Commit graph

9 commits

Author SHA1 Message Date
c257dde02f refactor: fold driver pumps into iroh-driver and codecs into transport
Consolidate the duplicated JSON codec into `transport` and relocate the iroh edge-transport pieces into `iroh-driver`, dissolving the `mvp-system` transport shim.

- `transport`: add a canonical `json_codec::JsonCodec<M>` (re-exported from the crate root) as the single JSON codec for serde message types
- `distribution`/`datastream`: drop the per-crate `JsonCodec` copies and the `impl_json_codec!` macro; register SWIM/gossip and publisher messages against the shared `swactor_transport::JsonCodec`
- `iroh-driver`: move `driver_pumps` and `endpoint_advertisement` out of `mvp-system/src/transport/`, re-exporting `EndpointAddrMask`/`advertised_endpoint`/`MVP_IROH_ENDPOINT_ADDR_MASK_ENV`, and relocate the endpoint guarantee test to `iroh-driver/tests/endpoint_advertisement.rs`
- `mvp-system`: delete the `transport/` module and keep codec aggregation in a new `codecs.rs` (`register_mvp_actor_codecs`)
- `mvp-system/node`: shrink `worker_node_runtime.rs` (~260 lines) by adopting the relocated modules and collapsing verbose `emit_stdio_node_event` calls into local `boot()`/`worker_evt()` closures

Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-07-30 12:18:02 +04:00
caba15264e fix: harden edge transport and vastai provisioning
- Edge send pump reconnects and retries dropped streams with 30s timeouts.
- Orchestrator adds vastai host blacklist and provider-start outcome tracking.
- xtask adds benchmark-observability dump-log and gpu-pipeline fact checks.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-07-26 22:23:48 +04:00
841a2de911 feat(mvp-system): working mvp-chat over edge transport
Add iroh-driver edge_transport; restructure mvp_chat/orchestrator/worker bins; drop stale gpu_worker_node_e2e and MVP_NODE_PROVISIONING_SPEC.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-07-22 11:50:53 +04:00
a7d2828cc3 docs(iroh-driver): add spec, slim mvp-system specs
Add the iroh-driver spec; trim and restructure the mvp-system orchestrator and
mvp-chat specs. Reframe prompt RPC as the prompt-engine contract in mvp_chat.md; add an
iroh-driver dependency; minor datastream_transport cleanup.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-07-21 10:25:52 +04:00
ce57012e11 feat: rework datastream into catalog events, add gguf metadata
- Rework the datastream endpoint into a catalog/event model (DatastreamEvent,
  SubscriptionRequest, channel/stream descriptors, DatastreamPublisherActor) across
  endpoint/frame/mux/wire/views.
- Add gguf_metadata planning reader, a dashboard hardware view, and iroh-driver
  datastream transport.
- Grow mvp-system orchestrator/worker_node bins and staging/provisioning; rename
  mvp_one_node_chat->mvp_chat; extend tinygrad worker.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-07-12 10:14:34 +04:00
4811564d0f feat(mvp-system): actor admin control, iroh relay debug
Add node_agent actor and orchestrator/worker_node admin control; iroh-driver relay debugging; ACTOR_CONTROL_AUDIT_IDEAS notes.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-07-09 12:53:53 +04:00
0ffc5fd275 feat: add mvp provisioning subsystem and datastream transport
mvp-system: provisioner actor, provisioning module, node_agent, dashboard_view,
observability_surface; expand gpu_worker ctl/ingress/egress and run_plan.
iroh-driver: replace relay binary with datastream_transport; datastream gains endpoint
abstraction. Archive pipeline-parallel-inference app to old-pipeline-parallel-inference.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-06-25 16:30:18 +04:00
cf996d9697 refactor(dashboard): rebuild around swactor worker view
Replace telemetry/history/plugin/topology/warnings layer with store/view and
swactor worker_page/worker_view fed by datastream frames. Add mvp-system
local_e2e_cluster harness; archive pipeline-parallel-inference to
old-pipeline-parallel-inference.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-06-25 11:29:16 +04:00
f4dee176c0 refactor: extract iroh-driver crate, drop node example
Move iroh_driver and the relay binary out of distribution into a dedicated
crates/iroh-driver (lib re-exports IrohDriver; relay bin renamed). Remove the node crate
and the single-gpu-inference example; drop the docker/datastream demo. Slim
pipeline-parallel vastai.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-06-24 00:10:41 +04:00