Spectre.Reply.Sanitizer (Spectre v0.3.0)

Strips Spectre control tokens from model output before it becomes a user-visible reply.

Prompts teach the model Spectre's routing and planning markup — <al>, <intent>, <reply> wrappers, INTENT:/AL: control lines — and models also emit reasoning wrappers (<think>, HTML comments). None of that may reach the user, and without a core scrubber every host rewrites the same cleanup. This sanitizer is the runtime default wherever LLM text becomes reply_text; pass sanitize_reply: false to opt out, or configure an action planner with a clean_reply/3 callback to take full ownership.

Host-specific cleanup (localized model preambles, channel formatting) stays in the host — this module removes only tokens Spectre itself introduces plus universal reasoning wrappers.

Summary

Functions

sanitize(text, opts \\ [])

Removes Spectre control tokens and reasoning wrappers, then trims.

Functions

sanitize(text, opts \\ [])

@spec sanitize(
  String.t(),
  keyword()
) :: String.t()

Removes Spectre control tokens and reasoning wrappers, then trims.

iex> Spectre.Reply.Sanitizer.sanitize("<think>hmm</think>Hello <al>a1</al>there")
"Hello there"

Honors sanitize_reply: false in opts by returning the text trimmed but otherwise untouched.