This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+1 more
Summary
AI summaryAdds a usage ledger for Resolve‑local AI operations tracking invocation metrics and output file accounting.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Low |
Adds Resolve AI-ops ledger for tracking usage and resource accounting of Resolve-local AI operations. Adds Resolve AI-ops ledger for tracking usage and resource accounting of Resolve-local AI operations. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Low |
Introduces new table `resolve_ai_op_usage` in timeline_brain DB schema v7. Introduces new table `resolve_ai_op_usage` in timeline_brain DB schema v7. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Low |
Adds new module `src/utils/resolve_ai_ledger.py` with `timed()` context manager and usage utilities. Adds new module `src/utils/resolve_ai_ledger.py` with `timed()` context manager and usage utilities. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Low |
Adds instrumentation to consolidated `folder`/`media_pool_item` AI handlers and `project_settings.generate_speech`. Adds instrumentation to consolidated `folder`/`media_pool_item` AI handlers and `project_settings.generate_speech`. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Low |
Adds new MCP action `media_analysis(action="get_resolve_ai_usage", …)` returning usage summary and recent records. Adds new MCP action `media_analysis(action="get_resolve_ai_usage", …)` returning usage summary and recent records. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Low |
Adds read‑only "Resolve 21 AI ops" control panel card backed by `/api/resolve_ai_usage`. Adds read‑only "Resolve 21 AI ops" control panel card backed by `/api/resolve_ai_usage`. Source: llm_adapter@2026-06-05 Confidence: high |
— |
Full changelog
Adds the Resolve 21 AI-ops ledger — usage/time/file accounting for the Resolve-local AI operations added in v2.29.0 (audio classification, IntelliSearch, slate, motion-deblur, speech generation). These run on Resolve's own GPU/AI engine and do not consume the Claude-side analysis token budget, so they get their own ledger instead of being metered by the analysis-caps layer.
This is Phase 1 of a staged build: ledger → interactive console → governance.
What's tracked
Every run of the five 21.0 ops records: op name, op class (analysis vs render), clip id, success/failure, wall-clock time, and — for the two media-creating ops (remove_motion_blur, generate_speech) — the output file path and byte size. The reliable signal is invocation counts + the file/disk accounting for the creators; durations for the bool-returning analysis ops reflect the script-call time.
What's new
- New table
resolve_ai_op_usage(timeline_brain DB schema v7). - New module
src/utils/resolve_ai_ledger.py—timed()context manager +record_op/get_usage/get_summary. All writes are best-effort and never block or mask the underlying Resolve op. - Instrumentation on the consolidated
folder/media_pool_itemAI handlers andproject_settings.generate_speech. - New MCP action
media_analysis(action="get_resolve_ai_usage", session_only?, op?, limit?)→{summary, recent}. - Control panel: read-only "Resolve 21 AI ops" card backed by
/api/resolve_ai_usage.
Notes
Granular --full server instrumentation is deferred (the consolidated server is the default surface). Validated live end-to-end against Resolve Studio 21.0.0.47. Tool counts unchanged.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
Related context
Beta — feedback welcome: [email protected]