## Investigate why "entire review" in ../entire.io is failing

4w ago·4.8s·1 call

### Reproduced with just Gemini:

```
cd ../entire.io
../cli/entire review general --agent gemini --timeout 3m
```

**Root cause:** **Gemini CLI is failing due to quota exhaustion**, not because of Entire’s hook message.

Key stderr:

```
TerminalQuotaError: You have exhausted your daily quota on this model.

Quota exceeded for metric:
generativelanguage.googleapis.com/generate_content_free_tier_requests
limit: 20
model: gemini-3.5-flash

Please retry in 49.578347863s.
```

The confusing line:

```
Entire CLI will link this conversation to your next commit.
```

is just Entire’s hook message being printed first in stderr, so the review status table truncates there and makes it look like the cause.

I also saw prior Gemini transcript/log evidence of the same issue:

```
Subagent 'generalist' failed. Error: You have exhausted your daily quota on this model.
```

**Fix options:**
- wait for Gemini quota reset / retry later  
- use a paid Gemini API key or higher quota project  
- switch Gemini to another model if available  
- remove/skip Gemini from the Entire review profile for now  
- run only non-Gemini reviewers until quota recovers

### Yes — it’s the same underlying issue.
What’s happening:
- Gemini starts the review.  
- Gemini invokes its local subagent: `generalist`.  
- That subagent also uses `gemini-3.5-flash`.  
- The API returns `429` quota exceeded.  
- Gemini CLI retries after ~52–62s.  
- The next top-level Gemini turn also hits quota and exits with status 1.  
- Entire then reports Gemini review as failed.

### The important lines are:

```
TerminalQuotaError: You have exhausted your daily quota on this model.
```

and:

```
Quota exceeded ... model: gemini-3.5-flash
```

The `limit: 5` vs `limit: 20` likely reflects different Gemini quota buckets/metrics, but both are quota failures for the same model.

### Changes Implemented:
- Multi-agent review now only fails the command if **no reviewer succeeds**.  
- A failed reviewer is still shown in terminal output/counts.
- Failed reviewer output is excluded from:
  - judge synthesis prompt  
  - trail fallback findings/report body

#### Conclusion:
- Current behavior leads to inconsistent results, which can confuse users.
- Suggested future behavior adjustments ensuring clarity and reducing the impact of individual failures on overall results.