halo copilot explain

Explain a release, a policy diff or an experiment in plain language, citing only Halos outputs

Usage

halo copilot explain release <ring> | diff <git-ref> | experiment <name> [flags]

Flags

Flag	Shorthand	Type	Default	Description
--api-key-env		string	ANTHROPIC_API_KEY	env var holding the provider credential (never printed)
--debug		bool	false	log prompts and replies to stderr (default: token counts only)
--diff		string		release: git ref of the policy to compare with (default: an empty release)
--llm-url		string		provider or gateway base URL (default: the policy’s gateway baseURL, e.g. a halo-proxy, else https://api.anthropic.com)
--max-cost-usd		float64	2	estimated spend per run in USD (hard ceiling)
--max-iterations		int	3	model calls per run (hard ceiling)
--max-tokens		int	60000	input+output tokens per run (hard ceiling)
--model		string	claude-opus-5-5	pinned model id
--offline		bool	false	deterministic templates, no model call (air-gapped, tests)
--policy-dir		string		policy repo directory (default “.”)
--price-in		float64	5	USD per million input tokens, for the cost estimate
--price-out		float64	25	USD per million output tokens, for the cost estimate
--roi		string		experiment: ROI report JSON (halo roi report –output json)
--scorecard		string		experiment: eval scorecard JSON
--verdicts-file		string		experiment: verdicts JSON array (halo exp analyze –verdicts-file)
--wire		string	anthropic-messages	provider wire: anthropic-messages | openai-responses

Global flags

Flag	Shorthand	Type	Default	Description
--output		string	text	output format: text|json

Examples

halo copilot explain diff main
  halo copilot explain release ring1-canary --diff main
  halo copilot explain experiment opus-5-5-canary --verdicts-file verdicts.json --offline

Parent

halo copilot