Module fill_transcripts 

Stage 2 — fill-transcripts.

Walks the iteration’s eval-* directories and, for each (eval, condition) run.json, populates tool_invocations from the persisted transcript (Claude Code subagent JSONL resolved by the task’s agent_description, or Codex codex-events.jsonl). Records that already carry invocations are skipped unless overwrite.

Structs

FillTranscriptsResult

Tally of what fill-transcripts did across the iteration’s runs.

Functions

fill_transcripts

Populate tool_invocations for every run.json under iteration_dir. See the module docs for the transcript sources and overwrite semantics.

resolve_agent_description

The canonical dispatch description for an (eval, condition, run) run.