Auto Review Loop

---
name: "auto-review-loop"
description: "Autonomous multi-round research review loop. Repeatedly reviews using Gemini via gemini-review MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says \"auto review loop\", \"review until it passes\", or wants autonomous iterative improvement."
---

<!-- EVO-INQUIRY:BEGIN -->
For research work, read [EvoInquiry](../shared-references/evo-inquiry.md),
or reuse it if already loaded and unchanged in this session. Apply relevant
principles within the user's scope and this skill's existing outputs, review
standards, and recovery contracts. Carry them into nested research tasks and
reviewer briefs. Continue authorized work through its necessary steps; honor
budgets, blocking checkpoints, and stopping conditions.
<!-- EVO-INQUIRY:END -->

> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.

# Auto Review Loop: Autonomous Research Improvement

> **Gemini overlay assurance:** verify the actual different-family reviewer before recording `review_independence: cross-family`; `acceptance_status: accepted` requires a positive disposition and the workflow's evidence closure. Negative, unavailable and budget-stop outcomes grant no phase acceptance; same-family responses retain the base provisional contract.

Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.

## Context: $ARGUMENTS

## Evidence closure and bounded stopping

Scores and verdicts remain required interface fields. A positive threshold is
necessary, and every material issue must also have a checked disposition: fixed
with evidence, or excluded with a specific, evidenced scope reason. Reviewer
agreement alone does not resolve an issue. Keep strengths that the evidence
supports; do not invent objections to make another round appear useful.

Apply this closure condition at every positive stop and any review receipt this workflow produces.
An unresolved critical issue prevents a positive receipt even when the score is
high. Preserve existing independent-review requirements and same-family
provisional status. File checks do not establish scientific support.

Before iterating, use the authorized round, time, experiment and cost budgets.
Track which decision-relevant uncertainty each action can resolve. Stop when a
budget is reached or successive rounds produce no new evidence or actionable
change; record the reason and remaining unknowns. A budget/stall/user stop is
completion of the loop, not research acceptance, and grants no acquittal.
Never hide an unfavorable primary result by adding a favorable metric or by
renaming the original hypothesis. Label any exploratory reframing explicitly.

## Constants

- MAX_ROUNDS = 4
- POSITIVE_THRESHOLD: score >= 6/10 AND verdict ∈ {"ready", "almost"} — both must hold, matching the operative STOP CONDITION below. Verdict vocabulary is {"ready", "almost", "not ready"}. (Earlier wording used "or" + a stale verdict set; the AND form is authoritative.)
- REVIEW_DOC: `review-stage/AUTO_REVIEW.md` (cumulative log) *(fall back to `./AUTO_REVIEW.md` for legacy projects)*
- **OUTPUT_DIR = `review-stage/`** — Directory for review output files.
- **REVIEWER_MODEL = `gemini-review`** — Gemini reviewer invoked through the local `gemini-review` MCP bridge. Set `GEMINI_REVIEW_MODEL` if you need a specific Gemini model override.
- **HUMAN_CHECKPOINT = false** — When `true`, pause after each round's review (Phase B) and present the score + weaknesses to the user. Wait for user input before proceeding to Phase C. The user can: approve the suggested fixes, provide custom modification instructions, skip specific fixes, or stop the loop early. When `false` (default), the loop runs fully autonomously.

> 💡 Override: `/auto-review-loop "topic" — human checkpoint: true`

## State Persistence (Compact Recovery)

Long-running loops may hit the context window limit, triggering automatic compaction. To survive this, persist state to `review-stage/REVIEW_STATE.json` after each round:

```json
{
  "round": 2,
  "thread_id": "019cd392-...",
  "status": "in_progress",
  "last_score": 5.0,
  "last_verdict": "not ready",
  "pending_experiments": ["screen_name_1"],
  "timestamp": "2026-03-13T21:00:00"
}
```

**Write this file at the end of every Phase E** (after documenting the round). Overwrite each time — only the latest state matters.

**On completion** (positive assessment or max rounds), set `"status": "completed"` so future invocations don't accidentally resume a finished loop.

## Workflow

### Initialization

1. **Check for `review-stage/REVIEW_STATE.json`** *(fall back to `./REVIEW_STATE.json` if not found — legacy path)*:
   - If neither path exists: **fresh start** (normal case, identical to behavior before this feature existed)
   - If it exists AND `status` is `"completed"`: **fresh start** (previous loop finished normally)
   - If it exists AND `status` is `"in_progress"` AND `timestamp` is older than 24 hours: **fresh start** (stale state from a killed/abandoned run — delete the file and start over)
   - If it exists AND `status` is `"in_progress"` AND `timestamp` is within 24 hours: **resume**
     - Read the state file to recover `round`, `thread_id`, `last_score`, `pending_experiments`
     - Read `review-stage/AUTO_REVIEW.md` to restore full context of prior rounds *(fall back to `./AUTO_REVIEW.md`)*
     - If `pending_experiments` is non-empty, check if they have completed (e.g., check screen sessions)
     - Resume from the next round (round = saved round + 1)
     - Log: "Recovered from context compaction. Resuming at Round N."
2. Read project narrative documents, memory files, and any prior review documents
3. Read recent experiment results (check output directories, logs)
4. Identify current weaknesses and open TODOs from prior reviews
5. Initialize round counter = 1 (unless recovered from state file)
6. Create/update `review-stage/AUTO_REVIEW.md` with header and timestamp

### Loop (repeat up to MAX_ROUNDS)

#### Phase A: Review

Send comprehensive context to the external reviewer:

```
mcp__gemini-review__review_start:
  prompt: |
    [Round N/MAX_ROUNDS of autonomous review loop]

    [Full research context: claims, methods, results, known weaknesses]
    [Changes since last round, if any]

    Please review the work against its question, evidence and intended use.
    Verify consequential claims against actual artifacts. Identify supported
    strengths, material weaknesses, alternative explanations and missing evidence.
    Apply the same evidential standard to favorable and unfavorable conclusions.

    1. Score this work 1-10 for a top venue
    2. List remaining critical weaknesses (ranked by severity)
    3. For each weakness, specify the MINIMUM fix (experiment, analysis, or reframing)
    4. State clearly: is this READY for submission? Yes/No/Almost

    Be brutally honest. If the work is ready, say so clearly.

    === REVIEW SCOPE ===
    Evaluate the actual research question, requested deliverable and applicable
    disciplinary standards. Locate strengths and defects in the supplied evidence;
    do not presume acceptance, rejection or a particular threat model. Distinguish
    observed errors, unsupported claims and optional extensions. Propose the smallest
    adequate correction, citing its failing path, evidence or preserved invariant.
    Keep hypotheses, speculation and unperformed checks explicit. A real boundary
    or reproducibility defect is in scope when it affects this work; unrelated
    infrastructure and speculative redesign are not automatically required.
    Say plainly when something is correct. Do not manufacture findings.
```

After this start call, immediately save the returned `jobId` and poll `mcp__gemini-review__review_status` with a bounded `waitSeconds` until `done=true`. Treat the completed status payload's `response` as the reviewer output, and save the completed `threadId` for any follow-up round.

If this is round 2+, use `mcp__gemini-review__review_reply_start` with the saved completed `threadId`, then poll `mcp__gemini-review__review_status` with the returned `jobId` until `done=true` to maintain continuity.

#### Phase B: Parse Assessment

**CRITICAL: Save the FULL raw response** from the external reviewer verbatim (store in a variable for Phase E). Do NOT discard or summarize — the raw text is the primary record.

Then extract structured fields:
- **Score** (numeric 1-10)
- **Verdict** ("ready" / "almost" / "not ready")
- **Action items** (ranked list of fixes)

**STOP CONDITION**: If score >= 6 AND verdict ∈ {"ready", "almost"} (exact match — "not ready" does NOT qualify) AND material-issue closure is verified → stop loop, document the evidence and final state. Otherwise continue only within the remaining authorized budget; a budget/stall/user stop is not acceptance.

#### Human Checkpoint (if enabled)

**Skip this step entirely if `HUMAN_CHECKPOINT = false`.**

When `HUMAN_CHECKPOINT = true`, present the review results and wait for user input:

```
📋 Round N/MAX_ROUNDS review complete.

Score: X/10 — [verdict]
Top weaknesses:
1. [weakness 1]
2. [weakness 2]
3. [weakness 3]

Suggested fixes:
1. [fix 1]
2. [fix 2]
3. [fix 3]

Options:
- Reply "go" or "continue" → implement all suggested fixes
- Reply with custom instructions → implement your modifications instead
- Reply "skip 2" → skip fix #2, implement the rest
- Reply "stop" → end the loop, document current state
```

Wait for the user's response. Parse their input:
- **Approval** ("go", "continue", "ok", "proceed"): proceed to Phase C with all suggested fixes
- **Custom instructions** (any other text): treat as additional/replacement guidance for Phase C. Merge with reviewer suggestions where appropriate
- **Skip specific fixes** ("skip 1,3"): remove those fixes from the action list
- **Stop** ("stop", "enough", "done"): terminate the loop, jump to Termination

#### Feishu Notification (if configured)

After parsing the score, check if `~/.codex/feishu.json` exists and mode is not `"off"`:
- Send a `review_scored` notification: "Round N: X/10 — [verdict]" with top 3 weaknesses
- If **interactive** mode and verdict is "almost": send as checkpoint, wait for user reply on whether to continue or stop
- If config absent or mode off: skip entirely (no-op)

#### Phase C: Implement Fixes (if not stopping)

For each action item (highest priority first):

1. **Code changes**: Write/modify experiment scripts, model code, analysis scripts
2. **Run experiments**: Deploy to GPU server via SSH + screen/tmux
3. **Analysis**: Run evaluation, collect results, update figures/tables
4. **Documentation**: Update project notes and review document

Prioritization rules:
- Skip fixes requiring excessive compute (flag for manual follow-up)
- Skip fixes requiring external data/models not available
- Prefer reframing/analysis over new experiments when both address the concern
- Add a metric only when it resolves a material question within authorization and budget; retain original primary outcomes

#### Phase D: Wait for Results

If experiments were launched:
- Monitor remote sessions for completion
- Collect results from output files and logs

#### Phase E: Document Round

Append to `review-stage/AUTO_REVIEW.md`:

```markdown
## Round N (timestamp)

### Assessment (Summary)
- Score: X/10
- Verdict: [ready/almost/not ready]
- Key criticisms: [bullet list]

### Reviewer Raw Response

<details>
<summary>Click to expand full reviewer response</summary>

[Paste the COMPLETE raw response from the external reviewer here — verbatim, unedited.
This is the authoritative record. Do NOT truncate or paraphrase.]

</details>

### Actions Taken
- [what was implemented/changed]

### Results
- [experiment outcomes, if any]

### Status
- [continuing to round N+1 / stopping]
```

**Write `review-stage/REVIEW_STATE.json`** with current round, agent id, score, verdict, and any pending experiments.

Increment round counter → back to Phase A.

### Termination

When the loop ends (evidence-backed positive assessment, budget, stall or user stop):

1. Update `review-stage/REVIEW_STATE.json` with `"status": "completed"`
2. Write final summary to `review-stage/AUTO_REVIEW.md`
3. Update project notes with conclusions
4. If stopped for budget, stall or user instruction without evidence closure:
   - List remaining blockers
   - Estimate effort needed for each
   - Suggest whether to continue manually or pivot
5. **Feishu notification** (if configured): Send `pipeline_done` with final score progression table

## Output Protocols

> Follow these shared protocols for all output files:
> - **[Output Versioning Protocol](../shared-references/output-versioning.md)** — write timestamped file first, then copy to fixed name
> - **[Output Manifest Protocol](../shared-references/output-manifest.md)** — log every output to MANIFEST.md
> - **[Output Language Protocol](../shared-references/output-language.md)** — respect the project's language setting

## Key Rules

- **Large file handling**: If the Write tool fails due to file size, immediately retry using Bash (`cat << 'EOF' > file`) to write in chunks. Do NOT ask the user for permission — just do it silently.

- Always ask the Gemini reviewer for strict, high-rigor feedback.
- Save the completed `threadId` from the first `mcp__gemini-review__review_status` result, then use `mcp__gemini-review__review_reply_start` plus `mcp__gemini-review__review_status` for subsequent rounds
- Be honest — include negative results and failed experiments
- Do NOT hide weaknesses to game a positive score
- Implement fixes BEFORE re-reviewing (don't just promise to fix)
- If an experiment takes > 30 minutes, launch it and continue with other fixes while waiting
- Document EVERYTHING — the review log should be self-contained
- Update project notes after each round, not just at the end

## Prompt Template for Round 2+

```
mcp__gemini-review__review_reply_start:
  threadId: [saved from round 1]
  prompt: |
    [Round N update]

    Since your last review, we have:
    1. [Action 1]: [result]
    2. [Action 2]: [result]
    3. [Action 3]: [result]

    Updated results table:
    [paste metrics]

    Please re-score and re-assess. Are the remaining concerns addressed?
    Same format: Score, Verdict, Remaining Weaknesses, Minimum Fixes.

    === REVIEW SCOPE ===
    Evaluate the actual research question, requested deliverable and applicable
    disciplinary standards. Locate strengths and defects in the supplied evidence;
    do not presume acceptance, rejection or a particular threat model. Distinguish
    observed errors, unsupported claims and optional extensions. Propose the smallest
    adequate correction, citing its failing path, evidence or preserved invariant.
    Keep hypotheses, speculation and unperformed checks explicit. A real boundary
    or reproducibility defect is in scope when it affects this work; unrelated
    infrastructure and speculative redesign are not automatically required.
    Say plainly when something is correct. Do not manufacture findings.
```

After this start call, immediately save the returned `jobId` and poll `mcp__gemini-review__review_status` with a bounded `waitSeconds` until `done=true`. Treat the completed status payload's `response` as the reviewer output, and save the completed `threadId` for any follow-up round.