Todos, reflection, and shortlisting

These are Orchestrator knobs — they change how CugaLite plans and retries, not which tools you attach.

All three live under [advanced_features] in settings.toml.

Todos

Off by default. When on, CugaLite gets a create_update_todos tool and prompt instructions so it can keep a checklist for multi-step work (and reset it between tasks).

[advanced_features]
enable_todos = true

Use it when a task has several independent steps you want the model to track. Leave it off for short, single-tool runs.

Reflection

Off by default. After a sandbox/code step, CUGA checks whether the result actually moved the task forward. If not, it can retry instead of answering from a bad state.

[advanced_features]
reflection_enabled = true

Turn it on when wrong-but-confident answers are costly. Leave it off when latency matters more than a second look.

Tool shortlister (find_tools)

When an app has more tools than the threshold, CugaLite does not dump the whole catalog into the prompt. It exposes find_tools: the model describes what it needs in natural language, and an LLM shortlister returns the relevant subset.

[advanced_features]
shortlisting_tool_threshold = 35   # find_tools when total tools > this
cuga_lite_enable_few_shots = true  # few-shots for the shortlister path

Over-cap on native bind_tools (providers that reject > ~128 tools) uses the same shortlister:

[advanced_features]
cuga_lite_bind_tools_max_count = 128   # 0 disables the cap
cuga_lite_bind_tools_pad_to_cap = false
cuga_lite_bind_tools_include_find_tools = false

Related

• Settings reference — planning
• Context summarization