaction. You can switch this to another model using the `--compaction-model` (or `-c`) flag:
90
+ By default, `harper-agent` uses `gpt-5-nano` for session memory compaction. You can switch this to another model using the `--compaction-model` (or `-c`) flag:
91
91
 
92
92
  ```bash
93
93
  # Use a different compaction model
94
- harper-agent --compaction-model claude-3-haiku-20240307
94
+ harper-agent --compaction-model claude-4-5-haiku-latest
95
95
  ```
96
96
 
97
97
  You can also set the default compaction model via the `HARPER_AGENT_COMPACTION_MODEL` environment variable.
@@ -128,21 +128,21 @@ To use local models with [Ollama](https://ollama.com/), use the `ollama-` prefix
128
128
 
129
129
  ```bash
130
130
  # Use Llama 3 via Ollama
131
- harper-agent --model ollama-llama3
131
+ harper-agent --model ollama-qwen2.5-coder
132
132
  ```
133
133
 
134
134
  If your Ollama instance is running on a custom URL, you can set the `OLLAMA_BASE_URL` environment variable:
135
135
 
136
136
  ```bash
137
137
  export OLLAMA_BASE_URL=http://localhost:11434
138
- harper-agent --model ollama-llama3
138
+ harper-agent --model ollama-qwen2.5-coder
139
139
  ```
140
140
 
141
141
  ### OpenAI API Key Permissions
142
142
 
143
143
  If you are using a restricted API key, ensure the following permissions are enabled:
144
144
 
145
- - **Models**: `Write` access for `gpt-5.2` (the main model) and `gpt-4o-mini` (the memory summarizer)
145
+ - **Models**: `Write` access for `gpt-5.2` (the main model) and `gpt-5-nano` (the memory summarizer)
146
146
  - **Model capabilities**: `Write` (to allow tool calling and completions).
147
147
 
148
148
  No other permissions (like Assistants, Threads, or Files) are required as `harper-agent` runs its tools locally.