chore: prepare CCPE participants standby

README.md

@@ -33,7 +33,9 @@ This workspace helps the user save effort after the article has entered writing:
 - prepare outline-review context under current context-window limits;
 - compress or organize source materials without replacing the original sources;
 - invoke real reviewer and writer sessions when the user explicitly names them;
-- preserve complete `session.md` and final `report.md` records;
+- preserve root-level CCPE registry and invocation policy files under `ccpe/`;
+- preserve reviewer audit runs under `audit/<reviewer-id>/rS.R/` with agent invocation packets, thread IDs, prompts, and returned outputs, where `S` is the reviewer-session number and `R` is that session's round number;
+- preserve complete invocation records and final returned outputs;
 - preserve user decisions, reflections, outline versions, and draft sessions;
 - create capability request tickets when required agents or skills are missing.
 
@@ -42,9 +44,12 @@ This workspace helps the user save effort after the article has entered writing:
 1. No initial outline, no project.
 2. No user-named reviewer, no reviewer invocation.
 3. No real sub-session, no formal reviewer or writer output.
-4. No user decision, no stage advancement.
+4. No root-level registry binding to a readable CCPE canonical artifact, no CCPE participant invocation.
-5. No full-article generation by default.
+5. No `agent-invocation-packet.md`, no accepted reviewer audit record.
-6. Missing capability creates a supplier ticket and pauses the project.
+6. No recorded thread ID and returned output, no accepted reviewer audit record.
+7. No user decision, no stage advancement.
+8. No full-article generation by default.
+9. Missing capability creates a supplier ticket and pauses the project.
 
 ## Directory Overview
 

WORKBENCH.md

@@ -13,7 +13,7 @@ Web source discussion
   -> Web initial outline v1.0
   -> Writing Workbench project
   -> outline review preparation
-  -> user-named reviewer sessions
+  -> user-named reviewer audit sessions
   -> user reflection and decision
   -> user-directed lead writer repair
   -> outline v2.0 / v3.0 / ...
@@ -45,7 +45,9 @@ Execution mode may:
 - prepare source digests;
 - create review briefs;
 - invoke user-named reviewers or writers through real sub-sessions;
-- record sessions and reports;
+- maintain the root-level CCPE registry and invocation policy under `ccpe/`;
+- record reviewer audit runs under `audit/<reviewer-id>/rS.R/`;
+- preserve returned outputs, prompts, and thread IDs;
 - prepare synthesis files for the user;
 - update status and decision logs.
 
@@ -78,7 +80,11 @@ Derived material files are working aids, not source of truth.
 
 Formal reviewer and writer outputs require real invocation.
 
-The controller session may prepare context, launch or coordinate sub-sessions, summarize returned outputs, and ask the user for decisions. It may not role-play a reviewer or writer and label that result formal.
+Before invoking a CCPE participant, the controller session must read the external CCPE interface at `C:\Users\wangq\Documents\Codex\ccpe-system\Interface.md`. Follow that interface to the consumer setup contract and then to any task-required protocol, Runtime, Agent, Lite, or Skill files. After that, resolve the participant through the root-level `ccpe/agent-registry.yaml`, and write `agent-invocation-packet.md` for the run.
+
+The controller session may prepare context, launch or coordinate sub-sessions, summarize returned outputs, and ask the user for decisions. It may not role-play a reviewer or writer and label that result formal. It must not treat `agent-invocation-packet.md` or `prompt-to-send.md` as executed output.
+
+Reviewer audit outputs live in the project under `audit/<reviewer-id>/rS.R/`, where `S` is the reviewer-session number and `R` is that session's round number. A continued review uses the same reviewer thread and increments the round part, such as `r1.1` to `r1.2`; a restarted review creates a new thread, increments the session part, and starts at `.1`, such as `r2.1`.
 
 ## 7. Drafting Policy
 

ccpe/agent-registry.yaml

@@ -0,0 +1,95 @@
+schema: writing_workbench.ccpe.agent_registry.v1
+workbench_id: writing-workbench
+workbench_root: 'C:\Users\wangq\Documents\Codex\writing-workbench'
+ccpe_system_root: 'C:\Users\wangq\Documents\Codex\ccpe-system'
+ccpe_interface_path: 'C:\Users\wangq\Documents\Codex\ccpe-system\Interface.md'
+consumer_setup_path: 'C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\ccpe-agent-consumer-setup.md'
+invocation_protocol_path: 'C:\Users\wangq\Documents\Codex\ccpe-system\runtimes\hybrid\agent-invocation-packet.protocol.md'
+strict_invocation_required: true
+no_simulation_requirement: true
+
+defaults:
+  invocation_mode: prompt_path_reference
+  carrier_type: codex_thread_participant
+  role_integrity_requirement: must_load_canonical_artifact_before_task
+  missing_canonical_behavior: blocked_missing_canonical_artifact
+  task_prompt_authority: task_context_only
+  output_structure_authority: canonical_artifact
+  packet_only_is_execution: false
+  prompt_to_send_only_is_execution: false
+
+participants:
+  han-yu:
+    display_name: '韩愈'
+    aliases:
+      - 'CCPE的韩愈'
+    default_workbench_role: lead_writer
+    canonical_artifact_path: 'C:\Users\wangq\Documents\Codex\ccpe-system\agents\lite\han-yu.prompt.md'
+    canonical_artifact_type: ccpe_lite
+    canonical_artifact_version: current
+    default_invocation_mode: prompt_path_reference
+    default_carrier_type: codex_thread_participant
+    role_integrity_requirement: must_load_canonical_artifact_before_task
+    missing_canonical_behavior: blocked_missing_canonical_artifact
+    output_structure_authority: canonical_artifact
+    allowed_wrapper_instructions:
+      - workbench_id
+      - 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 writing method
+      - treating the task prompt as the role definition
+
+  zhang-liao:
+    display_name: '张辽'
+    aliases:
+      - 'CCPE的张辽'
+    default_workbench_role: reviewer
+    canonical_artifact_path: 'C:\Users\wangq\Documents\Codex\ccpe-system\agents\lite\zhang-liao.prompt.md'
+    canonical_artifact_type: ccpe_lite
+    canonical_artifact_version: current
+    default_invocation_mode: prompt_path_reference
+    default_carrier_type: codex_thread_participant
+    role_integrity_requirement: must_load_canonical_artifact_before_task
+    missing_canonical_behavior: blocked_missing_canonical_artifact
+    output_structure_authority: canonical_artifact
+
+  giant-cognition:
+    display_name: '巨人'
+    aliases:
+      - 'CCPE的巨人'
+      - '巨人认知'
+    default_workbench_role: reviewer
+    canonical_artifact_path: 'C:\Users\wangq\Documents\Codex\ccpe-system\agents\lite\giant-cognition.prompt.md'
+    canonical_artifact_type: ccpe_lite
+    canonical_artifact_version: current
+    default_invocation_mode: prompt_path_reference
+    default_carrier_type: codex_thread_participant
+    role_integrity_requirement: must_load_canonical_artifact_before_task
+    missing_canonical_behavior: blocked_missing_canonical_artifact
+    output_structure_authority: canonical_artifact
+
+  cognitive-imaging:
+    display_name: '显影'
+    aliases:
+      - '认知显影'
+      - 'CCPE的显影'
+      - 'CCPE的认知显影'
+    default_workbench_role: reviewer
+    canonical_artifact_path: 'C:\Users\wangq\Documents\Codex\ccpe-system\agents\lite\cognitive-imaging-practitioner.prompt.md'
+    canonical_artifact_type: ccpe_lite
+    canonical_artifact_version: current
+    default_invocation_mode: prompt_path_reference
+    default_carrier_type: codex_thread_participant
+    role_integrity_requirement: must_load_canonical_artifact_before_task
+    missing_canonical_behavior: blocked_missing_canonical_artifact
+    output_structure_authority: canonical_artifact

ccpe/invocation-policy.md

@@ -0,0 +1,57 @@
+# Writing Workbench CCPE Invocation Policy
+
+This is the root-level CCPE invocation policy for `writing-workbench`.
+
+No article project owns a special CCPE participant registry. Article projects only own their run records under their own `audit/` directories. Participant identity, canonical artifact binding, and default invocation rules live here.
+
+## External Interface
+
+Use this single CCPE external entrypoint:
+
+```text
+C:\Users\wangq\Documents\Codex\ccpe-system\Interface.md
+```
+
+Before invoking any CCPE participant:
+
+1. Read `C:\Users\wangq\Documents\Codex\ccpe-system\Interface.md`.
+2. Follow that interface to the consumer setup contract.
+3. Read only the protocol, Runtime, Agent, Lite, or Skill files required for the current task.
+4. Resolve the participant through `ccpe/agent-registry.yaml`.
+5. Create a project run directory under `projects/<project>/audit/<participant-display-name>/rS.R/`.
+6. Write run-specific `agent-invocation-packet.md`.
+7. Write run-specific `prompt-to-send.md` so the participant loads the canonical artifact before task context.
+8. Launch a real participant carrier.
+9. Save `returned-output.md` only after the real participant returns.
+
+If the canonical artifact is missing or unreadable, stop with:
+
+```text
+blocked_missing_canonical_artifact
+```
+
+If a real participant cannot be launched, stop with:
+
+```text
+blocked_waiting_for_participant_output
+```
+
+## Default Roles
+
+- `han-yu`: default lead writer for outline repair.
+- `zhang-liao`: default reviewer.
+- `giant-cognition`: default reviewer.
+- `cognitive-imaging`: default reviewer, display alias `显影`.
+
+## Acceptance Rule
+
+A participant output is formal only when all of these are true:
+
+- `ccpe/agent-registry.yaml` binds the participant to a canonical artifact.
+- The canonical artifact was readable or pasted before task context.
+- `agent-invocation-packet.md` exists for the project run.
+- A real participant carrier was launched and recorded.
+- `returned-output.md` was saved after the participant returned.
+- Metadata says `simulation_only: false`.
+
+Packet-only and prompt-only states are not execution evidence. The controller session must not write a formal reviewer or lead-writer result.

ccpe/participants-standby.md

@@ -0,0 +1,28 @@
+# CCPE Participants Standby
+
+This file records root-level Writing Workbench readiness only. It is not a participant output.
+
+## Lead Writer
+
+- Display name: 韩愈
+- Participant ID: `han-yu`
+- Canonical artifact: `C:\Users\wangq\Documents\Codex\ccpe-system\agents\lite\han-yu.prompt.md`
+- Default workbench role: lead writer for outline repair
+- Status: standby
+
+## Reviewers
+
+- 张辽: `zhang-liao`, standby
+- 巨人: `giant-cognition`, standby
+- 显影: `cognitive-imaging`, standby
+
+## Test Mode
+
+Use real CCPE participant carriers only:
+
+1. launch reviewer audit through a run-specific `agent-invocation-packet.md`;
+2. wait for returned reviewer output;
+3. record user decision or synthesis;
+4. launch Han Yu as lead writer for outline repair.
+
+Project-specific audit directories contain run evidence only. They do not define special CCPE participants or project-local role behavior.

docs/ccpe-rebuild-context.md

@@ -15,7 +15,7 @@ Web discussion and source digestion
   -> Web initial outline v1.0
   -> Writing Workbench project
   -> outline review preparation
-  -> user-named reviewer invocation
+  -> user-named reviewer audit invocation
   -> user reflection and decision
   -> user-directed lead writer repair
   -> revised outline v2.0+
@@ -42,10 +42,12 @@ Priority capabilities:
    - Any additional reviewer only after a concrete Writing Workbench requirement exists.
 
 3. Invocation protocols
+   - single external CCPE interface path, `C:\Users\wangq\Documents\Codex\ccpe-system\Interface.md`;
+   - root-level Writing Workbench CCPE agent registry;
    - reviewer invocation packet;
    - lead writer repair packet;
-   - returned-output record;
+   - reviewer audit run contract;
-   - session/report contract;
+   - thread ID and returned-output record;
    - no-simulation rule.
 
 4. Context preparation rules
@@ -54,7 +56,7 @@ Priority capabilities:
    - how to distinguish source-grounded content from model-supplied additions.
 
 5. Evaluation and decision support
-   - review report contract;
+   - reviewer returned-output contract;
    - conflict synthesis for user decision;
    - repair instruction builder;
    - outline versioning rules.
@@ -67,7 +69,7 @@ Do not put these in CCPE:
 
 - full article project folders;
 - source digests made for one article;
-- reviewer `session.md` files for one article;
+- reviewer `audit/<reviewer-id>/rS.R/` run files for one article;
 - draft chapters;
 - user decision logs;
 - publication metadata for one essay.
@@ -140,4 +142,3 @@ It needs a reliable supplier layer for:
 - careful section-level drafting support.
 
 The user remains the director. CCPE supplies the actors, contracts, and guardrails.
-

docs/invocation-policy.md

@@ -11,6 +11,26 @@ Formal output includes:
 
 Formal output must come from a real sub-session, thread, tool invocation, or explicitly approved external execution path.
 
+## CCPE Participant Preflight
+
+Before invoking any CCPE participant, read the single external CCPE interface:
+
+1. `C:\Users\wangq\Documents\Codex\ccpe-system\Interface.md`
+
+Then follow that interface to the consumer setup contract. Read protocol, Runtime, Agent, Lite, or Skill files only when the interface and consumer setup contract require them for the current task.
+
+Writing Workbench maintains root-level CCPE infrastructure:
+
+- `ccpe/agent-registry.yaml`: binds each participant ID and display name to a `canonical_artifact_path`;
+- `ccpe/invocation-policy.md`: records the workbench invocation and acceptance policy;
+- `audit/<participant-display-name>/rS.R/agent-invocation-packet.md`: records the formal participant startup packet for that run;
+- `audit/<participant-display-name>/rS.R/prompt-to-send.md`: contains the prompt or wrapper actually sent to the real participant carrier;
+- `audit/<participant-display-name>/rS.R/returned-output.md`: saved only after the real participant returns.
+
+The controller must verify that the canonical artifact is readable, or paste the full canonical artifact into `prompt-to-send.md` before task context. If the canonical artifact is missing or unreadable, stop with `blocked_missing_canonical_artifact`.
+
+The task prompt is task context only. It must not replace the canonical role, tone, judgment method, or output structure.
+
 ## Controller May Do
 
 The controller session may:
@@ -18,8 +38,11 @@ The controller session may:
 - prepare context packs;
 - create review briefs;
 - route source files;
+- resolve participants through `ccpe/agent-registry.yaml`;
+- create `agent-invocation-packet.md` and `prompt-to-send.md`;
 - launch or coordinate sub-sessions;
 - summarize returned formal outputs;
+- copy or move returned formal outputs into their contracted audit directories without rewriting their judgment;
 - update project records;
 - ask the user for decisions.
 
@@ -29,6 +52,9 @@ The controller session must not:
 
 - impersonate a reviewer or lead writer;
 - create a formal report without real invocation;
+- invoke a CCPE participant by display name alone;
+- launch a CCPE participant before binding the name to a readable canonical artifact;
+- treat `agent-invocation-packet.md` as executed output;
 - treat a prompt draft as an executed report;
 - advance the project after its own recommendation;
 - hide uncertainty about missing capability.
@@ -50,3 +76,37 @@ simulation_only: true
 formal_output: false
 excluded_from_synthesis: true
 ```
+
+## Reviewer Audit Run Contract
+
+Reviewer audit runs use the project-root layout:
+
+```text
+audit/<reviewer-id>/rS.R/
+```
+
+`rS.R` encodes reviewer session and session-local round. For example, `r1.1` is the first round in the first reviewer thread, `r1.2` is the second round continuing that same thread, and `r2.1` is the first round in a newly started reviewer thread.
+
+Each run directory must contain:
+
+- `agent-invocation-packet.md`: participant ID, canonical artifact path, carrier metadata, input files, output contract, and runtime acceptance rule;
+- `run-metadata.json`: reviewer ID, round ID, child thread ID, prompt mode, continuation mode, source prompt path or reviewed target, canonical artifact path, packet path, prompt path, and output path;
+- `prompt-to-send.md`: the exact wrapper prompt or instruction sent to the reviewer thread, including the instruction to load the canonical artifact before task context;
+- `returned-output.md`: the formal reviewer output from the real child thread.
+
+`audit/audit-log.md` is the project-level index of reviewer runs. It records the reviewer, round, child thread ID, whether the run continued a prior thread, prompt mode, source prompt path, and returned-output path.
+
+For continued reviews, reuse the same child thread ID and increment only the round part. For restarted reviews, create a new child thread, increment the session part, reset the round part to `.1`, and record the new thread ID.
+
+## Acceptance Rule
+
+A CCPE participant run is accepted as formal output only when:
+
+- the root-level registry binds the participant to a canonical artifact;
+- the canonical artifact was readable or pasted before task context;
+- `agent-invocation-packet.md` exists for the run;
+- a real participant carrier was launched and recorded;
+- `returned-output.md` exists only after the participant returned;
+- returned metadata or run metadata says `simulation_only: false`.
+
+Packet-only and prompt-only states are blocked handoff states, not execution evidence.

docs/operating-playbook.md

@@ -16,7 +16,7 @@ If the user only has source materials or open discussion, stop and keep the work
 
 ## 2. Create The Folder
 
-Use:
+Use the user-specified project directory when the user gives one. Otherwise use:
 
 ```text
 projects/YYYY-MM-DD-short-slug/
@@ -47,18 +47,56 @@ For each source, decide the processing method from the source type:
 
 Always keep source paths in `source-map.md`.
 
-## 4. Review Rounds
+## 4. Reviewer Audit Runs
 
 A review round starts only when the user names the reviewer or reviewers.
 
-Each reviewer gets:
+Before launching any CCPE reviewer, read the external CCPE interface:
+
+1. `C:\Users\wangq\Documents\Codex\ccpe-system\Interface.md`
+
+Follow the interface to the consumer setup contract, then read any protocol, Runtime, Agent, Lite, or Skill files required for this task.
+
+Then resolve the reviewer through root-level `ccpe/agent-registry.yaml`. Do not launch from the display name alone.
+
+Formal reviewer output is stored under a project-root `audit/` folder. Each reviewer owns its own round sequence:
 
 ```text
-02-outline-review/round-NN/reviewers/<reviewer-id>/session.md
+audit/
-02-outline-review/round-NN/reviewers/<reviewer-id>/report.md
+  audit-log.md
+  <reviewer-id>/
+    r1.1/
+      agent-invocation-packet.md
+      run-metadata.json
+      prompt-to-send.md
+      returned-output.md
+    r1.2/
+      agent-invocation-packet.md
+      run-metadata.json
+      prompt-to-send.md
+      returned-output.md
+    r2.1/
+      agent-invocation-packet.md
+      run-metadata.json
+      prompt-to-send.md
+      returned-output.md
 ```
 
-The review brief may be prepared by the controller session, but the report must come from the real reviewer sub-session.
+Each run ID is local to each reviewer and uses `rS.R`: `S` is the reviewer-session number, and `R` is that session's round number. For example, `audit/张辽/r1.2/` is 张辽's second round in the first thread; `audit/张辽/r2.1/` is 张辽's first round in a newly started thread.
+
+The user chooses:
+
+- the reviewers to invoke;
+- whether the prompt is a bare outline review or a full-context review;
+- whether to continue the prior reviewer thread or start a fresh review thread.
+
+The controller session may prepare context and launch or coordinate sub-sessions. It must write `agent-invocation-packet.md` before `prompt-to-send.md`, and the prompt sent to the child thread must force the reviewer to load the canonical artifact before reading task context. It must record the child thread ID in `run-metadata.json` and `audit/audit-log.md`. The formal returned output must come from the real reviewer sub-session and be preserved as `returned-output.md`.
+
+If the reviewer cannot load the canonical artifact, stop with `blocked_missing_canonical_artifact`. If the reviewer cannot be truly invoked, stop with `blocked_waiting_for_participant_output`. Do not write a formal reviewer report in the controller session.
+
+If a reviewer continues a prior review, send the new prompt to that same child thread and write the result to the next same-session round directory. If the user asks for a restart, create a new thread, start a new session directory such as `r2.1`, and record `continuation: false`.
+
+`02-outline-review/` may still hold shared review briefs, synthesis notes, and user-facing summaries. It is not the authoritative location for individual reviewer returned outputs.
 
 ## 5. User Decision Gate
 
@@ -69,7 +107,7 @@ The user may provide:
 - reflection;
 - accepted and rejected review points;
 - direction for lead writer repair;
-- instruction to run another review;
+- instruction to continue or restart a reviewer audit;
 - instruction to draft a specific part.
 
 Record these in `decision-log.md` and the relevant stage folder.

docs/project-lifecycle.md

@@ -25,6 +25,7 @@ States may repeat. For example, after several review rounds the user may add new
 ```text
 00-intake/
 01-materials/
+audit/
 02-outline-review/
 03-outline-repair/
 04-drafting/
@@ -34,6 +35,10 @@ publish/
 
 These folders are working areas, not mandatory linear gates.
 
+`audit/` is the authoritative folder for individual reviewer audit runs. `02-outline-review/` is for shared briefs, synthesis, and user-decision support.
+
+Root-level `ccpe/` owns the CCPE registry and invocation policy. Project `audit/` folders contain run evidence only.
+
 ## Advancement Rule
 
 The workspace may suggest next actions, but only the user advances the project.

templates/article-project/PROJECT_STRUCTURE.md

@@ -18,15 +18,19 @@ YYYY-MM-DD-short-slug/
     source-digests/
     compression-notes.md
 
+  audit/
+    audit-log.md
+    reviewer-id/
+      r1.1/
+        agent-invocation-packet.md
+        run-metadata.json
+        prompt-to-send.md
+        returned-output.md
+
   02-outline-review/
-    round-01/
+    review-brief.md
-      review-brief.md
+    user-reflection.md
-      reviewers/
+    synthesis-for-writer.md
-        reviewer-id/
-          session.md
-          report.md
-      user-reflection.md
-      synthesis-for-writer.md
 
   03-outline-repair/
     writer-session-v2.0/

templates/article-project/audit/reviewer-id/r1.1/agent-invocation-packet.md

@@ -0,0 +1,89 @@
+# 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`.

templates/article-project/audit/reviewer-id/r1.1/prompt-to-send.md

@@ -0,0 +1,48 @@
+# Prompt To Send: reviewer-id
+
+You are being invoked as a formal CCPE participant for Writing Workbench.
+
+First read your canonical CCPE artifact:
+
+`<canonical_artifact_path resolved from ccpe/agent-registry.yaml>`
+
+This canonical artifact defines your role, tone, judgment method, and output structure.
+
+Then read the CCPE external interface and workbench policy files:
+
+1. `C:\Users\wangq\Documents\Codex\ccpe-system\Interface.md`
+2. `ccpe/invocation-policy.md`
+3. `audit/reviewer-id/r1.1/agent-invocation-packet.md`
+
+Follow `Interface.md` to the consumer setup contract, then read any protocol, Runtime, Agent, Lite, or Skill files that the interface and setup contract require for this task.
+
+The task prompt and project files below are task context only. They must not replace your canonical role.
+
+If the canonical artifact is unavailable or unreadable, stop and return:
+
+```text
+blocked_missing_canonical_artifact
+```
+
+After loading the canonical artifact, read the task input:
+
+`<source prompt, outline, or context pack path>`
+
+Write the formal output to:
+
+`audit/reviewer-id/r1.1/returned-output.md`
+
+Return metadata:
+
+- project_id: `<fill from project.md>`
+- workflow: article_outline_review
+- stage: outline_review
+- participant_id: reviewer-id
+- canonical_artifact_path: `<canonical_artifact_path resolved from registry>`
+- invocation_mode: prompt_path_reference
+- carrier_type: codex_thread_participant
+- thread_id: `<created child thread id>`
+- execution_status: returned
+- simulation_only: false
+
+Do not write to other directories. If you cannot read the task input or cannot write the returned output path, report the blocking reason instead of producing a formal review.

templates/article-project/audit/reviewer-id/r1.1/run-metadata.json

@@ -0,0 +1,29 @@
+{
+  "schema": "writing-workbench.ccpe-participant-run.v1",
+  "project_id": "<fill from project.md>",
+  "workflow": "article_outline_review",
+  "stage": "outline_review",
+  "participant_id": "reviewer-id",
+  "display_name": "<display name from ccpe/agent-registry.yaml>",
+  "round_id": "r1.1",
+  "session_id": "r1",
+  "session_round": 1,
+  "task_type": "outline_review",
+  "prompt_mode": "<full_context_review | bare_outline_review>",
+  "context_mode": "<fresh_thread | continued_from_prior_round>",
+  "continuation": false,
+  "child_thread_id": "<created child thread id>",
+  "canonical_artifact_path": "<resolved from ccpe/agent-registry.yaml>",
+  "canonical_artifact_type": "ccpe_lite",
+  "canonical_artifact_version": "current",
+  "invocation_mode": "prompt_path_reference",
+  "carrier_type": "codex_thread_participant",
+  "strict_invocation_required": true,
+  "simulation_only": false,
+  "formal_output": false,
+  "packet_path": "audit/reviewer-id/r1.1/agent-invocation-packet.md",
+  "prompt_path": "audit/reviewer-id/r1.1/prompt-to-send.md",
+  "output_path": "audit/reviewer-id/r1.1/returned-output.md",
+  "returned_output_written": false,
+  "status": "prepared"
+}