Agent

usage: lightpanda agent [SCRIPT] [OPTIONS] [COMMON_OPTIONS]
 
Arguments:
[SCRIPT]
          Optional path to a .js script. Runs the script (no LLM calls) and
          exits; `lightpanda run SCRIPT` is the preferred spelling. With no
          script and no --task, the REPL starts; from there /load runs a
          script and /save exports the session to a file.
          Caution: .js files can contain evaluate(...) calls that run
          arbitrary JavaScript in the page. Only run scripts you trust, the
          same way you would a shell script.
 
Options:
  -a, --attach <PATH>
          Feed a local file to the model alongside --task. Repeatable, one
          file per flag. Text files are inlined (max 512 KiB each);
          images/audio/pdf are base64-encoded (max 20 MiB each).
          Unsupported MIME types fail before any browser work runs.
          Requires --task.
  --base-url <URL>
          Override the API base URL for the provider. Defaults to the
          provider's standard endpoint.
          Ollama default: http://localhost:11434/v1.
          llama.cpp default: http://localhost:8080/v1.
          Hugging Face default is the serverless router
              (https://router.huggingface.co/v1);
              point this at a dedicated Inference Endpoint to use one.
  --effort <LEVEL>
          Per-turn reasoning budget, mapped to each provider's native
          thinking/reasoning knob. Default: low in the REPL (snappy turns),
          medium in one-shot --task mode, unless the provider sets its own
          default (Mistral defaults to none, as its default model rejects
          effort). In the REPL, use /effort to change it.
          Allowed values: none, minimal, low, medium, high, xhigh.
  --list-models
          Print the model IDs usable with `agent` for --provider, one per
          line, sorted, and exit. Auto-detects the provider from env when
          --provider is omitted.
  --model <MODEL>
          The model name to use. Defaults to a sensible default per
          provider. In the REPL, use /model to list and change models for
          the active provider.
  --no-llm
          Force the basic REPL even when an API key is present or
          --provider is set. Useful for testing slash commands without
          burning tokens, or for disabling the LLM in a saved command
          without editing the existing flags. Wins over --provider.
  --provider <PROVIDER>
          The AI provider. When omitted, lightpanda auto-detects an API
          key from your environment (ANTHROPIC_API_KEY, OPENAI_API_KEY,
          GOOGLE_API_KEY/GEMINI_API_KEY, HF_TOKEN, AI_GATEWAY_API_KEY,
          MISTRAL_API_KEY). With exactly one key set: that provider is
          used. With multiple keys on a TTY: you'll be prompted to pick;
          in non-interactive contexts, pass --provider explicitly. With
          no keys set: falls back to the basic REPL (slash commands only,
          no natural-language input, no LOGIN / ACCEPT_COOKIES keywords).
 
          Local servers (ollama, llama_cpp) are never auto-detected (they
          need no key); select them explicitly with --provider ollama /
          --provider llama_cpp.
 
          Allowed values: "anthropic", "openai", "gemini", "huggingface",
                          "vercel", "mistral", "ollama", "llama_cpp".
          In the REPL, use /provider to list and change providers.
  --save <PATH>
          Synthesize a replayable .js script from the --task run and write
          it to PATH, instead of printing the answer. Replay it later with
          `run PATH` (no LLM calls). Overwrites PATH if it exists.
          Requires --task.
  --system-prompt <STRING>
          Override the default system prompt.
  --task <STRING>
          One-shot mode: run a single user turn, print the final answer
          to stdout, and exit. Conflicts with the positional script. With
          --save, the answer is suppressed and a script is written instead.
  --verbosity <LEVEL>
          Stderr chatter level. Default: high when --task captures stderr
          to a pipe or file; low otherwise. low/medium also raise
          --log-level to err (mutes page-side console.error spam) unless
          --log-level is set explicitly.
          Allowed values:
              low  silent in --task mode (final answer to stdout only);
                   spinner + summary in REPL.
              medium  + one `● [tool: ...]` line per call.
              high    + the matching `[result: ...]` body (required by the
                        benchmarks harness).

lightpanda agent                                (auto-detects API key from env)
lightpanda agent --provider anthropic --model claude-sonnet-4-6
lightpanda agent --provider huggingface         (HF serverless router, HF_TOKEN)
lightpanda agent --provider ollama --model qwen3.5:latest
lightpanda agent --no-llm                       (basic slash-command-only REPL)
lightpanda agent --task "..." --save out.js     (synthesize a replayable script)