> ## Documentation Index
> Fetch the complete documentation index at: https://docs.reasonblocks.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Monitor weights and profiles

> The six server-side trajectory monitors, the built-in task profiles (coding, pr_review, qa) that weight them, and how to override weights per call.

ReasonBlocks evaluates trajectory health with six trajectory monitors that run **server-side** on `POST /monitors/evaluate`. `task_profile` selects which weight preset the server applies; the weighted sum of the monitor scores is the composite that drives steering injection.

<Note>
  These weights live in rb-api, not the SDK. The SDK forwards your `task_profile` (and any `monitor_weights` override) to the server, which owns the resolution. There is no local monitor suite to weight on the client.
</Note>

## The six monitors

Each monitor returns a score in `[0, 1]` where `1` is maximum badness. A monitor "fires" when its individual score crosses the fire threshold; the weighted sum across all six is the composite.

| Monitor               | What it detects                                                                                                                                                    |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `claim_contradiction` | The agent's stated conclusions contradict each other or earlier findings. The only detector that examines what the agent *concluded*, not what it called.          |
| `semantic_loop`       | The same action or search repeated with reworded inputs (embedding-based, so "session timeout" / "session expiry" / "session token expiration" count as one loop). |
| `verification_skip`   | The agent reaches a conclusion without verifying its work (no test run, no re-read of the changed file).                                                           |
| `cyclic_compression`  | Repeated re-summarization / context churn — the agent compresses and re-derives the same state in cycles.                                                          |
| `late_sprawl`         | The trajectory sprawls late: new tools and tangents introduced deep into a run that should be converging.                                                          |
| `silent_topic_drift`  | The agent quietly drifts off the original task without acknowledging the change.                                                                                   |

## Built-in profiles

Three profiles are defined in `rb-api/app/scoring/monitors.py` (`WEIGHTS_BY_PROFILE`). Select one with `task_profile`:

```python theme={null}
from reasonblocks import ReasonBlocks

rb = ReasonBlocks(
    api_key="rb_live_...",
    task_profile="coding",   # or "pr_review", "qa"
)
```

### `coding` (default)

Standard weights for an agent that edits code, runs tests, and may loop. `claim_contradiction` leads.

| Monitor               | Weight |
| --------------------- | ------ |
| `claim_contradiction` | `0.30` |
| `semantic_loop`       | `0.25` |
| `verification_skip`   | `0.15` |
| `cyclic_compression`  | `0.10` |
| `late_sprawl`         | `0.10` |
| `silent_topic_drift`  | `0.10` |

### `pr_review`

Read-only review agent. `semantic_loop` leads — review agents most often fail by re-explaining the same diff — and `cyclic_compression` / `late_sprawl` are raised for runs that sprawl across files.

| Monitor               | Weight |
| --------------------- | ------ |
| `claim_contradiction` | `0.20` |
| `semantic_loop`       | `0.30` |
| `verification_skip`   | `0.10` |
| `cyclic_compression`  | `0.15` |
| `late_sprawl`         | `0.15` |
| `silent_topic_drift`  | `0.10` |

### `qa`

QA / tutoring agent. `claim_contradiction` and `silent_topic_drift` dominate (wrong or off-topic answers are the primary failure mode); verification and compression matter less.

| Monitor               | Weight |
| --------------------- | ------ |
| `claim_contradiction` | `0.40` |
| `semantic_loop`       | `0.15` |
| `verification_skip`   | `0.05` |
| `cyclic_compression`  | `0.05` |
| `late_sprawl`         | `0.10` |
| `silent_topic_drift`  | `0.25` |

Resolution order on the server: defaults ← named profile preset ← per-call `monitor_weights` overrides. Unknown monitor names in overrides are dropped; negative weights are clamped to `0`; each weight is capped at `1.0`.

## Per-call weight overrides

Pass `monitor_weights` on `ReasonBlocksConfig` to override individual weights on top of the chosen profile. The override is forwarded into `MonitorSteeringInjection` and rides on every `POST /monitors/evaluate` request.

```python theme={null}
from reasonblocks import ReasonBlocksConfig

config = ReasonBlocksConfig(
    monitor_task_profile="coding",
    monitor_weights={
        "semantic_loop": 0.40,    # raise — catch loops sooner
        "verification_skip": 0.05,  # lower — your agent verifies elsewhere
    },
)
```

Partial dicts are fine — unspecified monitors fall through to the profile, then to server defaults.

<Note>
  `monitor_weights` is only a field on `ReasonBlocksConfig`. The simpler `ReasonBlocks(...)` constructor doesn't expose it — use the config + `build_middleware` path when you need per-call weight overrides.
</Note>

## Custom profiles

You can create and manage named profiles per organization through the dashboard or the REST API (`GET/POST /v1/monitor/profiles`). A custom profile referenced by `task_profile` resolves the same way as a built-in. The set of valid monitor names is returned by `GET /v1/monitor/scorers`.