wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Auto-generate changelog from fragments

Browse Source
This commit is contained in:
Mark Backman
2025-12-04 15:10:20 -05:00
parent 11aa9c9e68
commit 21b2229b2b
25 changed files with 461 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files

126
.github/workflows/generate-changelog.yml vendored Normal file
View File

@@ -0,0 +1,126 @@
name: Generate Changelog for Release
on:
workflow_dispatch:
inputs:
version:
description: "Release version (e.g., 0.0.97)"
required: true
type: string
date:
description: "Release date (YYYY-MM-DD format, e.g., 2025-12-04)"
required: true
type: string
permissions:
contents: write
pull-requests: write
jobs:
generate-changelog:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: "3.12"
- name: Install uv
uses: astral-sh/setup-uv@v4
with:
enable-cache: true
- name: Install dependencies
run: |
uv sync --group dev
- name: Validate inputs
run: |
# Validate version format (basic check)
if ! [[ "${{ inputs.version }}" =~ ^[0-9]+\.[0-9]+\.[0-9]+.*$ ]]; then
echo "Error: Version must be in format X.Y.Z (e.g., 0.0.97)"
exit 1
fi
# Validate date format
if ! date -d "${{ inputs.date }}" >/dev/null 2>&1; then
# Try macOS date format
if ! date -j -f "%Y-%m-%d" "${{ inputs.date }}" >/dev/null 2>&1; then
echo "Error: Date must be in YYYY-MM-DD format (e.g., 2025-12-04)"
exit 1
fi
fi
- name: Check for changelog fragments
id: check_fragments
run: |
FRAGMENT_COUNT=$(find changelog -name "*.md" ! -name "README.md" ! -name "_template.md.j2" | wc -l | tr -d ' ')
echo "fragment_count=$FRAGMENT_COUNT" >> $GITHUB_OUTPUT
if [ "$FRAGMENT_COUNT" -eq "0" ]; then
echo "⚠️ Warning: No changelog fragments found"
echo "has_fragments=false" >> $GITHUB_OUTPUT
else
echo "✓ Found $FRAGMENT_COUNT changelog fragment(s)"
echo "has_fragments=true" >> $GITHUB_OUTPUT
fi
- name: Preview changelog
run: |
echo "## Preview of changelog for version ${{ inputs.version }}"
echo ""
uv run towncrier build --draft --version "${{ inputs.version }}" --date "${{ inputs.date }}"
- name: Build changelog
run: |
uv run towncrier build --version "${{ inputs.version }}" --date "${{ inputs.date }}" --yes
- name: Create Pull Request
uses: peter-evans/create-pull-request@v7
with:
token: ${{ secrets.GITHUB_TOKEN }}
commit-message: "Update changelog for version ${{ inputs.version }}"
title: "Release ${{ inputs.version }} - Changelog Update"
body: |
## Changelog Update for Release ${{ inputs.version }}
This PR updates the CHANGELOG.md with all changes for version **${{ inputs.version }}**.
### Summary
- **Version:** ${{ inputs.version }}
- **Date:** ${{ inputs.date }}
- **Fragments processed:** ${{ steps.check_fragments.outputs.fragment_count }}
### What this PR does
- ✅ Adds new release section to CHANGELOG.md
- ✅ Removes processed changelog fragments
- ✅ Ready to merge for release
### Next Steps
1. Review the changelog entries below
2. Make any necessary edits to CHANGELOG.md if needed
3. Merge this PR
4. Continue with your release process
---
<details>
<summary>📋 Preview of changes</summary>
The changelog has been updated with entries from the following fragments:
```bash
${{ steps.check_fragments.outputs.fragment_count }} fragments processed
```
</details>
branch: changelog-${{ inputs.version }}
delete-branch: true
labels: |
changelog
release

94
CHANGELOG.md
View File

@@ -5,99 +5,7 @@ All notable changes to **Pipecat** will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [Unreleased]
### Added
- Added new languages to AsyncAI in `AsyncAITTSService` and
`AsyncAIHttpTTSService`. New `languages`: `pt`, `nl`, `ar`, `ru`, `ro`, `ja`,
`he`, `hy`, `tr`, `hi`, `zh`.
- Updated the default AsyncAI TTS model to `asyncflow_multilingual_v1.0` for
improved accuracy and broader language coverage.
- Added new Gradium services, `GradiumSTTService` and `GradiumTTSService`, for
speech-to-text and text-to-speech functionality using Gradium's API.
### Changed
- Updated `CartesiaSTTService` to return the full transcription `result` in the
`TranscriptionFrame` and `InterimTranscriptionFrame`. This provides access to
word timestamp data.
- If an unexpected exception is caught, or if `FrameProcessor.push_error()` is
called with an exception, the file name and line number where the exception
occured are now logged.
- Improved interruption handling to prevent bots from repeating themselves.
LLM services that return multiple sentences in a single response (e.g.,
`GoogleLLMService`) are now split into individual sentences before being sent
to TTS. This ensures interruptions occur at sentence boundaries, preventing
the bot from repeating content after being interrupted during long responses.
- Text Aggregation Improvements:
- **Breaking Change**: `BaseTextAggregator.aggregate()` now returns
`AsyncIterator[Aggregation]` instead of `Optional[Aggregation]`. This
enables the aggregator to return multiple results based on the provided
text.
- Refactored text aggregators to use inheritance: `SkipTagsAggregator` and
`PatternPairAggregator` now inherit from `SimpleTextAggregator`, reusing
the base class's sentence detection logic.
- Updated `AICFilter` to use Quail STT as the default model
(`AICModelType.QUAIL_STT`). Quail STT is optimized for human-to-machine
interaction (e.g., voice agents, speech-to-text) and operates at a native
sample rate of 16 kHz with fixed enhancement parameters.
- Updated Deepgram logging to include Deepgram request IDs for improved debugging.
- Updated Smart Turn model weights to v3.1.
- Smart Turn analyzer now uses the full context of the turn rather than just the
audio since VAD last triggered.
### Deprecated
- Package `pipecat.sync` is deprecated, use `pipecat.utils.sync` instead.
- The `noise_gate_enable` parameter in `AICFilter` is deprecated and no longer
has any effect. Noise gating is now handled automatically by the AIC VAD
system. Use `AICFilter.create_vad_analyzer()` for VAD functionality instead.
- NVIDIA Services name changes (all functionality is unchanged):
- `NimLLMService` is now deprecated, use `NvidiaLLMService` instead.
- `RivaSTTService` is now deprecated, use `NvidiaSTTService` instead.
- `RivaTTSService` is now deprecated, use `NvidiaTTSService` instead.
- Use `uv pip install pipecat-ai[nvidia]` instead of
`uv pip install pipecat-ai[riva]`
### Fixed
- Fixed an issue in `ElevenLabsTTSService` where character usage metrics were
only reported on the first TTS generation per turn.
- Fixed an issue where `LLMTextFrame.skip_tts` was being overwritten by LLM
services.
- Fixed sentence aggregation to correctly handle ambiguous punctuation in
streaming text, such as currency ("$29.95") and abbreviations ("Mr. Smith").
- Fixed bug in `PatternPairAggregator` where pattern handlers could be called
multiple times for `KEEP` or `AGGREGATE` patterns.
- Fixed an issue in `SarvamTTSService` where the last sentence was not being
spoken. Now, audio is flushed when the TTS services receives the
`LLMFullResponseEndFrame` or `EndFrame`.
- Fixed an issue in `AWSTranscribeSTTService` where the `region` arg was
always set to `us-east-1` when providing an AWS_REGION env var.
- Fixed an issue in `DeepgramTTSService` where a `TTSStoppedFrame` was
incorrectly pushed after a functional call. This caused an issue with the
voice-ui-kit's conversational panel rending of the LLM output after a
function call.
<!-- towncrier release notes start -->
## [0.0.96] - 2025-11-26 🦃 "Happy Thanksgiving!" 🦃

105
CONTRIBUTING.md
View File

@@ -17,24 +17,121 @@ We welcome contributions of all kinds! Your help is appreciated. Follow these st
git checkout -b your-branch-name
```
4. **Make your changes**: Edit or add files as necessary.
5. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
6. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
5. **Add a changelog entry**: Create a changelog fragment file (see [Changelog Entries](#changelog-entries) below).
6. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
7. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
```bash
git commit -m "Description of your changes"
```
7. **Push your changes**: Push your branch to your forked repository.
8. **Push your changes**: Push your branch to your forked repository.
```bash
git push origin your-branch-name
```
8. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
9. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
> Important: Describe the changes you've made clearly!
Our maintainers will review your PR, and once everything is good, your contributions will be merged!
## Changelog Entries
Every pull request that makes a user-facing change should include a changelog entry. We use a changelog fragment system to avoid merge conflicts.
### Creating a Changelog Fragment
1. Create a new file in the `changelog/` directory with this naming pattern:
```
<PR_number>.<type>.md
```
2. Choose the appropriate type:
- `added.md` - New features
- `changed.md` - Changes in existing functionality
- `deprecated.md` - Soon-to-be removed features
- `removed.md` - Removed features
- `fixed.md` - Bug fixes
- `security.md` - Security fixes
3. Write your changelog entry as a Markdown bullet point. Include the `-` at the start:
**Example files:**
`changelog/1234.added.md`:
```markdown
- Added support for Anthropic Claude 3.5 Sonnet with improved streaming performance.
```
`changelog/5678.fixed.md`:
```markdown
- Fixed an issue where audio frames were dropped during high-load scenarios.
```
**For entries with nested bullets:**
`changelog/1234.changed.md`:
```markdown
- Updated service configuration:
- Changed default timeout to 30 seconds
- Added retry logic for failed connections
```
### Multiple Changes in One PR
**Different types of changes:** Create separate fragment files for each type:
```
changelog/1234.added.md
changelog/1234.fixed.md
```
**Multiple changes of the same type:** Create numbered fragment files:
```
changelog/1234.changed.md
changelog/1234.changed.2.md
```
**Related changes:** Use nested bullets in a single fragment:
```markdown
- Updated service configuration:
- Changed default timeout to 30 seconds
- Added retry logic for failed connections
```
**Rule of thumb:** One logical change per fragment file. If changes are unrelated, use separate files.
### Preview Your Changes
To see what your changelog entry will look like:
```bash
towncrier build --draft --version Unreleased
```
This won't modify any files, just show you a preview.
### When to Skip Changelog Entries
You can skip adding a changelog entry for:
- Documentation-only changes
- Internal refactoring with no user-facing impact
- Test-only changes
- CI/build configuration changes
If you're unsure whether your change needs a changelog entry, ask in your PR!
## Dependency Management
This project uses [uv](https://docs.astral.sh/uv/) for dependency management. The `uv.lock` file is committed to ensure reproducible builds.

1
changelog/3072.changed.md Normal file
View File

@@ -0,0 +1 @@
- Updated Deepgram logging to include Deepgram request IDs for improved debugging.

1
changelog/3120.added.md Normal file
View File

@@ -0,0 +1 @@
- Added `wait_for_all` argument to the base `LLMService`. When enabled, this ensures all function calls complete before returning results to the LLM (i.e., before running a new inference with those results).

7
changelog/3130.deprecated.md Normal file
View File

@@ -0,0 +1,7 @@
- NVIDIA Services name changes (all functionality is unchanged):
- `NimLLMService` is now deprecated, use `NvidiaLLMService` instead.
- `RivaSTTService` is now deprecated, use `NvidiaSTTService` instead.
- `RivaTTSService` is now deprecated, use `NvidiaTTSService` instead.
- Use `uv pip install pipecat-ai[nvidia]` instead of
`uv pip install pipecat-ai[riva]`

9
changelog/3132.changed.2.md Normal file
View File

@@ -0,0 +1,9 @@
- Text Aggregation Improvements:
- **Breaking Change**: `BaseTextAggregator.aggregate()` now returns
`AsyncIterator[Aggregation]` instead of `Optional[Aggregation]`. This
enables the aggregator to return multiple results based on the provided
text.
- Refactored text aggregators to use inheritance: `SkipTagsAggregator` and
`PatternPairAggregator` now inherit from `SimpleTextAggregator`, reusing
the base class's sentence detection logic.

1
changelog/3132.changed.md Normal file
View File

@@ -0,0 +1 @@
- Improved interruption handling to prevent bots from repeating themselves. LLM services that return multiple sentences in a single response (e.g., `GoogleLLMService`) are now split into individual sentences before being sent to TTS. This ensures interruptions occur at sentence boundaries, preventing the bot from repeating content after being interrupted during long responses.

1
changelog/3132.fixed.2.md Normal file
View File

@@ -0,0 +1 @@
- Fixed bug in `PatternPairAggregator` where pattern handlers could be called multiple times for `KEEP` or `AGGREGATE` patterns.

1
changelog/3132.fixed.md Normal file
View File

@@ -0,0 +1 @@
- Fixed sentence aggregation to correctly handle ambiguous punctuation in streaming text, such as currency ("$29.95") and abbreviations ("Mr. Smith").

1
changelog/3153.fixed.md Normal file
View File

@@ -0,0 +1 @@
- Fixed an issue in `AWSTranscribeSTTService` where the `region` arg was always set to `us-east-1` when providing an AWS_REGION env var.

1
changelog/3155.fixed.md Normal file
View File

@@ -0,0 +1 @@
- Fixed an issue in `SarvamTTSService` where the last sentence was not being spoken. Now, audio is flushed when the TTS services receives the `LLMFullResponseEndFrame` or `EndFrame`.

1
changelog/3156.fixed.md Normal file
View File

@@ -0,0 +1 @@
- Fixed an issue in `DeepgramTTSService` where a `TTSStoppedFrame` was incorrectly pushed after a functional call. This caused an issue with the voice-ui-kit's conversational panel rending of the LLM output after a function call.

1
changelog/3162.changed.md Normal file
View File

@@ -0,0 +1 @@
- Updated `AICFilter` to use Quail STT as the default model (`AICModelType.QUAIL_STT`). Quail STT is optimized for human-to-machine interaction (e.g., voice agents, speech-to-text) and operates at a native sample rate of 16 kHz with fixed enhancement parameters.

1
changelog/3162.deprecated.md Normal file
View File

@@ -0,0 +1 @@
- The `noise_gate_enable` parameter in `AICFilter` is deprecated and no longer has any effect. Noise gating is now handled automatically by the AIC VAD system. Use `AICFilter.create_vad_analyzer()` for VAD functionality instead.

1
changelog/3168.fixed.md Normal file
View File

@@ -0,0 +1 @@
- Fixed an issue where `LLMTextFrame.skip_tts` was being overwritten by LLM services.

1
changelog/3176.changed.md Normal file
View File

@@ -0,0 +1 @@
- If an unexpected exception is caught, or if `FrameProcessor.push_error()` is called with an exception, the file name and line number where the exception occured are now logged.

1
changelog/3177.changed.md Normal file
View File

@@ -0,0 +1 @@
- Updated Smart Turn model weights to v3.1.

1
changelog/3181.deprecated.md Normal file
View File

@@ -0,0 +1 @@
- Package `pipecat.sync` is deprecated, use `pipecat.utils.sync` instead.

1
changelog/3183.changed.md Normal file
View File

@@ -0,0 +1 @@
- Smart Turn analyzer now uses the full context of the turn rather than just the audio since VAD last triggered.

1
changelog/3186.fixed.md Normal file
View File

@@ -0,0 +1 @@
- Fixed an issue in `ElevenLabsTTSService` where character usage metrics were only reported on the first TTS generation per turn.

126
changelog/README.md Normal file
View File

@@ -0,0 +1,126 @@
# Changelog Fragments
This directory contains changelog fragments that will be compiled into the main `CHANGELOG.md` at release time using [towncrier](https://towncrier.readthedocs.io/).
## For Contributors: Adding a Changelog Entry
When you make a change that should be documented in the changelog, create a new file in this directory.
### Creating a Fragment
Create a file in this directory with this naming pattern:
```
changelog/<PR_number>.<type>.md
```
Choose the appropriate type:
- `added.md` - New features
- `changed.md` - Changes in existing functionality
- `deprecated.md` - Soon-to-be removed features
- `removed.md` - Removed features
- `fixed.md` - Bug fixes
- `security.md` - Security fixes
Write your changelog entry as a Markdown bullet point. Include the `-` at the start:
**Example files:**
`changelog/1234.added.md`:
```markdown
- Added support for Anthropic Claude 3.5 Sonnet with improved streaming performance.
```
`changelog/5678.fixed.md`:
```markdown
- Fixed an issue where audio frames were dropped during high-load scenarios.
```
**For entries with nested bullets:**
`changelog/1234.changed.md`:
```markdown
- Updated service configuration:
- Changed default timeout to 30 seconds
- Added retry logic for failed connections
- Improved error messages
```
### Multiple Changes in One PR
**Different types of changes:** Create separate fragment files for each type:
```
changelog/1234.added.md
changelog/1234.fixed.md
```
**Multiple changes of the same type:** Create numbered fragment files:
```
changelog/1234.changed.md
changelog/1234.changed.2.md
changelog/1234.changed.3.md
```
**Related changes:** Use nested bullets in a single fragment:
```markdown
- Updated service configuration:
- Changed default timeout to 30 seconds
- Added retry logic for failed connections
```
**Rule of thumb:** One logical change per fragment file. If changes are unrelated, use separate files.
### Preview Your Changes
To see what your changelog entry will look like:
```bash
towncrier build --draft --version Unreleased
```
This won't modify any files, just show you a preview.
### When to Skip Changelog Entries
You can skip adding a changelog entry for:
- Documentation-only changes
- Internal refactoring with no user-facing impact
- Test-only changes
- CI/build configuration changes
If you're unsure whether your change needs a changelog entry, ask in your PR!
---
## For Maintainers: Releasing
### Automated Release
The changelog is automatically generated via GitHub Actions. When you're ready to release:
1. **Trigger the workflow** from GitHub Actions:
- Go to Actions → "Generate Changelog for Release"
- Click "Run workflow"
- Enter the version (e.g., `0.0.97`)
- Enter the release date (e.g., `2025-12-04`)
2. **Review the PR** that gets created automatically
3. **Merge the PR** to update the changelog
## References
- [Towncrier Documentation](https://towncrier.readthedocs.io/)
- [Keep a Changelog](https://keepachangelog.com/)
- [Contributing Guide](../CONTRIBUTING.md)

17
changelog/_template.md.j2 Normal file
View File

@@ -0,0 +1,17 @@
{% for section, _ in sections.items() %}
{% if sections[section] %}
{% for category, val in definitions.items() if category in sections[section]%}
### {{ definitions[category]['name'] }}
{% for text, values in sections[section][category].items() %}
{{ text }}
{% endfor %}
{% endfor %}
{% else %}
No significant changes.
{% endif %}
{% endfor %}

42
pyproject.toml
View File

@@ -130,6 +130,7 @@ dev = [
"setuptools~=78.1.1",
"setuptools_scm~=8.3.1",
"python-dotenv>=1.0.1,<2.0.0",
"towncrier~=25.8.0",
]
docs = [
@@ -207,3 +208,44 @@ convention = "google"
command_line = "--module pytest"
source = ["src"]
omit = ["*/tests/*"]
[tool.towncrier]
package = "pipecat"
package_dir = "src"
filename = "CHANGELOG.md"
directory = "changelog"
start_string = "<!-- towncrier release notes start -->\n"
template = "changelog/_template.md.j2"
title_format = "## [{version}] - {project_date}"
underlines = ["", "", ""]
wrap = true
[[tool.towncrier.type]]
directory = "added"
name = "Added"
showcontent = true
[[tool.towncrier.type]]
directory = "changed"
name = "Changed"
showcontent = true
[[tool.towncrier.type]]
directory = "deprecated"
name = "Deprecated"
showcontent = true
[[tool.towncrier.type]]
directory = "removed"
name = "Removed"
showcontent = true
[[tool.towncrier.type]]
directory = "fixed"
name = "Fixed"
showcontent = true
[[tool.towncrier.type]]
directory = "security"
name = "Security"
showcontent = true

16
uv.lock generated
View File

@@ -4658,6 +4658,7 @@ dev = [
{ name = "ruff" },
{ name = "setuptools" },
{ name = "setuptools-scm" },
{ name = "towncrier" },
]
docs = [
{ name = "sphinx", version = "8.1.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
@@ -4792,6 +4793,7 @@ dev = [
{ name = "ruff", specifier = ">=0.12.11,<1" },
{ name = "setuptools", specifier = "~=78.1.1" },
{ name = "setuptools-scm", specifier = "~=8.3.1" },
{ name = "towncrier", specifier = "~=25.8.0" },
]
docs = [
{ name = "sphinx", specifier = ">=8.1.3" },
@@ -7251,6 +7253,20 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/c1/7b/30d423bdb2546250d719d7821aaf9058cc093d165565b245b159c788a9dd/torchvision-0.22.0-cp313-cp313t-win_amd64.whl", hash = "sha256:e5d680162694fac4c8a374954e261ddfb4eb0ce103287b0f693e4e9c579ef957", size = 1638621, upload-time = "2025-04-23T14:41:46.06Z" },
]
[[package]]
name = "towncrier"
version = "25.8.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "click" },
{ name = "jinja2" },
{ name = "tomli", marker = "python_full_version < '3.11'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/c2/eb/5bf25a34123698d3bbab39c5bc5375f8f8bcbcc5a136964ade66935b8b9d/towncrier-25.8.0.tar.gz", hash = "sha256:eef16d29f831ad57abb3ae32a0565739866219f1ebfbdd297d32894eb9940eb1", size = 76322, upload-time = "2025-08-30T11:41:55.393Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/42/06/8ba22ec32c74ac1be3baa26116e3c28bc0e76a5387476921d20b6fdade11/towncrier-25.8.0-py3-none-any.whl", hash = "sha256:b953d133d98f9aeae9084b56a3563fd2519dfc6ec33f61c9cd2c61ff243fb513", size = 65101, upload-time = "2025-08-30T11:41:53.644Z" },
]
[[package]]
name = "tqdm"
version = "4.67.1"