90 lines
3.1 KiB
Markdown
90 lines
3.1 KiB
Markdown
# Agent Invocation Packet: reviewer-id
|
|
|
|
## 1. Invocation Identity
|
|
|
|
- project_id: `<fill from project.md>`
|
|
- workflow: article_outline_review
|
|
- stage: outline_review
|
|
- run_id: r1.1
|
|
- participant_id: reviewer-id
|
|
- target_participant_name: `<display name from ccpe/agent-registry.yaml>`
|
|
- participant_type: ccpe_lite
|
|
- canonical_artifact_path: `<resolved from ccpe/agent-registry.yaml>`
|
|
- canonical_artifact_version: current
|
|
- invocation_mode: prompt_path_reference
|
|
- packet_type: participant_startup_packet
|
|
|
|
## 2. Carrier Metadata
|
|
|
|
- carrier_type: codex_thread_participant
|
|
- thread_id: `<created child thread id>`
|
|
- agent_id:
|
|
- persistent_required: true
|
|
- resume_or_followup_method: continue same child thread for r1.2; start a new child thread for r2.1
|
|
- execution_status: prepared
|
|
- strict_invocation_required: true
|
|
- simulation_only: false
|
|
- returned_output_path: audit/reviewer-id/r1.1/returned-output.md
|
|
- skill_execution_record_path:
|
|
- prompt_to_send_path: audit/reviewer-id/r1.1/prompt-to-send.md
|
|
|
|
## 3. Canonical Artifact Handling
|
|
|
|
- should_paste_full_prompt_or_spec: no
|
|
- role_integrity_requirement: must_load_canonical_artifact_before_task
|
|
- allowed_wrapper_instructions: project_id, workflow, stage, run_id, input_files, context_files, output_path, output_language_policy
|
|
- forbidden_role_changes: replacing the canonical role; replacing the canonical tone; replacing the canonical output structure; weakening the canonical evaluation method; treating the task prompt as the role definition
|
|
- no_simulation_requirement: true
|
|
- path_readability_evidence: `<record Test-Path result or full prompt paste fallback>`
|
|
|
|
## 4. Current Task
|
|
|
|
`<state the review or repair task; task context must not replace the canonical role>`
|
|
|
|
## 5. Input Files
|
|
|
|
- `<source prompt, outline, or source pack path>`
|
|
|
|
## 6. Context Files
|
|
|
|
- `ccpe/agent-registry.yaml`
|
|
- `ccpe/invocation-policy.md`
|
|
- `C:\Users\wangq\Documents\Codex\ccpe-system\Interface.md`
|
|
- `C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccpe-agent-consumer-setup.md`
|
|
- `C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\agent-invocation-packet.protocol.md`
|
|
|
|
## 7. Embedded Inputs
|
|
|
|
None by default.
|
|
|
|
## 8. Output Contract
|
|
|
|
- source_primary_language: zh-CN
|
|
- output_language_policy: mirror_source_primary_language
|
|
- human_review_language_requirement: zh-CN
|
|
- human_confirmation_artifact: false
|
|
- gate_id_if_applicable:
|
|
|
|
## 9. Continuity Policy
|
|
|
|
For continued review, reuse the same child thread and increment only the round part of `rS.R`.
|
|
|
|
## 10. Session Logging
|
|
|
|
Record the child thread id in `run-metadata.json` and `audit/audit-log.md`.
|
|
|
|
## 11. Forbidden Actions
|
|
|
|
- Do not write a formal reviewer output in the controller session.
|
|
- Do not treat this packet as execution.
|
|
- Do not treat `prompt-to-send.md` as returned output.
|
|
- Do not save `returned-output.md` before the real participant returns.
|
|
|
|
## 12. Return Path
|
|
|
|
Write formal participant output to `audit/reviewer-id/r1.1/returned-output.md`.
|
|
|
|
## 13. Runtime Acceptance Rule
|
|
|
|
This run is accepted only after a real participant carrier returns and `returned-output.md` exists with `simulation_only: false`.
|