Skip to content

chore(release): 0.6.6 #166

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
FrancescoRosciano merged 1 commit into from
Jun 10, 2026
Merged

chore(release): 0.6.6 #166

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,7 @@
## Unreleased

## 0.6.6 (2026-06-10)

### Added

- **`CustomLLM` — the canonical "Custom LLM" provider for any OpenAI-compatible endpoint.** One generic provider (the same engine the `HermesLLM` / `OpenClawLLM` presets subclass) now ships under the name the voice-AI ecosystem uses for this pattern: `from getpatter import CustomLLM` / `from getpatter.llm import custom` (Python) and `import { CustomLLM, custom } from "getpatter"` (TypeScript). Works with agent runtimes (Hermes, OpenClaw), keyless local gateways (Ollama, vLLM, LM Studio), or any service implementing `/chat/completions` with SSE streaming + tool calls — barge-in cancellation, long-turn filler, spoken error fallback, and cost attribution included. As part of this, the `session_key_from="caller_hash"` / `sessionKeyFrom: "caller_hash"` per-caller memory selector was hoisted from the Hermes preset into the generic provider, so ANY header-scoped runtime can enable cross-call per-caller memory (`patter-caller-<hash>`, never the raw number); the Hermes preset now delegates to it (behaviour unchanged). New `libraries/python/getpatter/llm/custom.py`, `libraries/typescript/src/llm/custom.ts`; `docs/python-sdk/llm.mdx`, `docs/typescript-sdk/llm.mdx`.
Expand Down
2 changes: 1 addition & 1 deletion libraries/python/getpatter/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@
See ``pyproject.toml`` and the top-level README for the full matrix.
"""

__version__ = "0.6.5"
__version__ = "0.6.6"

from getpatter._speech_events import (
AgentState,
Expand Down
2 changes: 1 addition & 1 deletion libraries/python/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
[project]
name = "getpatter"
version = "0.6.5"
version = "0.6.6"
description = "Open-source voice AI SDK — connect any AI agent to real phone calls in 4 lines of code"
readme = "README.md"
license = { text = "MIT" }
Expand Down
4 changes: 2 additions & 2 deletions libraries/typescript/package-lock.json
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion libraries/typescript/package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"name": "getpatter",
"version": "0.6.5",
"version": "0.6.6",
"description": "Open-source voice AI SDK — connect any AI agent to real phone calls in 4 lines of code",
"license": "MIT",
"author": {
Expand Down
Loading