# v2.1.3

DVR 2.1.3 is a reliability and quality release for Structured 1+x vision. It closes the remaining evidence-completion edge cases from Round 1, then simplifies model-visible guidance so capable agents can choose the smallest useful visual tool instead of following prescriptive call recipes.

## Structured 1+x reliability

- Makes `structured-flow-hardening` the sole post-bootstrap completion authority. Core keeps bootstrap sequencing and presentation only; mixed classification remains advisory and never becomes a hidden branch quota.
- Uses tool-specific usable-evidence validation for 1+x completion instead of generic execution metadata. Successful artifacts, engine names, chunk counts, or malformed payloads cannot masquerade as visual evidence.
- Separates all-turn successful evidence accounting from post-bootstrap evidence accounting. Evidence collected before `vision_bootstrap` still consumes an explicit call cap when configured, but it cannot satisfy the required post-bootstrap `x >= 1` step.
- Tightens `vision_detect`: malformed inventories fail instead of collapsing into fake zero-detection evidence, explicit `elements: []` remains a valid negative result, and fully off-image boxes are rejected before clamping while genuine partial overlaps remain supported.
- Restores the public OCR contract everywhere: `vision_ocr` with omitted `engine` or `engine=auto` always tries local Tesseract first, then falls back to the vision model only when local OCR fails or returns no text. Structured mode does not silently rewrite this order.

## Smarter, less prescriptive agent guidance

- Removes the nonexistent `vision_ask` affordance from model-visible guidance and adds a closed-world contract test so future `vision_*` references must correspond to registered tools.
- Treats bootstrap `recommended_followups` as task-independent suggestions, not a downstream plan. The agent chooses follow-up evidence from the user question and the evidence still missing.
- Stops encouraging extra calls once the required post-bootstrap evidence is sufficient; depth strategies remain guidance rather than hidden call-count promises.
- UI guidance no longer implies a fixed `detect + ground` sequence, code guidance requires verbatim fidelity only when the task truly depends on exact/executable code, and mixed images verify only the branch or branches relevant to the user question.

## Settings, clipboard, and DSH compatibility

- Aligns the vision-task timeout defaults across Settings and runtime behavior so the UI no longer advertises a different default from execution.
- Marks progressive vision-tool exposure as restart-only, matching the actual tool-registration lifecycle instead of implying a hot runtime toggle.
- Hardens Web clipboard intake across Windows, QQ/WeChat, bitmap-style screenshots, and misleading MIME declarations: duplicate screenshots are deduplicated and supported image types are reconciled against magic bytes before DSH intake.
- Adds real alpha browser cold-toggle coverage and keeps the presentation/main source contract in CI so model-directory and Vision-toggle compatibility cannot silently regress between queue-loader and live-loader phases.

## Validation

- Release-candidate behavior is covered by the closed-world default test manifest, Node 22/24 CI, DSH rc.6/rc.7/rc.8 contracts, native multimodal cold-resume, P1 routing parity, architecture closure, large-image resource stress, and Windows/macOS/Linux host-sharp integration.
- No settings migration is required. Restart the DSH Web/Desktop process after upgrading so restart-bound tool registration and the updated runtime guidance are loaded.

## Upgrade

Upgrade to 2.1.3 and restart DSH Web/Desktop. Existing Vision Router settings remain compatible.