Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
Geometry service HTTP API
The client (client/atas/world/geometry_client.py) is the only caller. All /v1 routes accept
Authorization: Bearer $GEOMETRY_API_TOKEN when a token is configured. Identifiers
(run_id, story_id, scene_id, shot_id, event_id) are [A-Za-z0-9_-]+.
Health
GET /healthz→{"status": "ok"}while the process serves requests.GET /readyz→200with"ready": truewhen the Vista4D code, its Python, the Pi3X and SAM3 weights, a writable hot root andnvidia-smiare all present;503and the failing check otherwise.
Jobs
POST /v1/jobs creates a job and returns {"job_id": ...}. Identical requests return the same job
(a request fingerprint); retry_failed: true re-queues a failed one. Poll GET /v1/jobs/{job_id}
until status is succeeded or failed. While a job waits for a card its stage is
waiting_gpu; admission is by free GPU memory.
Reconstruction (multipart form)
Fields: video (the reviewed clip), run_id, story_id, shot_id, scene_id, event_id,
duration, world_time_start, dynamic_keywords (JSON list of SAM3 class nouns observed in the
clip), entity_registry, review_lineage, publication_mode=reviewed_candidate_v1.
The service reconstructs the clip (Pi3X + SAM3, dense per-frame RGB-D and dynamic masks), then
either builds the scene's initial world (first observation) or registers the clip to the committed
scene world with anchored fusion. The result's fuse block reports registered (the paper's r)
and, when registered, a candidate_job_id with publication_status: pending_review. Nothing is
published by reconstruction alone.
Render (JSON, type: "render", camera_contract: "semantic-camera-v1")
Renders the committed scene memory along a planned camera: geometry_layers: "l1" for ordinary
shots, "l1+l2" with render_mode: "recapture", source_shot_id, source_event_id,
source_time_start/end for a historical event (static L1 and the source clip's time-local dynamic
points share one depth buffer). camera_plan comes from the visual planner after
/v1/camera-context; camera_relation is continuous, cut_recompose or recapture.
Fetch the result with GET /v1/jobs/{job_id}/artifacts/memory_input.mp4.
Camera context
POST /v1/camera-context returns the observation the visual planner grounds subjects in (source
shot, frame index, crop and sampling metadata, current world version) and a context_id. A render
whose plan carries a stale context_id is refused.
World publication
POST /v1/world-publicationpublishes a registered candidate as the next world version. It is the state-update check (a): the film review must certify the exact reconstructed bytes, the review and reconstruction lineage must agree, the candidate must belong to the requested scene, and its parent version must still be current. A stale parent returns409.POST /v1/world-rebasere-registers such a candidate against the newer world.