agent-zero/plugins/_goal
Alessandro 039efe4198 Keep model prose as thoughts and retry silently
Preserve free text and reasoning-only output in the current generation
and retry without intermediate warning rows. Require an explicit response
tool call to finish in both API modes, including after provider built-in
actions.

Keep history metadata, Responses state, tool validation and the
consecutive-failure stop intact. Allow core retries when Context Doctor
and its prompts are unavailable.

Validation: 411 backend tests and 2 Chromium live/replay grouping tests
passed; live runtime health check passed.
2026-11-01 06:50:49 +01:00
..
api Consolidate goal tool 2026-07-18 21:03:14 +02:00
commands Consolidate goal tool 2026-07-18 21:03:14 +02:00
extensions feat(goal): render goal tool calls through a dedicated badge 2026-10-21 23:37:32 +03:00
prompts Consolidate goal tool 2026-07-18 21:03:14 +02:00
tests Keep model prose as thoughts and retry silently 2026-11-01 06:50:49 +01:00
tools feat(goal): render goal tool calls through a dedicated badge 2026-10-21 23:37:32 +03:00
webui feat(goal): render goal tool calls through a dedicated badge 2026-10-21 23:37:32 +03:00
__init__.py Add built-in goal management plugin 2026-07-09 17:09:08 +02:00
AGENTS.md feat(goal): render goal tool calls through a dedicated badge 2026-10-21 23:37:32 +03:00
plugin.yaml Add built-in goal management plugin 2026-07-09 17:09:08 +02:00