This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+1 more
Affected surfaces
Summary
AI summaryAdds governance tiers with soft, per-session limits for remove_motion_blur and generate_speech operations.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Adds governance tiers for media‑creating Resolve 21 AI ops. Adds governance tiers for media‑creating Resolve 21 AI ops. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Medium |
Introduces new module resolve_ai_governance.py with tiers, check(), and status(). Introduces new module resolve_ai_governance.py with tiers, check(), and status(). Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Medium |
Adds MCP actions media_analysis(get_ai_governance) and media_analysis(set_ai_governance). Adds MCP actions media_analysis(get_ai_governance) and media_analysis(set_ai_governance). Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Medium |
Adds Governance section in AI Console with tier picker and live consumption gauges. Adds Governance section in AI Console with tier picker and live consumption gauges. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Medium |
Imposes soft per‑session limits on remove_motion_blur and generate_speech based on selected governance tier. Imposes soft per‑session limits on remove_motion_blur and generate_speech based on selected governance tier. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Medium |
Adds governance block to confirm preview for remove_motion_blur and generate_speech ops. Adds governance block to confirm preview for remove_motion_blur and generate_speech ops. Source: llm_adapter@2026-06-05 Confidence: low |
— |
| Feature | Low |
Adds `governance` block to confirm preview for the two creators showing usage, projection, warnings, exceeded/near status. Adds `governance` block to confirm preview for the two creators showing usage, projection, warnings, exceeded/near status. Source: granite4.1:30b@2026-06-05-audit Confidence: low |
— |
Full changelog
Adds governance tiers for the media-creating Resolve 21 AI ops. Phase 3 (final) of the staged AI-ops build: ledger → console → governance.
The two ops that render new files — remove_motion_blur and generate_speech — now have soft, per-session limits chosen by a named tier:
| dimension | off | lenient | standard | strict |
|---|---|---|---|---|
| deblur runs | ∞ | 50 | 15 | 5 |
| speech runs | ∞ | 50 | 15 | 5 |
| media created | ∞ | 50 GB | 10 GB | 2 GB |
| render time | ∞ | 1 h | 20 min | 5 min |
Governance is advisory — it never hard-blocks (the ops are already confirm-token gated). When you're near or over the active tier, the confirmation dialog surfaces a warning before you proceed; limits are computed from the v2.30.0 AI-ops ledger for the current session.
- New module
resolve_ai_governance.py— tiers +check()+status(). Default tier:standard. - New MCP actions
media_analysis(get_ai_governance)/media_analysis(set_ai_governance, preset, overrides?). Override keys:deblur_runs,speech_runs,render_bytes,render_wall_clock_ms(int orunlimited). - Confirm preview for the two creators carries a
governanceblock (usage, projected, warnings, exceeded/near). - Control panel — the AI Console gains a Governance section: a tier picker (with each tier's thresholds) + live consumption gauges; the confirm dialog shows the warning inline.
This completes the staged AI-ops build. Validated live against Resolve Studio 21.0.0.47.
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]