# ADR-012: Rolling Token Window Screening for Long Documents

## Status

Accepted

## Context

The Phase 1 `screen()` API processes the full input as a single forward pass
through the detector model. This works for inputs within the model's context
window (2048 tokens for SmolLM2-135M) but fails for longer documents. Two
distinct windowing concepts exist in the detection pipeline:

1. **Token-level smoothing** (already in the codebook): Within a single
   forward pass, per-token z-coordinates are smoothed with a rolling average
   (window=8) before classification. This operates on the `(seq_len, 3)` z
   coordinate sequence.

2. **Input-level rolling windows** (this ADR): For long documents that exceed
   the model's context window, chunk the text into overlapping token windows
   and screen each window independently. Each window produces its own z-vector
   and alarm. Windows are aggregated into a document-level verdict.

Research ([rolling-window-analysis.md](../../research/streaming-screening-patterns/rolling-window-analysis.md))
confirmed that:
- Meta's PromptGuard 2 uses a similar approach (512-token segments)
- Max pooling is the correct aggregation strategy (consistent with existing
  weighted-max score composition)
- 25% overlap (512 tokens for SmolLM2-135M) balances detection quality vs
  throughput — enough to catch boundary-spanning injections
- Character offset mapping (from HuggingFace tokenizer `offset_mapping`)
  enables granular "section X is suspicious" reporting
- The Rust reference implementation in taskgraph-semantic validates the
  window creation algorithm

## Decision

Implement rolling token window screening as the Phase 2 `screen_document()`
API, with the following parameters:

- **Window size**: Model's max sequence length (2048 for SmolLM2-135M)
- **Overlap**: 25% (512 tokens) — same as PromptGuard's entire context window
- **Aggregation**: Max pooling across per-window, per-direction P(active)
  scores
- **Short input handling**: Inputs shorter than one window fall through to
  `screen()` with no overhead
- **Character offset tracking**: Token-to-character mapping for granular
  reporting of flagged sections

The two windowing concepts (token-level smoothing, input-level rolling windows)
are composable and solve different problems at different levels.

## Consequences

**Positive**:
- Long documents (academic papers, reports) can be screened without truncation
- Granular reporting identifies which sections are suspicious, not just the
  whole document
- Windows can be processed in parallel for throughput scaling
- Natural fallback: short inputs get the fast single-window path
- Character offsets enable UI integration (highlighting flagged sections)
- Pattern translates directly to Rust for future embedding system integration

**Negative**:
- Throughput cost: N windows = N forward passes. A 10K-token document needs
  ~7 windows at 25% overlap.
- Overlap regions are processed multiple times, increasing compute
- API surface expands — users must choose between `screen()` and
  `screen_document()`
- Edge cases around window boundaries (partial word tokens, very short
  windows) need careful handling

## References

- [rolling-window-analysis.md](../../research/streaming-screening-patterns/rolling-window-analysis.md) — Full research with API design and implementation sketch
- [OQ-03](../open-questions.md) — Original open question
- [firewall.md](../firewall.md) — Current screening API
- [codebook.md](../codebook.md) — Token-level smoothing (separate from this)
- taskgraph-semantic: `/workspace/@alkimiadev/taskgraph-semantic/src/embedding.rs` — Rust reference for `create_rolling_windows()`