# Participant Registry

## whole-source-gestalt-reviewer

- participant_type: high_context_participant
- canonical_artifact_path: `C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\whole-source-gestalt-reviewer.agent.md`
- default_invocation_mode: codex_thread_participant for persistent alignment; agent_subsession_participant only if resumable
- required_record: `agent-invocation-packet.md`
- external_record_when_needed: `prompt-to-send.md` plus returned output
- output_kind: whole-source topic portrait and coherence judgment
- must_run_before: `conversation-segmentation` when the source is coherent and within the high-context whole-source limit
- must_not_be_simulated_by_main_session: true
- continuity_requirement: preserve `thread_id` or resumable `agent_id` until human-confirmed

## conversation-segmentation

- participant_type: ccpe_skill
- canonical_artifact_path: `C:\Users\wangq\Documents\Codex\ccpe-system\skills\workflow\conversation-segmentation.skill.md`
- default_invocation_mode: local_skill_execution
- required_record: `skill-execution-record.md`
- output_kind: source block index

## topic-discovery-router

- participant_type: ccpe_agent
- canonical_artifact_path: `C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\topic-discovery-router.agent.md`
- default_invocation_mode: prompt_path_reference or full_prompt_paste
- required_record: `agent-invocation-packet.md`
- external_record_when_needed: `prompt-to-send.md` plus returned output
- output_kind: candidate topic map

## topic-graph-synthesizer

- participant_type: ccpe_agent
- canonical_artifact_path: `C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\topic-graph-synthesizer.agent.md`
- default_invocation_mode: codex_thread_participant or recorded main_session_synthesis over file-backed worker outputs
- required_record: `agent-invocation-packet.md` plus `returned-output.md`, or `synthesis-record.md` when no new source interpretation is added
- output_kind: topic hierarchy or graph with parent/child/tool/case/action-layer distinctions
- must_run_after: `topic-discovery-router`
- must_run_before: `evidence-routing-and-topic-doc-builder`
- must_not_be_simulated_by_main_session: true
- strict_invocation_rule: if the main session synthesizes, it may only integrate returned outputs and user-confirmed Step 0; otherwise record blocked

## evidence-routing-and-topic-doc-builder

- participant_type: ccpe_skill
- canonical_artifact_path: `C:\Users\wangq\Documents\Codex\ccpe-system\skills\workflow\evidence-routing-and-topic-doc-builder.skill.md`
- default_invocation_mode: worker_thread_or_local_skill_execution_with_record
- required_record: `skill-execution-record.md`
- output_kind: routing log and topic document draft
- strict_invocation_rule: source-heavy routing, topic docs, and material-unit extraction must be worker/sub-session work; main session may only integrate returned outputs

## lossless-coverage-auditor

- participant_type: ccpe_agent
- canonical_artifact_path: `C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\lossless-coverage-auditor.agent.md`
- default_invocation_mode: prompt_path_reference or full_prompt_paste
- required_record: `agent-invocation-packet.md`
- external_record_when_needed: `prompt-to-send.md` plus returned output
- output_kind: coverage audit and distortion risk log