agent-cli 0.89.0__tar.gz → 0.91.0__tar.gz

{agent_cli-0.89.0 → agent_cli-0.91.0}/.github/scripts/sync_extras.py

@@ -38,6 +38,7 @@ EXTRA_METADATA: dict[str, tuple[str, list[str]]] = {
     "rag": ("RAG proxy (ChromaDB, embeddings)", ["chromadb", "pydantic_ai"]),
     "memory": ("Long-term memory proxy", ["chromadb", "yaml", "pydantic_ai"]),
     "vad": ("Voice Activity Detection (Silero VAD via ONNX)", ["onnxruntime"]),
+    "diarization": ("Speaker diarization (pyannote.audio)", ["pyannote.audio"]),
     "whisper": ("Local Whisper ASR (faster-whisper)", ["faster_whisper"]),
     "whisper-mlx": ("MLX Whisper for Apple Silicon", ["mlx_whisper"]),
     "tts": ("Local Piper TTS", ["piper"]),

{agent_cli-0.89.0 → agent_cli-0.91.0}/.github/workflows/docs.yml

@@ -32,7 +32,7 @@ jobs:
           lfs: true
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@v8.1.0
 
       - name: Set up Python
         run: uv python install 3.12

{agent_cli-0.89.0 → agent_cli-0.91.0}/.github/workflows/markdown-code-runner.yml

@@ -22,7 +22,7 @@ jobs:
           python-version: "3.13.11"
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@v8.1.0
 
       - name: Run markdown-code-runner
         env:

{agent_cli-0.89.0 → agent_cli-0.91.0}/.github/workflows/pytest.yml

@@ -27,15 +27,15 @@ jobs:
         if: matrix.os == 'ubuntu-latest'
         run: sudo apt-get update && sudo apt-get install -y portaudio19-dev
       - name: Install uv
-        uses: astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@v8.1.0
       - name: Run pytest (macOS - all extras)
         if: matrix.os == 'macos-latest'
         run: uv run --all-extras pytest -vvv
       - name: Run pytest (non-macOS - exclude mlx-whisper)
         if: matrix.os != 'macos-latest'
-        run: uv run --extra audio --extra llm --extra rag --extra memory --extra vad --extra faster-whisper --extra piper --extra kokoro --extra server --extra speed --extra test pytest -vvv
+        run: uv run --extra audio --extra diarization --extra llm --extra rag --extra memory --extra vad --extra faster-whisper --extra piper --extra kokoro --extra server --extra speed --extra test pytest -vvv
       - name: Upload coverage reports to Codecov
         if: matrix.os == 'ubuntu-latest' && matrix.python-version == '3.13'
-        uses: codecov/codecov-action@v5
+        uses: codecov/codecov-action@v6
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

{agent_cli-0.89.0 → agent_cli-0.91.0}/.github/workflows/release.yml

@@ -15,7 +15,7 @@ jobs:
     steps:
       - uses: actions/checkout@v6
       - name: Install uv
-        uses: astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@v8.1.0
       - name: Build
         run: uv build
       - name: Publish package distributions to PyPI

{agent_cli-0.89.0 → agent_cli-0.91.0}/.pre-commit-config.yaml

@@ -11,13 +11,13 @@ repos:
       - id: end-of-file-fixer
       - id: mixed-line-ending
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: "v0.15.11"
+    rev: "v0.15.12"
     hooks:
       - id: ruff
         args: ["--fix"]
       - id: ruff-format
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: "v1.20.1"
+    rev: "v1.20.2"
     hooks:
       - id: mypy
         additional_dependencies: ["types-PyYAML"]

{agent_cli-0.89.0 → agent_cli-0.91.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agent-cli
-Version: 0.89.0
+Version: 0.91.0
 Summary: A suite of AI-powered command-line tools for text correction, audio transcription, and voice assistance.
 Project-URL: Homepage, https://github.com/basnijholt/agent-cli
 Author-email: Bas Nijholt <bas@nijho.lt>
@@ -34,6 +34,8 @@ Requires-Dist: pytest>=7.0.0; extra == 'dev'
 Requires-Dist: ruff; extra == 'dev'
 Requires-Dist: versioningit; extra == 'dev'
 Requires-Dist: zensical; extra == 'dev'
+Provides-Extra: diarization
+Requires-Dist: pyannote-audio>=3.3; extra == 'diarization'
 Provides-Extra: faster-whisper
 Requires-Dist: fastapi[standard]; extra == 'faster-whisper'
 Requires-Dist: faster-whisper>=1.0.0; extra == 'faster-whisper'
@@ -261,6 +263,7 @@ The setup scripts automatically install:
   - [Installation Commands](#installation-commands)
     - [Installing Optional Extras](#installing-optional-extras)
   - [Configuration](#configuration)
+    - [Environment variable overrides](#environment-variable-overrides)
     - [Managing Configuration](#managing-configuration)
     - [Provider Defaults](#provider-defaults)
   - [`autocorrect`](#autocorrect)
@@ -526,6 +529,7 @@ agent-cli install-extras rag memory vad
  Available extras:
 
   • audio - Audio recording/playback
+  • diarization - Speaker diarization (pyannote.audio)
   • faster-whisper - Whisper ASR via CTranslate2
   • kokoro - Kokoro neural TTS (GPU)
   • llm - LLM framework (pydantic-ai)
@@ -550,9 +554,9 @@ agent-cli install-extras rag memory vad
 
 
 ╭─ Arguments ────────────────────────────────────────────────────────────────────────────╮
-│   extras      [EXTRAS]...  Extras to install: audio, faster-whisper, kokoro, llm,      │
-│                            memory, mlx-whisper, piper, rag, server, speed, vad,        │
-│                            vectordb, whisper-transformers, wyoming                     │
+│   extras      [EXTRAS]...  Extras to install: audio, diarization, faster-whisper,      │
+│                            kokoro, llm, memory, mlx-whisper, piper, rag, server,       │
+│                            speed, vad, vectordb, whisper-transformers, wyoming         │
 ╰────────────────────────────────────────────────────────────────────────────────────────╯
 ╭─ Options ──────────────────────────────────────────────────────────────────────────────╮
 │ --list  -l        Show available extras with descriptions (what each one enables)      │
@@ -568,15 +572,36 @@ agent-cli install-extras rag memory vad
 
 ### Configuration
 
-All `agent-cli` commands can be configured using a TOML file. The configuration file is searched for in the following locations, in order:
+All `agent-cli` commands can be configured using a TOML file.
+The configuration file is searched for in the following locations, in order:
 
-1.  `./agent-cli-config.toml` (in the current directory)
-2.  `~/.config/agent-cli/config.toml`
+1.  CLI flag (`--config` on agent commands, `--path` on `agent-cli config ...`)
+2.  `$AGENT_CLI_CONFIG_HOME/config.toml` if set
+3.  `./agent-cli-config.toml` (in the current directory)
+4.  `$XDG_CONFIG_HOME/agent-cli/config.toml` if `XDG_CONFIG_HOME` is set and non-empty, otherwise `~/.config/agent-cli/config.toml`
 
 You can also specify a path to a configuration file using the `--config` option, e.g., `agent-cli transcribe --config /path/to/your/config.toml`.
 
 Command-line options always take precedence over settings in the configuration file.
 
+#### Environment variable overrides
+
+Use `AGENT_CLI_CONFIG_HOME` to redirect the user-level config to a directory of your choice:
+
+```bash
+# use a project-scoped config
+AGENT_CLI_CONFIG_HOME=./.agent-cli agent-cli chat ...
+```
+
+Use `XDG_CONFIG_HOME` to follow XDG-style config placement when no `AGENT_CLI_CONFIG_HOME` is set:
+
+```bash
+# follow XDG (e.g. inside a sandbox or container)
+XDG_CONFIG_HOME=/workspace/.config agent-cli chat ...
+```
+
+Config paths are resolved when `agent-cli` starts, so set these variables before invoking the command.
+
 #### Managing Configuration
 
 Use the `config` command to manage your configuration files:
@@ -617,11 +642,20 @@ agent-cli config edit
 
  Config files are TOML format and searched in order:
 
-  1 ./agent-cli-config.toml (project-local)
-  2 ~/.config/agent-cli/config.toml (user default)
+  1 $AGENT_CLI_CONFIG_HOME/config.toml (if set)
+  2 ./agent-cli-config.toml (project-local)
+  3 $XDG_CONFIG_HOME/agent-cli/config.toml (if set)
+  4 ~/.config/agent-cli/config.toml (user default)
+
+ Settings in [defaults] apply globally.
+
+ Use [chat] or [transcribe] for command-specific overrides.
 
- Settings in [defaults] apply to all commands. Override per-command with sections like
- [chat] or [transcribe]. CLI arguments override config file settings.
+ CLI arguments override config file settings.
+
+ Set env vars before startup.
+
+ Use $AGENT_CLI_CONFIG_HOME or $XDG_CONFIG_HOME to change config path.
 
 ╭─ Options ──────────────────────────────────────────────────────────────────────────────╮
 │ --help  -h        Show this message and exit.                                          │
@@ -836,7 +870,7 @@ the `[defaults]` section of your configuration file.
 │ --llm                   --no-llm          Clean up transcript with LLM: fix errors,    │
 │                                           add punctuation, remove filler words. Uses   │
 │                                           --extra-instructions if set (via CLI or      │
-│                                           config file).                                │
+│                                           config file). Not compatible with --diarize. │
 │                                           [default: no-llm]                            │
 ╰────────────────────────────────────────────────────────────────────────────────────────╯
 ╭─ Audio Recovery ───────────────────────────────────────────────────────────────────────╮
@@ -958,6 +992,44 @@ the `[defaults]` section of your configuration file.
 │                                                                  provide context for   │
 │                                                                  LLM cleanup.          │
 ╰────────────────────────────────────────────────────────────────────────────────────────╯
+╭─ Diarization ──────────────────────────────────────────────────────────────────────────╮
+│ --diarize           --no-diarize                       Enable speaker diarization      │
+│                                                        (requires pyannote-audio).      │
+│                                                        Install with: pip install       │
+│                                                        agent-cli[diarization]          │
+│                                                        [default: no-diarize]           │
+│ --diarize-format                        [inline|json]  Output format for diarization   │
+│                                                        ('inline' for [Speaker N]:      │
+│                                                        text, 'json' for structured     │
+│                                                        output).                        │
+│                                                        [default: inline]               │
+│ --hf-token                              TEXT           HuggingFace token for pyannote  │
+│                                                        models. Required for            │
+│                                                        diarization. Token must have    │
+│                                                        'Read access to contents of all │
+│                                                        public gated repos you can      │
+│                                                        access' permission. Accept      │
+│                                                        licenses at:                    │
+│                                                        https://hf.co/pyannote/speaker… │
+│                                                        https://hf.co/pyannote/segment… │
+│                                                        https://hf.co/pyannote/wespeak… │
+│                                                        [env var: HF_TOKEN]             │
+│ --min-speakers                          INTEGER        Minimum number of speakers      │
+│                                                        (optional hint for              │
+│                                                        diarization).                   │
+│ --max-speakers                          INTEGER        Maximum number of speakers      │
+│                                                        (optional hint for              │
+│                                                        diarization).                   │
+│ --align-words       --no-align-words                   Use wav2vec2 forced alignment   │
+│                                                        for word-level speaker          │
+│                                                        assignment (more accurate but   │
+│                                                        slower).                        │
+│                                                        [default: no-align-words]       │
+│ --align-language                        TEXT           Language code for word          │
+│                                                        alignment model (e.g., 'en',    │
+│                                                        'fr', 'de', 'es', 'it').        │
+│                                                        [default: en]                   │
+╰────────────────────────────────────────────────────────────────────────────────────────╯
 
 ```
 
@@ -1156,7 +1228,7 @@ uv tool install "agent-cli[vad]" -p 3.13
 ╭─ LLM Configuration ────────────────────────────────────────────────────────────────────╮
 │ --llm    --no-llm      Clean up transcript with LLM: fix errors, add punctuation,      │
 │                        remove filler words. Uses --extra-instructions if set (via CLI  │
-│                        or config file).                                                │
+│                        or config file). Not compatible with --diarize.                 │
 │                        [default: no-llm]                                               │
 ╰────────────────────────────────────────────────────────────────────────────────────────╯
 ╭─ Process Management ───────────────────────────────────────────────────────────────────╮

{agent_cli-0.89.0 → agent_cli-0.91.0}/README.md

@@ -158,6 +158,7 @@ The setup scripts automatically install:
   - [Installation Commands](#installation-commands)
     - [Installing Optional Extras](#installing-optional-extras)
   - [Configuration](#configuration)
+    - [Environment variable overrides](#environment-variable-overrides)
     - [Managing Configuration](#managing-configuration)
     - [Provider Defaults](#provider-defaults)
   - [`autocorrect`](#autocorrect)
@@ -423,6 +424,7 @@ agent-cli install-extras rag memory vad
  Available extras:
 
   • audio - Audio recording/playback
+  • diarization - Speaker diarization (pyannote.audio)
   • faster-whisper - Whisper ASR via CTranslate2
   • kokoro - Kokoro neural TTS (GPU)
   • llm - LLM framework (pydantic-ai)
@@ -447,9 +449,9 @@ agent-cli install-extras rag memory vad
 
 
 ╭─ Arguments ────────────────────────────────────────────────────────────────────────────╮
-│   extras      [EXTRAS]...  Extras to install: audio, faster-whisper, kokoro, llm,      │
-│                            memory, mlx-whisper, piper, rag, server, speed, vad,        │
-│                            vectordb, whisper-transformers, wyoming                     │
+│   extras      [EXTRAS]...  Extras to install: audio, diarization, faster-whisper,      │
+│                            kokoro, llm, memory, mlx-whisper, piper, rag, server,       │
+│                            speed, vad, vectordb, whisper-transformers, wyoming         │
 ╰────────────────────────────────────────────────────────────────────────────────────────╯
 ╭─ Options ──────────────────────────────────────────────────────────────────────────────╮
 │ --list  -l        Show available extras with descriptions (what each one enables)      │
@@ -465,15 +467,36 @@ agent-cli install-extras rag memory vad
 
 ### Configuration
 
-All `agent-cli` commands can be configured using a TOML file. The configuration file is searched for in the following locations, in order:
+All `agent-cli` commands can be configured using a TOML file.
+The configuration file is searched for in the following locations, in order:
 
-1.  `./agent-cli-config.toml` (in the current directory)
-2.  `~/.config/agent-cli/config.toml`
+1.  CLI flag (`--config` on agent commands, `--path` on `agent-cli config ...`)
+2.  `$AGENT_CLI_CONFIG_HOME/config.toml` if set
+3.  `./agent-cli-config.toml` (in the current directory)
+4.  `$XDG_CONFIG_HOME/agent-cli/config.toml` if `XDG_CONFIG_HOME` is set and non-empty, otherwise `~/.config/agent-cli/config.toml`
 
 You can also specify a path to a configuration file using the `--config` option, e.g., `agent-cli transcribe --config /path/to/your/config.toml`.
 
 Command-line options always take precedence over settings in the configuration file.
 
+#### Environment variable overrides
+
+Use `AGENT_CLI_CONFIG_HOME` to redirect the user-level config to a directory of your choice:
+
+```bash
+# use a project-scoped config
+AGENT_CLI_CONFIG_HOME=./.agent-cli agent-cli chat ...
+```
+
+Use `XDG_CONFIG_HOME` to follow XDG-style config placement when no `AGENT_CLI_CONFIG_HOME` is set:
+
+```bash
+# follow XDG (e.g. inside a sandbox or container)
+XDG_CONFIG_HOME=/workspace/.config agent-cli chat ...
+```
+
+Config paths are resolved when `agent-cli` starts, so set these variables before invoking the command.
+
 #### Managing Configuration
 
 Use the `config` command to manage your configuration files:
@@ -514,11 +537,20 @@ agent-cli config edit
 
  Config files are TOML format and searched in order:
 
-  1 ./agent-cli-config.toml (project-local)
-  2 ~/.config/agent-cli/config.toml (user default)
+  1 $AGENT_CLI_CONFIG_HOME/config.toml (if set)
+  2 ./agent-cli-config.toml (project-local)
+  3 $XDG_CONFIG_HOME/agent-cli/config.toml (if set)
+  4 ~/.config/agent-cli/config.toml (user default)
+
+ Settings in [defaults] apply globally.
+
+ Use [chat] or [transcribe] for command-specific overrides.
 
- Settings in [defaults] apply to all commands. Override per-command with sections like
- [chat] or [transcribe]. CLI arguments override config file settings.
+ CLI arguments override config file settings.
+
+ Set env vars before startup.
+
+ Use $AGENT_CLI_CONFIG_HOME or $XDG_CONFIG_HOME to change config path.
 
 ╭─ Options ──────────────────────────────────────────────────────────────────────────────╮
 │ --help  -h        Show this message and exit.                                          │
@@ -733,7 +765,7 @@ the `[defaults]` section of your configuration file.
 │ --llm                   --no-llm          Clean up transcript with LLM: fix errors,    │
 │                                           add punctuation, remove filler words. Uses   │
 │                                           --extra-instructions if set (via CLI or      │
-│                                           config file).                                │
+│                                           config file). Not compatible with --diarize. │
 │                                           [default: no-llm]                            │
 ╰────────────────────────────────────────────────────────────────────────────────────────╯
 ╭─ Audio Recovery ───────────────────────────────────────────────────────────────────────╮
@@ -855,6 +887,44 @@ the `[defaults]` section of your configuration file.
 │                                                                  provide context for   │
 │                                                                  LLM cleanup.          │
 ╰────────────────────────────────────────────────────────────────────────────────────────╯
+╭─ Diarization ──────────────────────────────────────────────────────────────────────────╮
+│ --diarize           --no-diarize                       Enable speaker diarization      │
+│                                                        (requires pyannote-audio).      │
+│                                                        Install with: pip install       │
+│                                                        agent-cli[diarization]          │
+│                                                        [default: no-diarize]           │
+│ --diarize-format                        [inline|json]  Output format for diarization   │
+│                                                        ('inline' for [Speaker N]:      │
+│                                                        text, 'json' for structured     │
+│                                                        output).                        │
+│                                                        [default: inline]               │
+│ --hf-token                              TEXT           HuggingFace token for pyannote  │
+│                                                        models. Required for            │
+│                                                        diarization. Token must have    │
+│                                                        'Read access to contents of all │
+│                                                        public gated repos you can      │
+│                                                        access' permission. Accept      │
+│                                                        licenses at:                    │
+│                                                        https://hf.co/pyannote/speaker… │
+│                                                        https://hf.co/pyannote/segment… │
+│                                                        https://hf.co/pyannote/wespeak… │
+│                                                        [env var: HF_TOKEN]             │
+│ --min-speakers                          INTEGER        Minimum number of speakers      │
+│                                                        (optional hint for              │
+│                                                        diarization).                   │
+│ --max-speakers                          INTEGER        Maximum number of speakers      │
+│                                                        (optional hint for              │
+│                                                        diarization).                   │
+│ --align-words       --no-align-words                   Use wav2vec2 forced alignment   │
+│                                                        for word-level speaker          │
+│                                                        assignment (more accurate but   │
+│                                                        slower).                        │
+│                                                        [default: no-align-words]       │
+│ --align-language                        TEXT           Language code for word          │
+│                                                        alignment model (e.g., 'en',    │
+│                                                        'fr', 'de', 'es', 'it').        │
+│                                                        [default: en]                   │
+╰────────────────────────────────────────────────────────────────────────────────────────╯
 
 ```
 
@@ -1053,7 +1123,7 @@ uv tool install "agent-cli[vad]" -p 3.13
 ╭─ LLM Configuration ────────────────────────────────────────────────────────────────────╮
 │ --llm    --no-llm      Clean up transcript with LLM: fix errors, add punctuation,      │
 │                        remove filler words. Uses --extra-instructions if set (via CLI  │
-│                        or config file).                                                │
+│                        or config file). Not compatible with --diarize.                 │
 │                        [default: no-llm]                                               │
 ╰────────────────────────────────────────────────────────────────────────────────────────╯
 ╭─ Process Management ───────────────────────────────────────────────────────────────────╮

{agent_cli-0.89.0 → agent_cli-0.91.0}/agent_cli/_extras.json

@@ -5,6 +5,12 @@
       "sounddevice"
     ]
   ],
+  "diarization": [
+    "Speaker diarization (pyannote.audio)",
+    [
+      "pyannote.audio"
+    ]
+  ],
   "faster-whisper": [
     "Whisper ASR via CTranslate2",
     [