$ the-wire · showcase
enqueue_task resolves once per creator, Gemini 4 Neon support
By RepoJournal · Filed · About Safety Evals · Composed from the cited sources · methodology
Inspect fixes two enqueue_task() behaviors that were silently multiplying or hollowing out tasks added mid-run, and adds the model-info entry needed to drive gemini-4-neon's thinking controls correctly.
fix!: a task added with enqueue_task() from inside a running task runs once, under that task's model UKGovernmentBEIS/inspect_ai
A task added with enqueue_task() from inside a running task now resolves exactly once, under that task's model, instead of once per run model. Under eval() with several models that used to create N copies per creator, most of them on a model nobody asked for; this is a breaking change to that behavior.
fix: tasks added with enqueue_task() in eval-set selection workers run the real task, not an empty placeholder UKGovernmentBEIS/inspect_ai
In eval-set runs, selection-worker pruning used to stay active for the whole process, so a @task factory called by a running solver, tool, scorer or TaskSource returned an empty placeholder Task and enqueue_task() added that shell. The real factory now runs at the call, so task_with() changes survive.
feat(google): support Gemini 4 Neon UKGovernmentBEIS/inspect_ai
Inspect gains a model-info entry for Gemini 4 Neon (gemini-4-neon), GA on the Gemini API as of 2026-11-18, whose thinking controls follow Hydrogen rather than Argon or Carbon. Two of them were being mapped wrong before this: xhigh and max were both sent as HIGH.
docs(design): sandbox agent bridge architecture and trust boundary, as built (#6619) UKGovernmentBEIS/inspect_ai
New as-built design docs for sandbox_agent_bridge() spell out the trust boundary: what the host does with a bridged request (model routing, generation settings, capabilities withheld by default), how approval and execution grants work, and what Inspect records.
docs(design): accepted residual risks of restic checkpoint egress (#6618) UKGovernmentBEIS/inspect_ai
The checkpoint snapshot design now states the accepted residual risks of restic checkpoint egress next to what the egress checks do not establish, including two ways a sandbox can make its own checkpoints fail to capture or restore.
Action items
- → Review eval() runs that call enqueue_task() from inside a task; tasks now resolve once under the creator's model inst... UKGovernmentBEIS/inspect_ai [plan]