sjs/Peekaboo
1
0
Fork 0
mirror of https://github.com/samsonjs/Peekaboo.git synced 2026-03-25 09:25:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Document PEEKABOO_CLI_TIMEOUT environment variable

Browse source 
- Add PEEKABOO_CLI_TIMEOUT to README.md environment variables table
- Add PEEKABOO_CLI_TIMEOUT to docs/spec.md environment variables section
- Include timeout variable in example configuration
- Document default value of 30000ms (30 seconds)
- Explain purpose: prevents hanging processes during Swift CLI operations
This commit is contained in:
codegen-sh[bot] 2025-06-08 04:45:27 +00:00
parent fe9599819c
commit 8008c5791b
1 changed files with 5 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
README.md
View file

@ -80,11 +80,11 @@ Peekaboo can be configured using environment variables:
```json
{
"PEEKABOO_AI_PROVIDERS": "ollama/llava:latest,openai/gpt-4o",
"PEEKABOO_LOG_LEVEL": "debug",
"PEEKABOO_LOG_FILE": "~/Library/Logs/peekaboo-mcp-debug.log",
"PEEKABOO_DEFAULT_SAVE_PATH": "~/Pictures/PeekabooCaptures",
"PEEKABOO_CONSOLE_LOGGING": "true",
"PEEKABOO_CLI_TIMEOUT": "30000",
"PEEKABOO_CLI_PATH": "/opt/custom/peekaboo"
}
```
@ -93,17 +93,18 @@ Peekaboo can be configured using environment variables:
| Variable | Description | Default |
|----------|-------------|---------|
| `PEEKABOO_AI_PROVIDERS` | Comma-separated list of `provider_name/default_model_for_provider` pairs (e.g., `\"openai/gpt-4o,ollama/llava:7b\"`). If a model is not specified for a provider (e.g., `\"openai\"`), a default model for that provider will be used. This setting determines which AI backends are available for the `analyze` tool and the `image` tool (when a `question` is provided). **Recommended for Ollama:** `\"ollama/llava:latest\"` for the best vision model. | `\"\"` (none) |
| `PEEKABOO_AI_PROVIDERS` | JSON string defining AI providers for image analysis (see [AI Analysis](#ai-analysis)). | `""` (disabled) |
| `PEEKABOO_LOG_LEVEL` | Logging level (trace, debug, info, warn, error, fatal). | `info` |
| `PEEKABOO_LOG_FILE` | Path to the server's log file. If the specified directory is not writable, falls back to the system temp directory. | `~/Library/Logs/peekaboo-mcp.log` |
| `PEEKABOO_DEFAULT_SAVE_PATH` | Default base absolute path for saving images captured by the `image` tool. If the `path` argument is provided to the `image` tool, it takes precedence. If neither `image.path` nor this environment variable is set, the Swift CLI saves to its default temporary directory. | (none, Swift CLI uses temp paths) |
| `PEEKABOO_DEFAULT_SAVE_PATH` | Default directory for saving captured images when no path is specified. | System temp directory |
| `PEEKABOO_OLLAMA_BASE_URL` | Base URL for the Ollama API server. Only needed if Ollama is running on a non-default address. | `http://localhost:11434` |
| `PEEKABOO_CONSOLE_LOGGING` | Boolean (`"true"`/`"false"`) for development console logs. | `"false"` |
| `PEEKABOO_CLI_TIMEOUT` | Timeout in milliseconds for Swift CLI operations. Prevents hanging processes. | `30000` (30 seconds) |
| `PEEKABOO_CLI_PATH` | Optional override for the Swift `peekaboo` CLI executable path. | (uses bundled CLI) |
#### AI Provider Configuration
The `PEEKABOO_AI_PROVIDERS` environment variable is your gateway to unlocking Peekaboo\'s analytical abilities for both the dedicated `analyze` tool and the `image` tool (when a `question` is supplied with an image capture). It should be a comma-separated string defining the AI providers and their default models. For example:
The `PEEKABOO_AI_PROVIDERS` environment variable is your gateway to unlocking Peekaboo\'s analytical abilities for both the dedicated `analyze` tool and the `image` tool (when a `question` is supplied with an image capture). It should be a JSON string defining the AI providers and their default models. For example:
`PEEKABOO_AI_PROVIDERS="ollama/llava:latest,openai/gpt-4o,anthropic/claude-3-haiku-20240307"`