Skip to main content

First Turn

This page walks through a first interactive session so you can see the harness in action.

Start Interactive Mode​

paddles --cuda

Or without CUDA acceleration:

paddles

The TUI opens with a prompt composer at the bottom and a transcript area above.

Ask A Question​

Type a question about the workspace and press Enter:

What does the planner loop do?

Read The Trace​

The transcript shows each step as it happens:

• Classified · 0ms
  └ planned

• Checked planner capability · 120ms (+120ms)
  └ qwen-1.5b: available

• Planning...

• Planner step 1: search · 3.2s (+3.1s)
  └ Rationale: Looking for planner loop implementation

• Planner step 2: read · 5.8s (+2.6s)
  └ Rationale: Reading the recursive execution loop

• Planner step 3: answer · 6.1s (+300ms)
  └ Rationale: Evidence is sufficient

• Synthesized grounded answer · 8.4s (+2.3s)
  └ Sources: src/application/mod.rs, src/domain/ports/planning.rs

Each line is a real event from the harness — not decorative output. The planner searched the workspace, read relevant files, and decided it had enough evidence before synthesis.

The muted "Planning..." row appeared because the planner step took more than two seconds. These in-flight indicators show what the harness is doing during long operations.

Tune Verbosity​

The default interactive stream runs at verbosity level 0. That view keeps the operator-facing steps visible while suppressing low-value bookkeeping for casual direct responses.

For example, a greeting at the default level stays short:

User
  └ Howdy

• Planner step 1: answer directly · 3.2s (+3.1s)
  └ Rationale: The user offered a casual greeting with no repository task or request for evidence, so a brief direct reply is appropriate.

Paddles · 3.2s total (+6ms)
  └ Howdy

Raise verbosity when you want more internals:

  • -v adds info-tier synthesis and planner summary rows.
  • -vv adds debug-tier routing and capability detail.
  • -vvv adds trace diagnostics such as boot and prompt-payload logging.

You can also set verbose = 0, 1, 2, or 3 in paddles.toml. CLI flags override config, and the same resolved level drives both the TUI transcript and the web UI event stream.

Use A Heavier Planner​

You can route the planner and synthesizer to different models:

paddles --model qwen-1.5b --planner-model qwen3.5-2b

The synthesizer stays lightweight while the planner uses a more capable model for investigation.

One-Shot Mode​

For scripts, use --prompt to skip the TUI:

paddles --prompt "Summarize the current runtime lanes"