mirror of
https://github.com/eyaltoledano/claude-task-master.git
synced 2026-01-30 06:12:05 +00:00
docs: auto-update documentation based on changes in next branch
This PR was automatically generated to update documentation based on recent changes. Original commit: chore: improve changeset\n\n Co-authored-by: Claude <claude-assistant@anthropic.com>
This commit is contained in:
@@ -47,7 +47,8 @@ Taskmaster uses two primary methods for configuration:
|
||||
"ollamaBaseURL": "http://localhost:11434/api",
|
||||
"azureBaseURL": "https://your-endpoint.azure.com/openai/deployments",
|
||||
"vertexProjectId": "your-gcp-project-id",
|
||||
"vertexLocation": "us-central1"
|
||||
"vertexLocation": "us-central1",
|
||||
"enableProxy": false
|
||||
}
|
||||
}
|
||||
```
|
||||
@@ -85,9 +86,77 @@ Taskmaster uses two primary methods for configuration:
|
||||
- `GOOGLE_APPLICATION_CREDENTIALS`: Path to service account credentials JSON file for Google Cloud auth (alternative to API key for Vertex AI).
|
||||
- **Optional Auto-Update Control:**
|
||||
- `TASKMASTER_SKIP_AUTO_UPDATE`: Set to '1' to disable automatic updates. Also automatically disabled in CI environments (when `CI` environment variable is set).
|
||||
- **Optional Proxy Configuration:**
|
||||
- `TASKMASTER_ENABLE_PROXY`: Set to 'true' to enable proxy support for AI provider API calls.
|
||||
- `http_proxy`: HTTP proxy URL (e.g., `http://proxy.company.com:8080`).
|
||||
- `https_proxy`: HTTPS proxy URL (e.g., `http://proxy.company.com:8080`).
|
||||
- `no_proxy`: Comma-separated list of hosts to bypass proxy (e.g., `localhost,127.0.0.1,.company.com`).
|
||||
|
||||
**Important:** Settings like model ID selections (`main`, `research`, `fallback`), `maxTokens`, `temperature`, `logLevel`, `defaultSubtasks`, `defaultPriority`, and `projectName` are **managed in `.taskmaster/config.json`** (or `.taskmasterconfig` for unmigrated projects), not environment variables.
|
||||
|
||||
## Proxy Configuration
|
||||
|
||||
Task Master includes comprehensive proxy support for corporate and restricted network environments. This is particularly useful when working behind corporate firewalls that require all HTTP/HTTPS traffic to go through a proxy server.
|
||||
|
||||
### Configuration Options
|
||||
|
||||
Proxy support can be enabled using either method, with environment variable taking priority:
|
||||
|
||||
**Method 1: Environment Variable (Recommended)**
|
||||
|
||||
```bash
|
||||
# Enable proxy support
|
||||
export TASKMASTER_ENABLE_PROXY=true
|
||||
|
||||
# Configure proxy settings
|
||||
export http_proxy=http://proxy.company.com:8080
|
||||
export https_proxy=http://proxy.company.com:8080
|
||||
|
||||
# Optional: bypass proxy for specific hosts
|
||||
export no_proxy=localhost,127.0.0.1,.company.com,internal.domain
|
||||
```
|
||||
|
||||
**Method 2: Configuration File**
|
||||
|
||||
```json
|
||||
{
|
||||
"global": {
|
||||
"enableProxy": true
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Technical Details
|
||||
|
||||
- **Implementation**: Uses undici's `EnvHttpProxyAgent` for automatic proxy detection
|
||||
- **Provider Coverage**: Supports all AI providers (OpenAI, Anthropic, Perplexity, Azure OpenAI, Google AI, Google Vertex AI, AWS Bedrock, OpenAI-compatible providers)
|
||||
- **Opt-in Design**: Users without proxy requirements are not affected
|
||||
- **Centralized**: Single implementation in `BaseAIProvider` ensures consistency
|
||||
|
||||
### Troubleshooting Proxy Issues
|
||||
|
||||
**Common proxy-related errors:**
|
||||
- `ECONNRESET`: Often indicates proxy configuration issues
|
||||
- `ECONNREFUSED`: Proxy server may be unreachable
|
||||
- `ENOTFOUND`: Proxy hostname resolution failure
|
||||
|
||||
**Solutions:**
|
||||
1. Verify proxy server address and port
|
||||
2. Check network connectivity to proxy server
|
||||
3. Ensure proxy supports HTTPS CONNECT method
|
||||
4. Test proxy settings with other tools (curl, wget)
|
||||
5. Check if authentication is required for your proxy
|
||||
|
||||
**Testing proxy configuration:**
|
||||
|
||||
```bash
|
||||
# Test with curl
|
||||
curl -x http://proxy.company.com:8080 https://api.anthropic.com/v1/health
|
||||
|
||||
# Test Task Master with proxy
|
||||
TASKMASTER_ENABLE_PROXY=true task-master next
|
||||
```
|
||||
|
||||
## Tagged Task Lists Configuration (v0.17+)
|
||||
|
||||
Taskmaster includes a tagged task lists system for multi-context task management.
|
||||
|
||||
@@ -27,6 +27,9 @@ description: "A comprehensive reference of all available Task Master commands"
|
||||
|
||||
# List tasks with a specific status and include subtasks
|
||||
task-master list --status=<status> --with-subtasks
|
||||
|
||||
# Output in JSON format (useful for AI agents and automation)
|
||||
task-master list --json
|
||||
```
|
||||
</Accordion>
|
||||
|
||||
@@ -46,6 +49,9 @@ description: "A comprehensive reference of all available Task Master commands"
|
||||
|
||||
# View a specific subtask (e.g., subtask 2 of task 1)
|
||||
task-master show 1.2
|
||||
|
||||
# Output in JSON format (useful for AI agents and automation)
|
||||
task-master show <id> --json
|
||||
```
|
||||
</Accordion>
|
||||
|
||||
|
||||
@@ -30,6 +30,7 @@ description: "Configure Task Master through environment variables in a .env file
|
||||
| `PROJECT_VERSION` | `"1.0.0"` | Version in metadata | `PROJECT_VERSION=2.1.0` |
|
||||
| `PERPLEXITY_API_KEY` | - | For research-backed features | `PERPLEXITY_API_KEY=pplx-...` |
|
||||
| `PERPLEXITY_MODEL` | `"sonar-medium-online"` | Perplexity model | `PERPLEXITY_MODEL=sonar-large-online` |
|
||||
| `TASKMASTER_ENABLE_PROXY` | `"false"` | Enable proxy support for AI providers | `TASKMASTER_ENABLE_PROXY=true` |
|
||||
|
||||
## TDD Workflow Configuration
|
||||
|
||||
@@ -69,8 +70,62 @@ LOG_LEVEL=info
|
||||
# TDD Workflow
|
||||
TM_MAX_ATTEMPTS=3
|
||||
TM_AUTO_COMMIT=true
|
||||
|
||||
# Proxy Support (Optional)
|
||||
# TASKMASTER_ENABLE_PROXY=true
|
||||
# http_proxy=http://your-proxy:port
|
||||
# https_proxy=http://your-proxy:port
|
||||
# no_proxy=localhost,127.0.0.1
|
||||
```
|
||||
|
||||
## Proxy Configuration
|
||||
|
||||
<Note>
|
||||
Task Master supports HTTP/HTTPS proxy configuration for corporate or restricted network environments where AI provider APIs are accessed through proxies.
|
||||
</Note>
|
||||
|
||||
Proxy support is **opt-in** and can be enabled using either method:
|
||||
|
||||
### Method 1: Environment Variable
|
||||
|
||||
```bash
|
||||
export TASKMASTER_ENABLE_PROXY=true
|
||||
export http_proxy=http://your-proxy:port
|
||||
export https_proxy=http://your-proxy:port
|
||||
export no_proxy=localhost,127.0.0.1 # Optional: bypass proxy for specific hosts
|
||||
|
||||
# Then use Task Master normally
|
||||
task-master add-task "Create a new feature"
|
||||
```
|
||||
|
||||
### Method 2: Configuration File
|
||||
|
||||
Add to `.taskmaster/config.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"global": {
|
||||
"enableProxy": true
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Then set your proxy environment variables:
|
||||
|
||||
```bash
|
||||
export http_proxy=http://your-proxy:port
|
||||
export https_proxy=http://your-proxy:port
|
||||
```
|
||||
|
||||
<Note>
|
||||
Priority: `TASKMASTER_ENABLE_PROXY` environment variable overrides the `config.json` setting.
|
||||
</Note>
|
||||
|
||||
**Supported scenarios:**
|
||||
- Corporate firewalls requiring HTTP/HTTPS proxy
|
||||
- Network environments with restricted internet access
|
||||
- All AI providers: OpenAI, Anthropic, Perplexity, Azure OpenAI, Google AI, Google Vertex AI, AWS Bedrock, and OpenAI-compatible providers
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### If `task-master init` doesn't respond:
|
||||
|
||||
51
output.txt
Normal file
51
output.txt
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user