agent-cli 0.68.4__tar.gz → 0.69.0__tar.gz

{agent_cli-0.68.4/agent_cli/dev/skill → agent_cli-0.69.0/.claude/skills/agent-cli-dev}/SKILL.md

@@ -34,14 +34,19 @@ Do NOT spawn when:
 
 ## Core command
 
-For short prompts:
+For new features (starts from origin/main):
 ```bash
-agent-cli dev new <branch-name> --agent --prompt "Fix the login bug"
+agent-cli dev new <branch-name> --agent --prompt "Implement the new feature..."
+```
+
+For work on current branch (review, test, fix) - use `--from HEAD`:
+```bash
+agent-cli dev new <branch-name> --from HEAD --agent --prompt "Review/test/fix..."
 ```
 
 For longer prompts (recommended for multi-line or complex instructions):
 ```bash
-agent-cli dev new <branch-name> --agent --prompt-file path/to/prompt.md
+agent-cli dev new <branch-name> --from HEAD --agent --prompt-file path/to/prompt.md
 ```
 
 This creates:
@@ -129,7 +134,7 @@ Each agent works independently in its own branch. Results can be reviewed and me
 | `--agent` / `-a` | Start AI coding agent after creation |
 | `--prompt` / `-p` | Initial prompt for the agent (short prompts only) |
 | `--prompt-file` / `-P` | Read prompt from file (recommended for longer prompts) |
-| `--from` / `-f` | Base branch (default: origin/main) |
+| `--from` / `-f` | Base ref (default: origin/main). **Use `--from HEAD` when reviewing/testing current branch!** |
 | `--with-agent` | Specific agent: claude, aider, codex, gemini |
 | `--agent-args` | Extra arguments for the agent |
 

{agent_cli-0.68.4 → agent_cli-0.69.0}/.claude/skills/agent-cli-dev/examples.md

@@ -20,7 +20,68 @@ Each prompt for a spawned agent should follow this structure:
 5. **Focused scope** - Keep solutions minimal, implement only what's requested
 6. **Structured report** - Write conclusions to `.claude/REPORT.md`
 
-## Scenario 1: Multi-feature implementation
+## Scenario 1: Code review of current branch
+
+**User request**: "Review the code on this branch" or "Spawn an agent to review my changes"
+
+**CRITICAL**: Use `--from HEAD` (or the branch name) so the review agent has access to the changes!
+
+```bash
+# Review the current branch - MUST use --from HEAD
+agent-cli dev new review-changes --from HEAD --agent --prompt "Review the code changes on this branch.
+
+<workflow>
+- Run git diff origin/main...HEAD to identify all changes
+- Read changed files in parallel to understand context
+- Check CLAUDE.md for project-specific guidelines
+- Test changes with real services if applicable
+</workflow>
+
+<code_exploration>
+- Use git diff origin/main...HEAD to see the full diff
+- Read each changed file completely before judging
+- Look at surrounding code to understand patterns
+- Check existing tests to understand expected behavior
+</code_exploration>
+
+<context>
+Code review catches issues before merge. Focus on real problems - not style nitpicks. Apply these criteria:
+- Code cleanliness: Is the implementation clean and well-structured?
+- DRY principle: Does it avoid duplication?
+- Code reuse: Are there parts that should be reused from other places?
+- Organization: Is everything in the right place?
+- Consistency: Is it in the same style as other parts of the codebase?
+- Simplicity: Is it over-engineered? Remember KISS and YAGNI. No dead code paths, no defensive programming.
+- No pointless wrappers: Functions that just call another function should be inlined.
+- User experience: Does it provide a good user experience?
+- Tests: Are tests meaningful or just trivial coverage?
+- Live tests: Test changes with real services if applicable.
+- Rules: Does the code follow CLAUDE.md guidelines?
+</context>
+
+<scope>
+Review only - identify issues but do not fix them. Write findings to report.
+</scope>
+
+<report>
+Write your review to .claude/REPORT.md:
+
+## Summary
+[Overall assessment of the changes]
+
+## Issues Found
+| Severity | File:Line | Issue | Suggestion |
+|----------|-----------|-------|------------|
+| Critical/High/Medium/Low | path:123 | description | fix |
+
+## Positive Observations
+[What's well done]
+</report>"
+```
+
+**Common mistake**: Forgetting `--from HEAD` means the agent starts from `origin/main` and won't see any of the branch changes!
+
+## Scenario 2: Multi-feature implementation
 
 **User request**: "Implement user auth, payment processing, and email notifications"
 
@@ -169,7 +230,7 @@ After verifying tests pass, write to .claude/REPORT.md with summary, files chang
 </report>"
 ```
 
-## Scenario 2: Test-driven development
+## Scenario 3: Test-driven development
 
 **User request**: "Add a caching layer with comprehensive tests"
 
@@ -289,7 +350,7 @@ After ALL tests pass, write to .claude/REPORT.md:
 </report>"
 ```
 
-## Scenario 3: Large refactoring by module
+## Scenario 4: Large refactoring by module
 
 **User request**: "Refactor the API to use consistent error handling"
 
@@ -357,7 +418,7 @@ After tests pass and linting is clean, write to .claude/REPORT.md:
 </report>"
 ```
 
-## Scenario 4: Documentation and implementation in parallel
+## Scenario 5: Documentation and implementation in parallel
 
 **User request**: "Add a plugin system with documentation"
 

{agent_cli-0.68.4/.claude → agent_cli-0.69.0/.claude-plugin}/skills/agent-cli-dev/SKILL.md

@@ -34,14 +34,19 @@ Do NOT spawn when:
 
 ## Core command
 
-For short prompts:
+For new features (starts from origin/main):
 ```bash
-agent-cli dev new <branch-name> --agent --prompt "Fix the login bug"
+agent-cli dev new <branch-name> --agent --prompt "Implement the new feature..."
+```
+
+For work on current branch (review, test, fix) - use `--from HEAD`:
+```bash
+agent-cli dev new <branch-name> --from HEAD --agent --prompt "Review/test/fix..."
 ```
 
 For longer prompts (recommended for multi-line or complex instructions):
 ```bash
-agent-cli dev new <branch-name> --agent --prompt-file path/to/prompt.md
+agent-cli dev new <branch-name> --from HEAD --agent --prompt-file path/to/prompt.md
 ```
 
 This creates:
@@ -129,7 +134,7 @@ Each agent works independently in its own branch. Results can be reviewed and me
 | `--agent` / `-a` | Start AI coding agent after creation |
 | `--prompt` / `-p` | Initial prompt for the agent (short prompts only) |
 | `--prompt-file` / `-P` | Read prompt from file (recommended for longer prompts) |
-| `--from` / `-f` | Base branch (default: origin/main) |
+| `--from` / `-f` | Base ref (default: origin/main). **Use `--from HEAD` when reviewing/testing current branch!** |
 | `--with-agent` | Specific agent: claude, aider, codex, gemini |
 | `--agent-args` | Extra arguments for the agent |
 

{agent_cli-0.68.4 → agent_cli-0.69.0}/.claude-plugin/skills/agent-cli-dev/examples.md

@@ -20,7 +20,68 @@ Each prompt for a spawned agent should follow this structure:
 5. **Focused scope** - Keep solutions minimal, implement only what's requested
 6. **Structured report** - Write conclusions to `.claude/REPORT.md`
 
-## Scenario 1: Multi-feature implementation
+## Scenario 1: Code review of current branch
+
+**User request**: "Review the code on this branch" or "Spawn an agent to review my changes"
+
+**CRITICAL**: Use `--from HEAD` (or the branch name) so the review agent has access to the changes!
+
+```bash
+# Review the current branch - MUST use --from HEAD
+agent-cli dev new review-changes --from HEAD --agent --prompt "Review the code changes on this branch.
+
+<workflow>
+- Run git diff origin/main...HEAD to identify all changes
+- Read changed files in parallel to understand context
+- Check CLAUDE.md for project-specific guidelines
+- Test changes with real services if applicable
+</workflow>
+
+<code_exploration>
+- Use git diff origin/main...HEAD to see the full diff
+- Read each changed file completely before judging
+- Look at surrounding code to understand patterns
+- Check existing tests to understand expected behavior
+</code_exploration>
+
+<context>
+Code review catches issues before merge. Focus on real problems - not style nitpicks. Apply these criteria:
+- Code cleanliness: Is the implementation clean and well-structured?
+- DRY principle: Does it avoid duplication?
+- Code reuse: Are there parts that should be reused from other places?
+- Organization: Is everything in the right place?
+- Consistency: Is it in the same style as other parts of the codebase?
+- Simplicity: Is it over-engineered? Remember KISS and YAGNI. No dead code paths, no defensive programming.
+- No pointless wrappers: Functions that just call another function should be inlined.
+- User experience: Does it provide a good user experience?
+- Tests: Are tests meaningful or just trivial coverage?
+- Live tests: Test changes with real services if applicable.
+- Rules: Does the code follow CLAUDE.md guidelines?
+</context>
+
+<scope>
+Review only - identify issues but do not fix them. Write findings to report.
+</scope>
+
+<report>
+Write your review to .claude/REPORT.md:
+
+## Summary
+[Overall assessment of the changes]
+
+## Issues Found
+| Severity | File:Line | Issue | Suggestion |
+|----------|-----------|-------|------------|
+| Critical/High/Medium/Low | path:123 | description | fix |
+
+## Positive Observations
+[What's well done]
+</report>"
+```
+
+**Common mistake**: Forgetting `--from HEAD` means the agent starts from `origin/main` and won't see any of the branch changes!
+
+## Scenario 2: Multi-feature implementation
 
 **User request**: "Implement user auth, payment processing, and email notifications"
 
@@ -169,7 +230,7 @@ After verifying tests pass, write to .claude/REPORT.md with summary, files chang
 </report>"
 ```
 
-## Scenario 2: Test-driven development
+## Scenario 3: Test-driven development
 
 **User request**: "Add a caching layer with comprehensive tests"
 
@@ -289,7 +350,7 @@ After ALL tests pass, write to .claude/REPORT.md:
 </report>"
 ```
 
-## Scenario 3: Large refactoring by module
+## Scenario 4: Large refactoring by module
 
 **User request**: "Refactor the API to use consistent error handling"
 
@@ -357,7 +418,7 @@ After tests pass and linting is clean, write to .claude/REPORT.md:
 </report>"
 ```
 
-## Scenario 4: Documentation and implementation in parallel
+## Scenario 5: Documentation and implementation in parallel
 
 **User request**: "Add a plugin system with documentation"
 

{agent_cli-0.68.4 → agent_cli-0.69.0}/.pre-commit-config.yaml

@@ -8,7 +8,7 @@ repos:
       - id: end-of-file-fixer
       - id: mixed-line-ending
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: "v0.14.13"
+    rev: "v0.14.14"
     hooks:
       - id: ruff
         args: ["--fix"]

{agent_cli-0.68.4 → agent_cli-0.69.0}/CLAUDE.md

@@ -12,7 +12,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 - Run `pre-commit run --all-files` before committing
 - Use `git add <specific-file>` not `git add .`
 - CLI help in README.md is auto-generated - don't edit manually
-- Keep CLI startup fast (<300ms) - use top-level imports by default, only use lazy imports when a heavy dependency actually causes slowdown
+- Keep CLI startup fast (<300ms) - use top-level imports by default for first-party and stdlib imports, use lazy imports for ALL 3rd party dependencies (except pydantic, typer, and rich)
 - External library assumptions (especially in `dev` command for terminals/editors/agents) must be backed by evidence (official docs, man pages, source code). Document evidence in test docstrings that also verify the implementation.
 - Private functions (`_name`) don't need parameter documentation in docstrings - a one-line description is sufficient
 

{agent_cli-0.68.4 → agent_cli-0.69.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agent-cli
-Version: 0.68.4
+Version: 0.69.0
 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>
@@ -13,6 +13,7 @@ Requires-Dist: pydantic
 Requires-Dist: pyperclip
 Requires-Dist: rich
 Requires-Dist: setproctitle
+Requires-Dist: typer
 Requires-Dist: typer-slim[standard]
 Provides-Extra: audio
 Requires-Dist: numpy; extra == 'audio'
@@ -20,9 +21,10 @@ Requires-Dist: sounddevice>=0.4.6; extra == 'audio'
 Requires-Dist: wyoming>=1.5.2; extra == 'audio'
 Provides-Extra: dev
 Requires-Dist: markdown-code-runner>=2.7.0; extra == 'dev'
+Requires-Dist: markdown-gfm-admonition; extra == 'dev'
 Requires-Dist: notebook; extra == 'dev'
+Requires-Dist: pre-commit-uv>=4.1.4; extra == 'dev'
 Requires-Dist: pre-commit>=3.0.0; extra == 'dev'
-Requires-Dist: pydantic-ai-slim[openai]; extra == 'dev'
 Requires-Dist: pylint>=3.0.0; extra == 'dev'
 Requires-Dist: pytest-asyncio>=0.20.0; extra == 'dev'
 Requires-Dist: pytest-cov>=4.0.0; extra == 'dev'
@@ -31,6 +33,7 @@ Requires-Dist: pytest-timeout; extra == 'dev'
 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: faster-whisper
 Requires-Dist: fastapi[standard]; extra == 'faster-whisper'
 Requires-Dist: faster-whisper>=1.0.0; extra == 'faster-whisper'
@@ -70,7 +73,6 @@ Requires-Dist: fastapi[standard]; extra == 'server'
 Provides-Extra: speed
 Requires-Dist: audiostretchy>=1.3.0; extra == 'speed'
 Provides-Extra: test
-Requires-Dist: pydantic-ai-slim[openai]; extra == 'test'
 Requires-Dist: pytest-asyncio>=0.20.0; extra == 'test'
 Requires-Dist: pytest-cov>=4.0.0; extra == 'test'
 Requires-Dist: pytest-mock; extra == 'test'
@@ -496,9 +498,12 @@ agent-cli install-extras rag memory vad
 
  Install optional extras (rag, memory, vad, etc.) with pinned versions.
 
- Examples: agent-cli install-extras rag           # Install RAG dependencies agent-cli
- install-extras memory vad    # Install multiple extras agent-cli install-extras --list
- # Show available extras agent-cli install-extras --all         # Install all extras
+ Examples:
+
+  • agent-cli install-extras rag           # Install RAG dependencies
+  • agent-cli install-extras memory vad    # Install multiple extras
+  • agent-cli install-extras --list        # Show available extras
+  • agent-cli install-extras --all         # Install all extras
 
 ╭─ Arguments ────────────────────────────────────────────────────────────────────────────╮
 │   extras      [EXTRAS]...  Extras to install                                           │

{agent_cli-0.68.4 → agent_cli-0.69.0}/README.md

@@ -414,9 +414,12 @@ agent-cli install-extras rag memory vad
 
  Install optional extras (rag, memory, vad, etc.) with pinned versions.
 
- Examples: agent-cli install-extras rag           # Install RAG dependencies agent-cli
- install-extras memory vad    # Install multiple extras agent-cli install-extras --list
- # Show available extras agent-cli install-extras --all         # Install all extras
+ Examples:
+
+  • agent-cli install-extras rag           # Install RAG dependencies
+  • agent-cli install-extras memory vad    # Install multiple extras
+  • agent-cli install-extras --list        # Show available extras
+  • agent-cli install-extras --all         # Install all extras
 
 ╭─ Arguments ────────────────────────────────────────────────────────────────────────────╮
 │   extras      [EXTRAS]...  Extras to install                                           │

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/_requirements/audio.txt

@@ -11,7 +11,9 @@ certifi==2026.1.4
 cffi==2.0.0
     # via sounddevice
 click==8.3.1
-    # via typer-slim
+    # via
+    #   typer
+    #   typer-slim
 colorama==0.4.6 ; sys_platform == 'win32'
     # via click
 dotenv==0.9.9
@@ -49,13 +51,18 @@ python-dotenv==1.2.1
 rich==14.2.0
     # via
     #   agent-cli
+    #   typer
     #   typer-slim
 setproctitle==1.3.7
     # via agent-cli
 shellingham==1.5.4
-    # via typer-slim
+    # via
+    #   typer
+    #   typer-slim
 sounddevice==0.5.3
     # via agent-cli
+typer==0.21.1
+    # via agent-cli
 typer-slim==0.21.1
     # via agent-cli
 typing-extensions==4.15.0
@@ -63,6 +70,7 @@ typing-extensions==4.15.0
     #   anyio
     #   pydantic
     #   pydantic-core
+    #   typer
     #   typer-slim
     #   typing-inspection
 typing-inspection==0.4.2

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/_requirements/faster-whisper.txt

@@ -176,6 +176,7 @@ tqdm==4.67.1
     #   huggingface-hub
 typer==0.21.1
     # via
+    #   agent-cli
     #   fastapi-cli
     #   fastapi-cloud-cli
 typer-slim==0.21.1

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/_requirements/kokoro.txt

@@ -367,6 +367,7 @@ triton==3.5.1 ; platform_machine == 'x86_64' and sys_platform == 'linux'
     # via torch
 typer==0.21.1
     # via
+    #   agent-cli
     #   fastapi-cli
     #   fastapi-cloud-cli
 typer-slim==0.21.1

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/_requirements/llm.txt

@@ -23,6 +23,7 @@ charset-normalizer==3.4.4
 click==8.3.1
     # via
     #   ddgs
+    #   typer
     #   typer-slim
 colorama==0.4.6
     # via
@@ -132,13 +133,16 @@ requests==2.32.5
 rich==14.2.0
     # via
     #   agent-cli
+    #   typer
     #   typer-slim
 rsa==4.9.1
     # via google-auth
 setproctitle==1.3.7
     # via agent-cli
 shellingham==1.5.4
-    # via typer-slim
+    # via
+    #   typer
+    #   typer-slim
 sniffio==1.3.1
     # via
     #   google-genai
@@ -151,6 +155,8 @@ tiktoken==0.12.0
     # via pydantic-ai-slim
 tqdm==4.67.1
     # via openai
+typer==0.21.1
+    # via agent-cli
 typer-slim==0.21.1
     # via agent-cli
 typing-extensions==4.15.0
@@ -161,6 +167,7 @@ typing-extensions==4.15.0
     #   opentelemetry-api
     #   pydantic
     #   pydantic-core
+    #   typer
     #   typer-slim
     #   typing-inspection
 typing-inspection==0.4.2

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/_requirements/memory.txt

@@ -300,6 +300,7 @@ transformers==4.57.5
     # via agent-cli
 typer==0.21.1
     # via
+    #   agent-cli
     #   chromadb
     #   fastapi-cli
     #   fastapi-cloud-cli

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/_requirements/mlx-whisper.txt

@@ -180,8 +180,9 @@ tqdm==4.67.1 ; platform_machine == 'arm64' and sys_platform == 'darwin'
     # via
     #   huggingface-hub
     #   mlx-whisper
-typer==0.21.1 ; platform_machine == 'arm64' and sys_platform == 'darwin'
+typer==0.21.1
     # via
+    #   agent-cli
     #   fastapi-cli
     #   fastapi-cloud-cli
 typer-slim==0.21.1

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/_requirements/piper.txt

@@ -140,6 +140,7 @@ sympy==1.14.0
     # via onnxruntime
 typer==0.21.1
     # via
+    #   agent-cli
     #   fastapi-cli
     #   fastapi-cloud-cli
 typer-slim==0.21.1

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/_requirements/rag.txt

@@ -343,6 +343,7 @@ transformers==4.57.5
     # via agent-cli
 typer==0.21.1
     # via
+    #   agent-cli
     #   chromadb
     #   fastapi-cli
     #   fastapi-cloud-cli

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/_requirements/server.txt

@@ -118,6 +118,7 @@ starlette==0.50.0
     # via fastapi
 typer==0.21.1
     # via
+    #   agent-cli
     #   fastapi-cli
     #   fastapi-cloud-cli
 typer-slim==0.21.1

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/_requirements/speed.txt

@@ -11,7 +11,9 @@ certifi==2026.1.4
     #   httpcore
     #   httpx
 click==8.3.1
-    # via typer-slim
+    # via
+    #   typer
+    #   typer-slim
 colorama==0.4.6 ; sys_platform == 'win32'
     # via click
 dotenv==0.9.9
@@ -49,13 +51,18 @@ python-dotenv==1.2.1
 rich==14.2.0
     # via
     #   agent-cli
+    #   typer
     #   typer-slim
 setproctitle==1.3.7
     # via agent-cli
 shellingham==1.5.4
-    # via typer-slim
+    # via
+    #   typer
+    #   typer-slim
 termcolor==3.3.0
     # via fire
+typer==0.21.1
+    # via agent-cli
 typer-slim==0.21.1
     # via agent-cli
 typing-extensions==4.15.0
@@ -63,6 +70,7 @@ typing-extensions==4.15.0
     #   anyio
     #   pydantic
     #   pydantic-core
+    #   typer
     #   typer-slim
     #   typing-inspection
 typing-inspection==0.4.2

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/_requirements/vad.txt

@@ -9,7 +9,9 @@ certifi==2026.1.4
     #   httpcore
     #   httpx
 click==8.3.1
-    # via typer-slim
+    # via
+    #   typer
+    #   typer-slim
 colorama==0.4.6 ; sys_platform == 'win32'
     # via click
 coloredlogs==15.0.1
@@ -112,13 +114,16 @@ python-dotenv==1.2.1
 rich==14.2.0
     # via
     #   agent-cli
+    #   typer
     #   typer-slim
 setproctitle==1.3.7
     # via agent-cli
 setuptools==80.9.0 ; python_full_version >= '3.12'
     # via torch
 shellingham==1.5.4
-    # via typer-slim
+    # via
+    #   typer
+    #   typer-slim
 silero-vad==6.2.0
     # via agent-cli
 sympy==1.14.0
@@ -133,6 +138,8 @@ torchaudio==2.9.1
     # via silero-vad
 triton==3.5.1 ; platform_machine == 'x86_64' and sys_platform == 'linux'
     # via torch
+typer==0.21.1
+    # via agent-cli
 typer-slim==0.21.1
     # via agent-cli
 typing-extensions==4.15.0
@@ -141,6 +148,7 @@ typing-extensions==4.15.0
     #   pydantic
     #   pydantic-core
     #   torch
+    #   typer
     #   typer-slim
     #   typing-inspection
 typing-inspection==0.4.2

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/agents/autocorrect.py

@@ -9,7 +9,6 @@ import sys
 import time
 from typing import TYPE_CHECKING
 
-import pyperclip
 import typer
 
 from agent_cli import config, opts
@@ -118,6 +117,8 @@ def _display_result(
 ) -> None:
     """Handle output and clipboard copying based on desired verbosity."""
     if clipboard:
+        import pyperclip  # noqa: PLC0415
+
         pyperclip.copy(corrected_text)
 
     if simple_output:

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/agents/memory/__init__.py

@@ -10,6 +10,7 @@ from agent_cli.core.process import set_process_title
 memory_app = typer.Typer(
     name="memory",
     help="Memory system operations (add, proxy, etc.).",
+    add_completion=True,
     rich_markup_mode="markdown",
     no_args_is_help=True,
 )

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/agents/memory/proxy.py

@@ -11,7 +11,7 @@ from rich.logging import RichHandler
 from agent_cli import constants, opts
 from agent_cli.agents.memory import memory_app
 from agent_cli.core.deps import requires_extras
-from agent_cli.core.utils import console, print_command_line_args, print_error_message
+from agent_cli.core.utils import console, print_command_line_args
 
 
 @memory_app.command("proxy")
@@ -105,17 +105,10 @@ def proxy(
     if print_args:
         print_command_line_args(locals())
 
-    try:
-        import uvicorn  # noqa: PLC0415
-
-        from agent_cli.memory._files import ensure_store_dirs  # noqa: PLC0415
-        from agent_cli.memory.api import create_app  # noqa: PLC0415
-    except ImportError as exc:
-        print_error_message(
-            "Memory dependencies are not installed. Please install with "
-            "`pip install agent-cli[memory]` or `uv sync --extra memory`.",
-        )
-        raise typer.Exit(1) from exc
+    import uvicorn  # noqa: PLC0415
+
+    from agent_cli.memory._files import ensure_store_dirs  # noqa: PLC0415
+    from agent_cli.memory.api import create_app  # noqa: PLC0415
 
     logging.basicConfig(
         level=log_level.upper(),

{agent_cli-0.68.4 → agent_cli-0.69.0}/agent_cli/agents/rag_proxy.py

@@ -77,16 +77,9 @@ def rag_proxy(
     logging.getLogger("chromadb").setLevel(logging.WARNING)
     logging.getLogger("uvicorn.access").setLevel(logging.WARNING)
 
-    try:
-        import uvicorn  # noqa: PLC0415
+    import uvicorn  # noqa: PLC0415
 
-        from agent_cli.rag.api import create_app  # noqa: PLC0415
-    except ImportError as exc:
-        print_error_message(
-            "RAG dependencies are not installed. Please install with "
-            "`pip install agent-cli[rag]` or `uv sync --extra rag`.",
-        )
-        raise typer.Exit(1) from exc
+    from agent_cli.rag.api import create_app  # noqa: PLC0415
 
     docs_folder = docs_folder.resolve()
     chroma_path = chroma_path.resolve()