Bryan Helmkamp f166bb4959 Replace text-scanning with report_outcome tool for routing ... The previous approach scanned LLM response text for JSON containing routing fields (extract_status_fields), which was fragile and violated the spec's abstraction boundary. Replace with two clean mechanisms: - Backend registers a report_outcome tool that the LLM calls to declare routing decisions (status, preferred_next_label, context_updates, etc.) - Handler auto-generates a routing preamble listing available edge labels, appended to the prompt only when 2+ labeled unconditional edges exist Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-02-24 09:29:25 -05:00
..
agent	Fix OpenAI error field, add Anthropic provider options pass-through, and improve parity tests	2026-02-23 21:21:45 -05:00
attractor	Replace text-scanning with report_outcome tool for routing	2026-02-24 09:29:25 -05:00
llm	Fix OpenAI error field, add Anthropic provider options pass-through, and improve parity tests	2026-02-23 21:21:45 -05:00
terminal	Extract terminal crate and prettify attractor CLI output	2026-02-23 12:06:24 -05:00