3 Commits

Author	SHA1	Message	Date
Diego Rodrigues de Sa e Souza	a7ddcf16ba	feat(bridge): native-vision skip guard + configurable describe output cap (#10289) ... * test(bridge): explicit native-vision skip guard + skip log * feat(bridge): configurable describe output cap (modalityBridgeVisionMaxChars) * feat(dashboard): maxChars field on Modality Bridge vision tab Add the "Max description characters" field to the Vision tab's Advanced panel (modalityBridgeVisionMaxChars, clamped to the 100-50000 schema range with 0 treated as the explicit "unlimited" sentinel), wire the en.json copy and sync it across all 42 locales, and document the new setting in GUARDRAILS.md. * fix(bridge): allow explicit 0 to disable the describe cap updateSettingsSchema previously rejected modalityBridgeVisionMaxChars: 0 because the field's range was min(100).max(50000), so a dashboard PATCH sending the explicit "unlimited" sentinel would 400. Widen the schema to z.union([z.literal(0), z.number().int().min(100).max(50000)]) so 0 validates as its own valid value, not just an implicit default. * chore(i18n): resync locale keys after release merge * chore(quality): rebaseline deadExports for the OCR/image-to-text series --------- Co-authored-by: Xiangzhe <bakryun0718@proton.me>	2026-08-14 13:06:29 -03:00
Diego Rodrigues de Sa e Souza	4d0182daa0	feat: bridge audio inputs for text-only models (#9807) ... * feat(modality-bridge): resolve audio input capability * feat(modality-bridge): resolve audio runtime settings * feat(modality-bridge): add audio transcription helpers * feat(modality-bridge): add Audio Bridge guardrail * feat(dashboard): make Modality Bridge audio tab functional * docs(guardrails): document Audio Bridge runtime * fix(modality-bridge): harden audio catalog and response header * chore(changelog): record audio modality bridge --------- Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>	2026-08-10 20:10:07 -03:00
Diego Rodrigues de Sa e Souza	71c85f31cd	feat(guardrails): modality bridge core — vision mode/task-aware/cache/input_image + modalityBridge settings (#9759) ... * feat(sse): unified media-part detection helper (image+audio, input_image) * refactor(guardrails): extractImageParts/comboStructure delegate to unified media detector * fix(sse): media detector — audio parts no longer shadow sibling/nested image indicators * fix(guardrails): close extract↔replace contract for input_image (allowlist + splice) * perf(guardrails): skip media traversal when bridge disabled; short-circuit combo image check * feat(guardrails): in-memory LRU bridge cache (sha256 keyed) * feat(settings): modalityBridge* schema with legacy visionBridge* fallback * feat(db): migrate visionBridge* settings to modalityBridge* (idempotent) * refactor(guardrails): harden bridge cache key/config + settings resolution (review minors) * feat(guardrails): vision bridge mode selector (auto/describe/reroute) short-circuit * feat(guardrails): task-aware vision description prompt (default on) * feat(guardrails): describe-path cache integration * docs(guardrails): review polish — cache-key coupling notes + helper header * feat(guardrails): in-memory bridge stats + modality-bridge response header * feat(api): modality bridge stats endpoint + header wiring in chat handler * docs(guardrails): document modality bridge mode/task-aware/cache/header + stats endpoint * chore: untrack _tasks symlink (inherited from base tip; blocks pre-commit tracked-artifacts gate) * fix(db): renumber modality bridge migration 139->140 (base renumbered ccr_blocks to 139) * docs(guardrails): migration filename touch-up 139->140 * docs(db): stale comment touch-ups after 139->140 renumber and #9688 landing * fix(db): renumber modality bridge migration 140->141 (base renumbered connection_runtime_state to 140) * test(db): migration test titles 139->141 --------- Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>	2026-08-08 01:59:11 -03:00