trending/OpenShell
1
0
Fork 0
mirror of https://github.com/NVIDIA/OpenShell.git synced 2026-10-04 16:39:35 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,624 Commits 458 Branches 135 Tags
dev
Commit Graph
14 Commits
Author SHA1 Message Date
Drew Newberry a649aa42fc docs: add 0.1.0 upgrade guide outline (#3540) 
* docs: add 0.1.0 upgrade guide outline

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs: add upgrade change provenance

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs: update 0.1.0 upgrade guidance

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs: move upgrade navigation below security

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs: remove release notes page

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs: announce OpenShell 0.1.0

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs: reorganize guides and require user-owned images

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs: reorganize navigation around core concepts

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs: simplify navigation and tutorial catalog

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs: refine 0.1.0 release highlights

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs: align navigation and 0.1.0 guidance

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

---------

Signed-off-by: Drew Newberry <anewberry@nvidia.com>
 2026-09-23 20:26:25 +00:00
John T. Myers f4dc6be4b2 refactor(inference): remove managed inference routes (#3195) 
* refactor(inference): remove managed inference routes

Closes #3172

Remove the inference route control plane, inference.local data path, built-in router crate, and SDK surface. Move inference workloads to explicitly imported provider profiles and native endpoints, with migration cleanup and updated tests and documentation.

Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com>

* fix(policy): preserve alternate upstream isolation

Restore the provider policy activation guard so legacy OpenAI and Anthropic providers configured for alternate base URLs do not grant egress to the built-in public vendor endpoints.

Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com>

---------

Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com>
 2026-09-09 18:47:22 +00:00
Matthew Grossman bc14018cad feat(sandbox): use policy-first OCI image identity (#2509) 
* feat(sandbox): use policy-first OCI image identity

Closes #2331

Preserve per-field policy omission, derive Docker and Podman fallbacks from the inspected immutable image, and resolve the final numeric identity before starting agent children.

Signed-off-by: Matthew Grossman <mgrossman@nvidia.com>

* fix(sandbox): preserve declared process identities

Keep explicit policy values and OCI-declared names intact, defer passwd lookup until a primary GID is required, and refresh stale policy examples.

Signed-off-by: Matthew Grossman <mgrossman@nvidia.com>

* fix(supervisor): reuse resolved OCI identity

Signed-off-by: Matthew Grossman <mgrossman@nvidia.com>

* fix(supervisor): allow Linux pre-exec arguments

Signed-off-by: Matthew Grossman <mgrossman@nvidia.com>

* fix(kubernetes): protect resolved sandbox identity

Signed-off-by: Matthew Grossman <mgrossman@nvidia.com>

* fix(sandbox): prepare workspace for OCI identity

Signed-off-by: Matthew Grossman <mgrossman@nvidia.com>

* refactor(sandbox): own only workspace root

Signed-off-by: Matthew Grossman <mgrossman@nvidia.com>

* fix(sandbox): harden partial identity drops

Signed-off-by: Matthew Grossman <mgrossman@nvidia.com>

* test(sandbox): scope OCI image e2e to Docker

Signed-off-by: Matthew Grossman <mgrossman@nvidia.com>

* fix(sandbox): narrow OCI identity fallback scope

Signed-off-by: Matthew Grossman <mgrossman@nvidia.com>

* test(podman): cover OCI identity launch

Signed-off-by: Matthew Grossman <mgrossman@nvidia.com>

* fix(podman): exercise OCI fallback in E2E

Signed-off-by: Matthew Grossman <mgrossman@nvidia.com>

---------

Signed-off-by: Matthew Grossman <mgrossman@nvidia.com>
 2026-07-29 05:27:21 +00:00
Mesut Oezdil ae5127f14d fix: correct example paths in local-inference README (#1676) 
* fix: correct example paths in local-inference README

* fix: correct example paths in local-inference routes.yaml
 2026-06-02 21:53:14 +00:00
Drew Newberry 70a0f6c547 refactor(cli): remove gateway lifecycle management (#1221) 2026-05-07 09:54:13 -07:00
Piotr Mlocek df38d1f66f feat(ci): add Markdown and Mermaid linting (#933) 2026-04-24 11:27:02 -07:00
Drew Newberry fbd93a4632 refactor: rename navigator- crate prefix to openshell- (#277) 2026-03-13 02:02:18 -07:00
Drew Newberry 7b0a243304 ci: remove sandbox docker build from publish and e2e workflows (#275) 2026-03-13 00:56:07 -07:00
Piotr Mlocek 14e296d318 fix(cli): add --no-keep for ephemeral sandbox create cleanup (#258) 2026-03-12 17:18:39 -07:00
John T. Myers 2e4c2fcc84 fix(proxy): stream inference responses instead of buffering entire body (#261) 
* fix(proxy): stream inference responses instead of buffering entire body

The inference.local proxy path called response.bytes().await which
buffered the entire upstream response before sending anything to the
client. For streaming SSE responses this inflated TTFB from sub-second
to the full generation time, causing clients with TTFB timeouts to abort.

Add a streaming proxy variant that returns response headers immediately
and forwards body chunks incrementally using HTTP chunked transfer
encoding. Non-streaming responses and mock routes continue to work
through the existing buffered path.

Closes #260

* docs: update architecture docs and example for inference streaming

* test(example): add direct NVIDIA endpoint tests via L7 TLS intercept

Expand inference example to 4 test cases: inference.local and direct
endpoint, each streaming and non-streaming. The direct path exercises
the L7 REST relay (relay_chunked) to verify it already streams
correctly. NVIDIA_API_KEY is picked up from the sandbox env when
started with --provider nvidia.
 2026-03-12 10:36:41 -07:00
Drew Newberry 984d1a6e5c chore: rename project from NemoClaw to OpenShell (#198) 2026-03-10 11:49:09 -07:00
Piotr MlocekandMiyoung Choi 107c85d1d7 docs(inference): clarify local inference routing (#190) 
* docs(inference): clarify local inference routing

* docs(inference): update provider and model examples

* fix doc build

---------

Co-authored-by: Miyoung Choi <miyoungc@nvidia.com>
 2026-03-09 21:34:14 -07:00
Drew Newberry 07b9d5d00e feat(cli): restructure CLI commands for simpler UX (#156) 2026-03-06 16:26:39 -08:00
Piotr Mlocek 31d7ca53ff refactor(inference): simplify routing — introduce inference.local, remove implicit catch-all (#146) 
Remove multi-route CRUD system and replace with single managed cluster
route (inference.local). Key changes:

- Remove inference route CRUD RPCs and CLI commands
- Remove InspectForInference OPA action; policy is binary allow/deny
- Introduce AuthHeader enum and InferenceProviderProfile in navigator-core
- Router is now provider-agnostic: auth style carried on ResolvedRoute
- Replace InferenceRouteSpec with ClusterInferenceConfig (2 fields vs 8)
- Rename proto: routing_hint->name, SandboxResolvedRoute->ResolvedRoute,
  GetSandboxInferenceBundle->GetInferenceBundle, drop sandbox_id param
- Rename RouteConfig.route -> RouteConfig.name; use inference.local
- Add 'nemoclaw cluster inference update' for partial config changes
- Delete stale navigator.inference.v1.rs checked-in proto file
- Update architecture docs, agent skills, and CLI reference

Closes #133
 2026-03-06 13:54:23 -08:00