ML.ai CodeReference

Limitations

Everything ML.ai deliberately does not do this release, grouped by policy exclusion, parked, or experimental.

Every limitation here has a stated reason. None of them are "we haven't gotten to it yet" unless labeled that way explicitly.

Excluded by policy

Blocked at the network or feature layer, with a specific reason each.

FeatureStatusWhy
Terminal UIExcludedML.ai is an editor extension; shell output already appears in the activity row for the command that produced it
Interactive PTY / terminal streamingExcludedNo user-facing surface this release
Session sharingExcludedPublishes conversation content to a public URL; verified live, blocked in both directions
Engine self-upgradeExcludedThe engine is versioned together with the extension
Shell-expression command templatesExcludedWould execute shell code with no approval gate: the exact thing the approval flow exists to prevent
Universal / Linux / Windows ARM64 / Windows 32-bit packagesExcludedNot built this release; the engine bundle has native binaries, and each platform package has to be built on its own target
Browser-hosted VS CodeExcludedNot supported

Parked

Deliberately not surfaced, each for a specific blocking reason, not effort alone.

FeatureStatusWhy
Price / cost meteringParkedThe engine's routing doesn't supply reliable billing data; ML.ai won't estimate one and present it as fact
Symbol searchParkedThe engine's handler unconditionally returns an empty array, and surfacing it would read as a false "no symbols" claim about your project
Manual compaction controlParkedThe underlying engine route is a stub in this build
Model-facing background shell commandsParkedThe job runner exists and is used internally, but exposing it to the model is gated on durable job status, restart recovery, and owner-bound get/wait/cancel tools: preconditions, not an omission
Subtask commands without a reported event streamParkedThe engine runs some commands as isolated background tasks with no subtask event stream; output would be lost or dumped as an unstructured wall of text. /review shipped once its output path was wired up; this row now covers only what's left unsurfaced.
Guaranteed proposed diffs for shell/MCP mutationsParkedML.ai can't know in advance what an arbitrary command or third-party tool will actually change
A durable learned-memory productParkedOut of scope this phase
Language-server / formatter configurationParkedNot surfaced when the engine reports none available

Experimental, off by default

Experimental features exist and can be turned on, but ship off because of a specific, stated risk.

FeatureSettingWhy off by default
Code modeml-ai.experimental.codeModeDelegation behavior has only been measured with this off; requires a restart to take effect
Worktrees / workspaces / project copies / syncml-ai.experimental.workspacesCan move or delete uncommitted work; some routes report false success; ordinary single-folder workflows don't need it
Isolated runs in a worktreeSame flag, delegate-picker optionInherits the same worktree risk

Shipped

For contrast, the core loop (chat, edits, commands, permission prompts, the command safety classifier, MCP, background runs) is Shipped and not gated behind any flag.