This release is a pre-release and may not be stable for production use.
Friday Chat
Terminal chat application for the Friday Framework.
Friday Chat provides the user-facing command-line chat experience built on the Friday runtime, memory, agent, LLM, transcript, and tools packages.
Install
pip install friday-chat==0.1.0a1
Run
friday-chat --help
Import Package
import friday_chat
Primary LLM Configuration
Friday Chat 0.1.0a1 uses Friday LLM's typed, provider-independent generation
configuration on the primary chat path. Target identity is explicit so Friday
does not infer provider capabilities from a model name or endpoint URL.
llm:
model: openai/qwen3.8-27b-mlx
api_base: http://127.0.0.1:1234/v1
api_key: ${FRIDAY_LLM_API_KEY}
max_retries: 3
timeout_seconds: 120.0
generation:
reasoning:
mode: enabled
effort: medium
preserve: false
sampling:
temperature: 0.2
top_p: 0.95
top_k: 40
min_p: 0.0
presence_penalty: 0.0
frequency_penalty: 0.0
repetition_penalty: 1.0
max_tokens: 8000
transport_target:
provider: openai_compatible
dialect: openai_chat_completions
serving_engine: lm_studio
model_target:
model_id: qwen3.8-27b-mlx
family: qwen3_8
revision: lmstudio-community/Qwen3.8-27B-MLX-8bit
Replace the revision with the exact artifact served by your local endpoint.
Friday LLM 0.1.0a1 provides the built-in normalized reasoning profile for
LM Studio, OpenAI-compatible Chat Completions, and Qwen3.8. Other transports
continue to work through the legacy path but are not automatically assigned
this capability profile.
Provider-specific controls, when needed, use a bounded provider_options
object with an explicit namespace. Arbitrary provider keyword dictionaries are
not accepted. Prefer normalized generation fields when they express the same
intent.
Legacy Compatibility
The former flat fields remain accepted through the 0.1.x compatibility
window:
| Legacy field | Canonical field |
|---|---|
llm.temperature |
llm.generation.sampling.temperature |
llm.top_p |
llm.generation.sampling.top_p |
llm.top_k |
llm.generation.sampling.top_k |
llm.max_tokens |
llm.generation.max_tokens |
llm.thinking |
llm.generation.reasoning.mode |
Legacy configurations without explicit targets retain their previous behavior and produce startup migration diagnostics. With explicit targets, flat fields are converted to typed generation controls. Equal flat and nested values are accepted with a diagnostic; contradictory values fail before provider I/O.
top_p and top_k were present in earlier Friday Chat YAML but were not
forwarded by its legacy adapter. They become effective on the typed path. Wire
emission proves forwarding, not that every endpoint behaviorally honors the
setting.
License
MIT
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file friday_chat-0.1.0a1.tar.gz.
File metadata
- Download URL: friday_chat-0.1.0a1.tar.gz
- Upload date:
- Size: 259.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/7.0.0 CPython/3.13.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
95753bd78e1531d7adbedb6f7aea931d78550cc04246a76c706a90f51c38acd7
|
|
| MD5 |
ebf0cde6a63c99160c791b8cf58de41a
|
|
| BLAKE2b-256 |
94dee2b06b4530733ebf905473b2c9e99b199e22e930b88d0c2794b1f3d7b323
|
File details
Details for the file friday_chat-0.1.0a1-py3-none-any.whl.
File metadata
- Download URL: friday_chat-0.1.0a1-py3-none-any.whl
- Upload date:
- Size: 175.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/7.0.0 CPython/3.13.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
648e131c952d32d16854cd720b403f22c387da6ee7785d2c30c9d737a8340f4e
|
|
| MD5 |
07beee6ccdfe7bd2d5ae8fbb84db5fd5
|
|
| BLAKE2b-256 |
1e3796b6359a288b5ea4a442188c223373c7e1f880a45caa4f8f669e99fd6743
|