PhaseEnum


Description:

public enum PhaseEnum

Which task-list or executor phase is active for markdown generation, link validation, and (on restore) transcript replay.

Prompt / markdown: Details.to_markdown, Step.to_markdown, and List.to_markdown take a PhaseEnum to include the right sections (e.g. tool calls, result summary, references). Validation: ValidateLink and ResolveLink branch on stage so list vs refinement vs executor output get the correct rules.

Live wire ids: the skill runner adds agent-stage messages whose body is a short id (task_list_parse, refinement , exec, …). from_string maps those strings here; to_string maps back for stages the live flow emits (others yield ).

Markdown and planning phases

  • COARSE / REFINEMENT / LIST — task list and refinement: coarse creation keys,

    refined task block, or outstanding list (+ optional executor result summary when

    exec_done) for prompts.

  • REFINE_COMPLETED — completed-task markdown for iteration prompts (omits certain

    reference sections; see Details.to_markdown).

  • EXECUTION / POST_EXEC — executor LLM output vs post-exec synthesis; used in

    ResultParser.exec_extract, ResultParser.exec_post_extract, and matching

    ValidateLink behavior.

Replay-only and sentinel

  • NONE — not a live stage: from_string default for unknown ids; GTK replay uses

    it only until the first agent-stage applies.

  • TASK_LIST_ITERATION — parsing a revised list ( ResultParser.parse_task_list_iteration).
  • EXEC_VALIDATE — validating executor writes after exec; replay cursor advances here

    while consuming exec_validate / validate agent-issues rows.

See also:

Details.to_markdown, List.to_markdown, ValidateLink, OLLMcoder.Skill.Runner.on_replay


Namespace: OLLMcoder.Task
Package: ollmchat

Content:

Enum values:

Static methods:

Methods: