mirror of
https://github.com/NVIDIA/OpenShell.git
synced 2026-10-15 05:09:44 +08:00
pull-request/2147
147
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Evan Lezar
|
45614a3fb6 |
refactor(api): remove SandboxTemplate.volume_claim_templates (#2088)
The field was added during the Kubernetes driver extraction refactor (#817) as a pass-through mechanism, but was never wired up to a CLI flag, Python SDK helper, or any documentation. The only reachable user path was raw gRPC construction. The Kubernetes driver now always injects the default workspace PVC, removing the branching logic that checked for a user-supplied VCT. Field number 9 is reserved in the proto to prevent reuse. Signed-off-by: Evan Lezar <elezar@nvidia.com> |
||
|
Evan Lezar
|
0a25fdf525 |
refactor(core): remove unused extra bind addresses (#2059)
Signed-off-by: Evan Lezar <elezar@nvidia.com> |
||
|
Evan Lezar
|
a5161d0bc3 |
refactor(server): normalize compute driver config acquisition (#1974)
* refactor(server): remove unused compute runtime constructor parameter Signed-off-by: Evan Lezar <elezar@nvidia.com> * refactor(server): normalize compute driver type imports Signed-off-by: Evan Lezar <elezar@nvidia.com> * refactor(server): key driver config tables by name Signed-off-by: Evan Lezar <elezar@nvidia.com> * refactor(server): normalize compute driver config acquisition Signed-off-by: Evan Lezar <elezar@nvidia.com> --------- Signed-off-by: Evan Lezar <elezar@nvidia.com> |
||
|
krishicksandddurst
|
7bce1223dc |
feat(policy): add JSON-RPC and MCP L7 policies (#1865)
Add policy schema, proto, provider profile, OPA, and L7 proxy support for `protocol: json-rpc` and `protocol: mcp`. Generic JSON-RPC endpoints match exact method names only, with `method: "*"` as the all-method sentinel; wildcard/glob methods and params matchers are rejected. Parse JSON-RPC request bodies and batches in the forward proxy, deny response-shaped client frames, limit receive-stream GET allowance to MCP endpoints, and redact params in decision logs. Preserve L7 rule params on the proto load path so MCP `tools/call` tool filters behave like YAML-loaded policies. Add MCP conformance coverage, JSON-RPC L7 e2e coverage, and docs for the new protocols and current matcher limitations. Signed-off-by: Kris Hicks <khicks@nvidia.com> Co-authored-by: ddurst <267424412+ddurst-nvidia@users.noreply.github.com> |
||
|
Gal Zaidman
|
45e5a5d128 |
fix(server): prevent exec relays from hanging on idle connections (#1992)
Add HTTP/2 keepalive on supervisor multiplex connections so half-dead sessions cannot leave in-flight exec relays parked indefinitely. Configure SSH keepalive on exec relay clients so long silent commands are not timed out on stdout idle alone; wedged or orphaned relays fail after missed keepalives instead. After a command reports exit status, bound how long the gateway waits for the trailing channel close. Return UNAVAILABLE when a relay closes before reporting exit status rather than defaulting to exit code 1. Signed-off-by: Gal Zaidman <gzaidman@nvidia.com> |
||
|
Taylor Mutch
|
ba21bb32a2 |
feat(kubernetes): support agent-sandbox v1beta1 (#2009)
* feat(kubernetes): support agent-sandbox v1beta1 Signed-off-by: Taylor Mutch <taylormutch@gmail.com> * ci(kubernetes): test agent-sandbox api versions Signed-off-by: Taylor Mutch <taylormutch@gmail.com> * fix(kubernetes): retry agent-sandbox raw 404s Signed-off-by: Taylor Mutch <taylormutch@gmail.com> * fix(kubernetes): harden agent-sandbox api setup Signed-off-by: Taylor Mutch <taylormutch@gmail.com> * fix(kubernetes): cache agent-sandbox api version Signed-off-by: Taylor Mutch <taylormutch@gmail.com> * docs(kubernetes): document agent-sandbox upgrade behavior Signed-off-by: Taylor Mutch <taylormutch@gmail.com> * refactor(kubernetes): collapse agent-sandbox api selection Signed-off-by: Taylor Mutch <taylormutch@gmail.com> --------- Signed-off-by: Taylor Mutch <taylormutch@gmail.com> |
||
|
John T. Myers
|
b855d8d872 |
fix(policy): reserve provider rule namespace (#1991)
Closes #1982 Reject user-authored _provider_* network policy keys at gateway boundaries, strip provider-derived rules from sandbox sync, and document the round-trip workflow. Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> |
||
|
Evan Lezar
|
e3382cb447 |
fix(server): update driver spec test argument (#2022)
* fix(server): update driver spec test argument Signed-off-by: Evan Lezar <elezar@nvidia.com> * test(server): stabilize concurrent lease steal test Signed-off-by: Evan Lezar <elezar@nvidia.com> --------- Signed-off-by: Evan Lezar <elezar@nvidia.com> |
||
|
st-grandEvan Lezar
|
75a317ea45 |
feat(server): support out-of-tree compute drivers via --compute-driver-socket (#1703)
* feat(server): support remote compute driver endpoints Add named remote compute driver endpoint support to the gateway. Remote drivers are selected by a non-reserved compute driver name and either a CLI/env socket endpoint or [openshell.drivers.<name>].socket_path. The VM driver now enters ComputeRuntime through the same acquired remote endpoint path, while Docker, Podman, and Kubernetes retain their in-process drivers. Require --drivers/OPENSHELL_DRIVERS when pairing an ad-hoc socket endpoint so the socket does not imply a magic driver name, and keep reserved in-tree names unavailable for unmanaged socket endpoints. Co-authored-by: Evan Lezar <elezar@nvidia.com> Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com> Signed-off-by: Evan Lezar <elezar@nvidia.com> * test(server): cover remote compute driver UDS lifecycle Signed-off-by: Evan Lezar <elezar@nvidia.com> --------- Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com> Signed-off-by: Evan Lezar <elezar@nvidia.com> Co-authored-by: Evan Lezar <elezar@nvidia.com> |
||
|
Simon Scatton
|
c7879a0a1d |
test(e2e): stop using custom e2e binary builds (#2000)
Remove the production-crate dev-settings feature so e2e tests build the same gateway, CLI, and supervisor binaries that we ship. Move settings coverage from dummy test-only keys to the production ocsf_json_enabled setting. Signed-off-by: Simon Scatton <sscatton@nvidia.com> |
||
|
Evan Lezar
|
2c545893ed |
feat(cli): add GPU count requests (#1812)
* feat(gpu)!: add resource requirements BREAKING CHANGE: SandboxSpec.gpu and DriverSandboxSpec.gpu were replaced with resource_requirements.gpu, changing protobuf field 9 from a bool to a message for both public and driver APIs. Signed-off-by: Evan Lezar <elezar@nvidia.com> * refactor(gpu): pass requirements through sandbox create Pass the coupled GPU requirement object through the CLI sandbox_create boundary instead of splitting presence and count into separate arguments. Signed-off-by: Evan Lezar <elezar@nvidia.com> * refactor(gpu): pass requirements to timeout message Pass ResourceRequirements into the provisioning timeout message helper so GPU hints are derived from the same nested request object used to create the sandbox. Signed-off-by: Evan Lezar <elezar@nvidia.com> * refactor(gpu): pass driver requirements through helpers Thread Option<GpuResourceRequirements> through driver validation and rendering helpers instead of splitting GPU presence and count into separate arguments. Signed-off-by: Evan Lezar <elezar@nvidia.com> * fix(gpu): validate exact device requests Require exact driver GPU device lists to be tied to a GPU request, allow a single exact device to use the default countless request, and require explicit matching counts for multi-device lists. Signed-off-by: Evan Lezar <elezar@nvidia.com> --------- Signed-off-by: Evan Lezar <elezar@nvidia.com> |
||
|
Taylor Mutch
|
8e831f3a52 | fix(ci): fix linting issues (#1985) | ||
|
st-grandClaude Opus 4.7
|
4ee27d9955 |
feat(sandbox,providers): add aws-bedrock as a recognized inference provider (#1704)
* feat(sandbox): allow AWS Bedrock InvokeModel paths through the L7 router
Adds two patterns to `default_patterns()` so the supervisor's L7
inference router recognizes the Bedrock InvokeModel URL shape and
forwards matched requests to the registered upstream:
- `POST /model/{modelId}/invoke` → aws_bedrock_invoke
- `POST /model/{modelId}/invoke-with-response-stream` → aws_bedrock_invoke_stream
The `{modelId}` segment is wildcarded by extending `detect_inference_pattern`
to handle one middle `/*/` segment in addition to the existing trailing
`/*`. The wildcard is constrained to a single non-empty path segment to
avoid path-traversal liabilities — `/model//invoke` and `/model/a/b/invoke`
both no-match.
Without this, sandboxes running Claude Code in its native Bedrock mode
(`CLAUDE_CODE_USE_BEDROCK=1`, `ANTHROPIC_BEDROCK_BASE_URL`, AWS-style
auth) hit the supervisor with `403 connection not allowed by policy`
because their URL doesn't match `/v1/*` shapes. The fix unblocks
operators wanting to register direct AWS Bedrock, an in-cluster
Bedrock-compatible bridge, or a Bedrock-emulating LiteLLM as
`--type aws-bedrock` providers.
Tests cover: positive matches for invoke + invoke-with-response-stream,
query-string handling, GET rejection, empty-segment rejection,
multi-segment rejection, and unknown-action rejection.
Companion changes (provider discovery spec + YAML profile) follow in
the next commit.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com>
* feat(providers): add aws-bedrock provider profile + discovery spec
Adds `aws-bedrock` to the built-in provider catalog so operators can
run `openshell provider create --type aws-bedrock --credential ...`
and have the gateway treat it as a first-class inference provider
alongside `anthropic`, `openai`, etc.
- `providers/aws-bedrock.yaml`: YAML profile declaring four credentials
(AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN, AWS_REGION).
Default endpoint is `bedrock-runtime.us-east-1.amazonaws.com:443`;
operators in other regions or running against a Bedrock-compatible
proxy override via the operator-supplied `BEDROCK_BASE_URL` config-key
(mirrors `ANTHROPIC_BASE_URL` for the `anthropic` provider).
- `crates/openshell-providers/src/providers/aws_bedrock.rs`: the
`ProviderDiscoverySpec` so `openshell provider create --auto-providers`
picks up AWS_* env vars from local credentials.
- `crates/openshell-providers/src/providers/mod.rs`: register the module.
- `crates/openshell-providers/src/lib.rs`: register the SPEC in the
default registry alongside the other providers.
- `crates/openshell-providers/src/profiles.rs`: include the new YAML in
`BUILT_IN_PROFILE_YAMLS`.
What this PR explicitly does NOT add (intentionally separated for
review-size reasons; will follow up):
- A SigV4 signer in `openshell-router`. The current change simply
declares the protocol; a follow-up PR adds outbound SigV4 signing
using the `aws-sigv4` crate and a new `auth_style: sigv4` validator
branch in profiles.rs. Operators who don't need SigV4 (e.g. an
in-cluster bridge that ignores it and authenticates separately to
the upstream) can use this PR today.
- Body translation between Bedrock InvokeModel shape and other
inference shapes. The router treats Bedrock requests as opaque
pass-through; if the operator's upstream is real AWS Bedrock it
speaks Bedrock natively, if it's a translating bridge the bridge
does any conversion server-side.
- `BEDROCK_BASE_URL` placeholder substitution in the YAML loader.
Today the YAML's `host` is a literal default; operators override
with the config-key the same way `ANTHROPIC_BASE_URL` works.
Tested: `cargo test -p openshell-providers` (35 tests green) and
`cargo test -p openshell-sandbox --lib l7::inference` (40 tests green
including the seven new aws_bedrock cases from the previous commit).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com>
* revert(providers): drop legacy aws-bedrock SPEC, rely on v2 YAML profile
Addresses johntmyers's review on NVIDIA/OpenShell#1704: net-new
providers should land via the v2 YAML profile only and should NOT
require changes to the legacy `ProviderDiscoverySpec` registry.
- Delete `crates/openshell-providers/src/providers/aws_bedrock.rs`
(the legacy SPEC + `test_discovers_env_credential!` invocation).
- Drop `pub mod aws_bedrock;` from `crates/openshell-providers/src/providers/mod.rs`.
- Drop `registry.register(providers::aws_bedrock::SPEC)` from
`crates/openshell-providers/src/lib.rs`.
Kept:
- `providers/aws-bedrock.yaml` and the `include_str!` in
`BUILT_IN_PROFILE_YAMLS` (`profiles.rs`) — the v2 path.
`discover_from_profile()` (`crates/openshell-providers/src/discovery.rs`)
picks up AWS_* env vars via `discovery.credentials` in the YAML.
- L7 router patterns in `crates/openshell-sandbox/src/l7/inference.rs`
— orthogonal to the provider registry.
The discovery test in the deleted file goes with it; v2 doesn't have
an established per-provider env-var-pickup unit test pattern, and
other YAML-only registrations (none today, but this is the new
direction) won't carry one either.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com>
* fix(providers): include aws_session_token in discovery + update profile assertion
Two fixes from johntmyers's gator-agent re-check on NVIDIA/OpenShell#1704:
1. `providers/aws-bedrock.yaml`: add `aws_session_token` to
`discovery.credentials`. The credential is declared in the profile
but was missing from the discovery scan list, so Providers v2
`--from-existing` would silently drop temporary AWS credentials
(STS / IRSA scenarios).
2. `crates/openshell-server/src/grpc/provider.rs`: update the static
`list_provider_profiles_returns_built_in_profile_categories`
assertion to include `aws-bedrock` at alphabetical position 0.
Adding `providers/aws-bedrock.yaml` to BUILT_IN_PROFILE_YAMLS made
the prior `["claude-code", "github", "nvidia"]` expectation stale.
Remaining blockers from the same review (deferred to follow-up
commits): `inference::profile_for` registration for aws-bedrock,
user-facing provider + inference-routing docs, and an
`upsert_cluster_inference_route` integration test.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com>
* feat(inference): register aws-bedrock profile (bridge-fronted) + docs
Addresses johntmyers's blocking review feedback on PR #1704:
"aws-bedrock still is not wired into the managed inference.local route
registry. profile_for only registers openai, anthropic, and nvidia, so
inference set --provider <aws-bedrock-provider> will reject this
provider before the new sandbox L7 patterns can be used."
Approach: register aws-bedrock as a *bridge-fronted* upstream — the
router does not inject any auth header on outbound requests; the
configured BEDROCK_BASE_URL is expected to point at a translating
bridge / Bedrock-compatible proxy that handles auth in its own pod.
This is the shape the L7 patterns commit (8b30211a) and the YAML
profile (6b51e1a6) were designed for. SigV4 signing for direct AWS
Bedrock is a separate follow-up; see PR thread.
Changes:
- core::inference::AuthHeader: add `None` variant for upstreams that
authenticate themselves.
- core::inference: add AWS_BEDROCK_PROFILE static + register in
profile_for. Default base URL is bedrock-runtime.us-east-1, override
via BEDROCK_BASE_URL config-key (mirrors ANTHROPIC_BASE_URL pattern).
Empty credential_key_names + auth: None means no router-side
credential lookup at route time.
- router::backend: handle AuthHeader::None as a no-op (skip auth
injection).
- server::inference::resolve_provider_route: gate find_provider_api_key
on auth != None. aws-bedrock providers with empty credentials now
resolve cleanly. Updated the unsupported-type error message to
include aws-bedrock in the supported list.
- server::inference tests: add positive
upsert_cluster_route_succeeds_for_aws_bedrock_without_api_key test
covering the new code path end-to-end (provider with empty creds +
BEDROCK_BASE_URL config → upsert succeeds → resolved route has
empty api_key + provider_type aws-bedrock + bridge URL).
- core::inference tests: profile_for_known_types covers aws-bedrock,
case-insensitive lookup, plus three new aws-bedrock-specific tests
(auth: None, no credential keys, bedrock-specific protocols).
- docs/sandboxes/inference-routing.mdx: header forwarding row
mentions aws-bedrock has no passthrough headers; new tabs in
Supported API Patterns (InvokeModel + InvokeModelWithResponseStream)
and Create a Provider (with the bridge-fronted shape note + SigV4
deferral).
- docs/sandboxes/manage-providers.mdx: new row in Supported Provider
Types table; new row in Supported Inference Providers table.
Verification (in dev container):
- cargo check -p openshell-core -p openshell-router -p openshell-server: clean
- cargo test -p openshell-core --lib inference: 14/14 pass (incl. 3 new)
- cargo test -p openshell-server --lib inference::tests::upsert: 6/6 pass
(incl. new aws-bedrock test)
- cargo fmt --check: clean
- cargo clippy --all-targets -D warnings: clean
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com>
* fix(aws-bedrock): bridge-only YAML, doc actual cmd shape, neg test
Addresses four findings from gator-agent's #1704 re-check on 4ab587f1:
- **Item 5** (YAML collects unused AWS creds): mark all four AWS
credentials `required: false` and clear `discovery.credentials`.
Bridge-fronted routing intentionally does not consume AWS
credentials, so `--from-existing` no longer scans for them. The
credentials remain in the schema (not deleted) so the SigV4
follow-up can flip them back without a schema migration. Added a
multi-line description that names the bridge-fronted shape and the
SigV4 deferral so readers don't have to cross-reference the PR
thread.
- **Item 3** (docs show command that the CLI rejects): rewrite the
Create-a-Provider example for AWS Bedrock to use the actual
required shape — placeholder `--credential AWS_ACCESS_KEY_ID=
unused-bridge-fronted-shape` plus the `--config BEDROCK_BASE_URL`.
The placeholder satisfies the gRPC handler's
`provider.credentials.is_empty()` rejection without expanding
server-side validation; the router ignores it on the outbound path
because `auth: AuthHeader::None` skips header injection. Operators
see a clearly-labeled placeholder in `provider get` output.
- **Item 1** (validator probe): document `--no-verify` as required
for `openshell inference set --provider <aws-bedrock>` since the
default validation probe doesn't recognize the
`aws_bedrock_invoke` / `aws_bedrock_invoke_stream` protocols. Doc
now shows the full `provider create` + `inference set --no-verify`
flow with rationale for both decisions inline.
- **Item 6** (docs polish): `inference-routing.mdx` summary row now
lists AWS Bedrock alongside NVIDIA, Anthropic, Vertex AI, and
OpenAI-compatible providers, with the bridge-fronted caveat
inline.
Test additions in `crates/openshell-server/src/inference.rs`:
- Renamed the existing aws-bedrock test from
`..._without_api_key` to `..._with_bridge_url` and updated it to
use a placeholder credential (mirroring the doc-recommended
pattern operators will copy-paste). The `auth: None` path still
produces an empty `api_key` on the resolved route — the test now
documents that the credential is *stored* but not *used*.
- Added `upsert_cluster_route_rejects_aws_bedrock_without_bedrock_base_url`:
the negative half of johntmyers' "successfully used by
upsert_cluster_inference_route or intentionally rejected with a
clear documented error" ask. With
`default_base_url: ""` and no `BEDROCK_BASE_URL` config, route
resolution returns `InvalidArgument` naming the missing base_url
rather than silently forwarding prompts to AWS Bedrock with no
usable auth.
Verification (in dev container):
- cargo test -p openshell-core --lib inference: 18/18 (incl. 3 new)
- cargo test -p openshell-server --lib inference::tests::upsert: 8/8
(incl. 2 new aws-bedrock cases — positive + negative)
- cargo fmt --check: clean
- cargo clippy --all-targets -D warnings: clean
Item 2 (router-side enforcement of operator-configured Bedrock model
path, replacing the current verbatim path forwarding + body-only
model rewrite) is the remaining blocker and is genuinely separable —
it touches the L7 router with streaming-aware test coverage.
Deferring to its own commit so the security-critical change gets the
review attention it deserves.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com>
* fix(router): enforce operator-configured Bedrock model in request path
Closes the security-blocking item from gator-agent's #1704 re-check
on 4ab587f1: "Bedrock carries the model id in /model/{modelId}/invoke,
but the router currently forwards the caller's original path and only
rewrites JSON body model. That lets sandbox code choose a different
upstream model than the operator-configured route model, and may also
mutate native Bedrock request bodies incorrectly."
Two changes in `prepare_backend_request`:
1. **Path rewrite for Bedrock routes.** Before computing the upstream
URL, parse the inbound path's `/model/<id>/invoke[-with-response-stream]`
shape and substitute the operator-configured `route.model` for the
caller-supplied model segment. Sandbox code that hardcodes a
different model still works (we don't reject on mismatch), but the
operator's configured model is what reaches the upstream / bridge.
If the inbound path is somehow not a recognized Bedrock shape on a
Bedrock route (the L7 pattern detector upstream of the router
should never produce this combination), reject with
RouterError::Internal naming the offending path rather than
forwarding verbatim.
2. **Skip body-model injection for Bedrock routes.** The existing body
rewriter unconditionally inserts `route.model` into the JSON body
for non-Vertex routes. AWS Bedrock InvokeModel encodes the model
in the URL path; the body is the raw provider-specific payload
(Anthropic Messages for Claude, Mistral payload for Mistral, etc.)
and must not be mutated. The branch ordering is now:
needs_vertex_anthropic_version → strip body model + inject
anthropic_version; route_is_bedrock → leave body alone; else →
inject route.model (existing default).
New helpers, all in `crates/openshell-router/src/backend.rs`:
- `route_is_bedrock(route)` — true when route.protocols contains
aws_bedrock_invoke or aws_bedrock_invoke_stream.
- `parse_bedrock_invocation_path(path)` — returns
Some((model_id, "/invoke" | "/invoke-with-response-stream")) for
paths matching the recognized Bedrock shapes. Strips query strings.
Rejects empty model ids and multi-segment ids (defense-in-depth
matching the L7 pattern detector's existing guards).
- `rewrite_bedrock_path(route, path)` — returns the path with the
caller's model segment replaced by route.model.
Test coverage in the same file (9 new tests):
- parse_bedrock_invocation_path: positive cases for both invoke
variants, query-string stripping; negative cases for empty model id,
multi-segment id, unknown action, wrong prefix, missing slash.
- route_is_bedrock: matches both protocol variants singly and
combined; rejects openai_chat_completions.
- rewrite_bedrock_path: substitutes operator model on both invoke
variants; returns None for non-Bedrock paths.
- bedrock_route_rewrites_model_in_path_and_preserves_body
(wiremock end-to-end): caller sends /model/some-other-model/invoke
with a body containing model: "caller-supplied-model-name". Mock
asserts the upstream receives /model/<operator-model>/invoke and the
body's model field is the caller's value (NOT route.model) — proves
both the path rewrite and the body preservation.
- bedrock_route_streaming_rewrites_model_in_path: same contract for
invoke-with-response-stream.
- bedrock_route_rejects_non_bedrock_path: defense-in-depth coverage of
the Internal-error path when a Bedrock route receives a path that
doesn't match Bedrock shape.
Verification (in dev container):
- cargo test -p openshell-router --lib: 53/53 (incl. 9 new)
- cargo fmt --check: clean
- cargo clippy -p openshell-core -p openshell-router -p openshell-server
--all-targets -- -D warnings: clean
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com>
* fix(sandbox/l7): declare framing for Bedrock patterns
Closes the buffered-vs-streaming framing warning from gator-agent's
re-check on 4ab587f1: "Bedrock InvokeModel should be buffered while
InvokeModelWithResponseStream is streaming. Please add framing/coverage
so /model/{id}/invoke cannot be corrupted by the streaming proxy's
truncation/error-frame behavior."
The InferenceApiPattern struct gained a `framing: ResponseFraming`
field upstream after the original Bedrock-patterns commit (#22b78cff)
landed; the cherry-pick onto current upstream/main left the two
Bedrock entries without the new field. Fixed here:
- aws_bedrock_invoke (POST /model/{id}/invoke):
framing = ResponseFraming::Buffered
InvokeModel returns one JSON object the caller decodes whole. Sending
it through the streaming proxy would risk a mid-body size-cap
truncation or idle-timeout failure appending an SSE error event onto
bytes the caller decodes as one JSON body — the same corruption mode
that drove the existing embeddings + model-discovery to Buffered.
- aws_bedrock_invoke_stream (POST /model/{id}/invoke-with-response-stream):
framing = ResponseFraming::Streaming
InvokeModelWithResponseStream returns an AWS event-stream of binary
chunks; the caller wants chunks incrementally, so the streaming proxy
path is correct.
Two new tests in `crates/openshell-sandbox/src/l7/inference.rs` pin
down the contract:
- aws_bedrock_invoke_is_buffered — detect_inference_pattern returns a
Buffered pattern for /model/<id>/invoke, with explanatory message
naming the corruption mode being prevented.
- aws_bedrock_invoke_stream_is_streaming — same shape, asserting
Streaming for /model/<id>/invoke-with-response-stream.
Verification (in dev container):
- cargo check -p openshell-sandbox: clean (was failing on missing
`framing` field before this commit)
- cargo test -p openshell-sandbox --lib l7::inference::tests::aws_bedrock:
7/7 (incl. 2 new framing tests)
- cargo fmt --check: clean
- cargo clippy --all-targets -- -D warnings: clean
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com>
* fix(inference): drop aws_bedrock_invoke_stream until protocol-aware errors land
Per PR #1704 review (johntmyers): defer Bedrock streaming to a follow-up
that also wires protocol-aware error framing for the AWS event-stream
shape. Until then, surfacing `/model/{id}/invoke-with-response-stream`
risks shipping responses the sandbox cannot interpret on failure.
- AWS_BEDROCK_PROTOCOLS no longer advertises `aws_bedrock_invoke_stream`.
- The L7 inference pattern table drops the streaming entry; only
`aws_bedrock_invoke` (buffered) is recognized.
- Test `aws_bedrock_invoke_stream_pattern_is_deferred` asserts no
pattern claims that protocol so the gap is visible.
Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com>
* fix(inference): validate AWS Bedrock model_id at route + rewrite, preserve query
Per PR #1704 review (johntmyers, gator agent): the operator-configured
Bedrock model_id flows verbatim into the upstream URL path; the previous
plumbing left no enforcement that the value was a single benign path
segment, opening a path-injection vector.
Defense in depth, both layers:
* `openshell-server::inference`: new `validate_aws_bedrock_model_id`
rejects empty, leading/trailing whitespace, `/`, `\\`, `?`, `#`, `%`,
`..`, control/whitespace characters. Wired into `resolve_provider_route`
ahead of base_url resolution so the route store cannot persist a
malformed model_id. Mirrors `validate_vertex_model_id` exactly.
* `openshell-router::backend`: `rewrite_bedrock_path` now refuses to
construct the upstream URL unless `route.model` passes
`is_valid_bedrock_model_id`, so even a stale or hand-edited route
cannot reach the wire. The parser also drops the
`/invoke-with-response-stream` arm to match the protocol catalog.
* `parse_bedrock_invocation_path` returns the `?`-prefixed query tail
as a third element; `rewrite_bedrock_path` re-attaches it so any
caller-supplied query string is preserved through the model rewrite.
Tests: 5 unit tests for the validator, 1 integration test that
exercises every unsafe-model_id reject path through
`upsert_cluster_inference_route`, plus a router-side rewrite-rejects
test covering 11 unsafe `route.model` values. All 72 server inference
tests + router tests pass.
Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com>
* fix(aws-bedrock): make built-in profile non-egress-granting; tighten docs
Per PR #1704 review (johntmyers): a single profile that is "usable as
is" — not a profile that auto-grants direct AWS Bedrock egress to any
sandbox that selects it. The bridge IS the egress point and is
operator-managed; the profile must not implicitly punch a hole through
the cluster's network policy on its behalf.
* `providers/aws-bedrock.yaml`: clear `endpoints` and `binaries` to
empty arrays. Rewrite the description to spell out that the profile
is intentionally non-egress-granting, that operators are responsible
for declaring their bridge's egress endpoint and binary attribution,
and that the SigV4 follow-up will repopulate these fields once
router-side signing exists.
* `docs/sandboxes/inference-routing.mdx`:
- Drop the `InvokeModelWithResponseStream` row from the supported
patterns table (matches the protocol-catalog + L7-pattern drop).
- Update the `--no-verify` paragraph to reference only
`aws_bedrock_invoke`.
- Generalise the placeholder-credential rationale: any
standalone-router profile registering `AuthHeader::None` will hit
the same non-empty-credentials structural requirement.
Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com>
* style(router): satisfy cargo fmt for Bedrock query-tail extraction
CI's rustfmt rejected the one-line `let (path_only, query_tail) = path.find('?').map_or(...)`
shape from commit c51160e4 and required the chained-method layout
instead. Functional behaviour is unchanged; tests still pass.
Signed-off-by: st-gr <38470677+st-gr@users.noreply.github.com>
* style(router): drop unnecessary `crate::` prefix on RouterError matcher
`RouterError` is already imported at the top of the file, so the
two test-side `matches!(result, Err(crate::RouterError::UpstreamProtocol(_)))`
uses trip clippy's `unused_qualifications` under `-D warnings`. Drop
the prefix on both sites; functional behaviour is unchanged.
These warnings predate this PR (originated in
|
||
|
Robert Sturla
|
48545cfb59 |
feat(sandbox): add GCE metadata emulator for Google Cloud (#1763)
* feat(core): add shared GCP constants module Single source of truth for GCP naming: env var aliases, provider config keys, token search order, and Vertex-specific env vars. Consumed by openshell-server, openshell-providers, and openshell-sandbox. - Add google_cloud.rs with metadata emulator host and loopback address - Define PROJECT_ID, REGION, and SERVICE_ACCOUNT_EMAIL env var aliases - Add provider config key constants for gcp provider implementations - Define TOKEN_ENV_KEYS search order (SA token takes priority over ADC) - Add Vertex-specific env vars for Goose and Claude Code SDK integration - Add STATIC_CONFIG_KEYS as union of all alias arrays for env resolution - Export module via openshell-core lib.rs Signed-off-by: Robert Sturla <rsturla@redhat.com> * feat(providers): add google-cloud and vertex provider plugins Add GoogleCloudProvider and VertexProvider implementing inject_env to project GCP config (project ID, region, SA email, metadata host) into sandbox environment variables. Replace the inline Vertex AI env injection in the server with the registry-based inject_env dispatch. Also adds the google-cloud.yaml provider profile with SA JWT and ADC OAuth2 credential refresh flows. Signed-off-by: Robert Sturla <rsturla@redhat.com> * feat(sandbox): add GCE metadata emulator for GCP Add a loopback HTTP server on 127.0.0.1:8174 inside the sandbox network namespace that emulates the GCE instance metadata API. GCP client SDKs discover it via GCE_METADATA_HOST and obtain credential placeholders that the proxy resolves to real tokens at egress. Add metadata_server module with MetadataHandler trait and netns-aware TCP binding via std::thread (not spawn_blocking) to avoid tokio pool namespace contamination Add google_cloud_metadata module implementing the GCE metadata API subset (token, project-id, email, scopes, service-accounts) Add child_env_resolved() and gcp_token_response() to ProviderCredentialState for GCP-aware credential projection Wire metadata server into sandbox lifecycle before SSH handler Collapse multi-line HTTP response format string into single line Signed-off-by: Robert Sturla <rsturla@redhat.com> * docs(sandbox): add GCP credentials documentation Document the google-cloud provider setup for ADC and service account flows, injected environment variables, metadata emulator behavior, and network policy configuration for GCP APIs. Signed-off-by: Robert Sturla <rsturla@redhat.com> * feat(cli): support --from-gcloud-adc for google-cloud providers Widen --from-gcloud-adc to accept google-cloud providers. The ADC credential key is derived from the provider profile rather than hardcoded per type, so future GCP provider types get ADC support by declaring the right refresh metadata in their profile YAML. Add ProviderTypeProfile::adc_credential() to find the ADC-compatible credential from a profile's refresh metadata. Remove unused VERTEX_AI_ADC_TOKEN_KEY and GCP_ADC_TOKEN_KEY constants. Signed-off-by: Robert Sturla <rsturla@redhat.com> --------- Signed-off-by: Robert Sturla <rsturla@redhat.com> |
||
|
John T. Myers
|
48a7d09e82 |
feat(providers): support profile updates (#1914)
* feat(providers): support profile updates Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> * fix(providers): require CAS for profile updates Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> * fix(providers): serialize profile update validation Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> * fix(providers): serialize profile import invariants Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> * fix(providers): require profile update target id Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> --------- Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> |
||
|
Evan Lezar
|
4c75b8542b |
fix(server): share gateway shutdown channel (#1945)
Signed-off-by: Evan Lezar <elezar@nvidia.com> |
||
|
mmilutinovic371
|
36bb9e3ec2 |
feat(providers): add DeepInfra as a built-in inference provider (#1902)
* feat(providers): add DeepInfra as a built-in inference provider (v2 only) - Adds `deepinfra` as a built-in Providers v2 profile (`providers/deepinfra.yaml`) with inference category, Bearer auth, and `DEEPINFRA_API_KEY` discovery - Adds `DEEPINFRA_PROFILE` to inference routing so `inference.local` works with the `deepinfra` provider type - Fixes `build_backend_url` to strip `/v1` from request paths when the base URL contains `/v1/` as an internal segment (e.g. `api.deepinfra.com/v1/openai`), preventing double-versioned paths like `.../v1/openai/v1/chat/completions` - Updates `docs/sandboxes/providers-v2.mdx` and `docs/sandboxes/manage-providers.mdx` with DeepInfra entries; removes the old v1 workaround row that used `openai` type with `OPENAI_API_KEY` Signed-off-by: Milos Milutinovic <codemastermilos@gmail.com> * fix(providers): address gator review findings for DeepInfra provider - Narrow build_backend_url /v1 dedupe to URLs whose path component is exactly /v1 or starts with /v1/ — prevents regression on proxy endpoints where /v1 is buried deeper (e.g. /api/v1/openai); add regression test for the nested proxy path case - Add deepinfra provider plugin with DEEPINFRA_API_KEY discovery, registered in ProviderRegistry so known_types() and TUI include it - Add deepinfra to unsupported-inference-provider error message in openshell-server for accurate user-facing debugging guidance - Add deepinfra to openai_compatible_profiles_include_embeddings test to lock in the OpenAI-compatible protocol contract Signed-off-by: Milos Milutinovic <codemastermilos@gmail.com> * fix(router): handle /v1 as final path segment in build_backend_url dedup Extends the /v1 deduplication logic to also strip /v1 from request paths when the base URL's path ends with /v1 (e.g. https://api.groq.com/openai/v1). The previous fix only matched paths starting with /v1/, which regressed providers like Groq whose base path has /v1 as the last segment rather than the first. The nested-proxy exclusion (e.g. /api/v1/openai) is preserved since /v1 appears in the middle — neither first nor last segment. Adds a regression test for the Groq-style base URL. Signed-off-by: Milos Milutinovic <codemastermilos@gmail.com> * fix(providers): add deepinfra telemetry bucket and update profile list test - Add DeepInfra variant to ProviderProfile telemetry enum and from_raw() mapping so deepinfra providers are tracked in their own bucket rather than falling through to Custom - Map deepinfra in telemetry_provider_profile() in openshell-server - Add deepinfra to list_provider_profiles_returns_built_in_profile_categories test (sorted between cursor and github) - Update architecture/gateway.md inference provider list to include deepinfra Signed-off-by: Milos Milutinovic <codemastermilos@gmail.com> * style(router): apply cargo fmt to backend.rs Signed-off-by: Milos Milutinovic <codemastermilos@gmail.com> --------- Signed-off-by: Milos Milutinovic <codemastermilos@gmail.com> |
||
|
Yuedong Wu
|
ff028ce0df |
feat(server): support TLS certificate hot-reload (#1870)
* feat(server): support TLS certificate hot-reload Signed-off-by: Yuedong Wu <dwcn22@outlook.com> * refactor(server): extract shared TLS test utilities Signed-off-by: Yuedong Wu <dwcn22@outlook.com> --------- Signed-off-by: Yuedong Wu <dwcn22@outlook.com> |
||
|
Taylor Mutch
|
fd6cbf6b6c |
fix(server): retry sandbox delete phase conflicts (#1905)
Signed-off-by: Taylor Mutch <taylormutch@gmail.com> |
||
|
Derek Carr
|
e73745f10e |
feat(gateway): add reconciler lease for HA multi-replica deployments (#1577)
Introduce a database-backed lease that ensures only one gateway replica runs the watch and reconcile loops. Includes lease primitives with CAS safety, cooperative cancellation via watch channels, SQLite bypass for single-replica deployments, and integration tests covering failover, contention, and CAS chain integrity. Signed-off-by: Derek Carr <decarr@redhat.com> |
||
|
alangou
|
f33fd02f4d |
fix(server): use public tonic body type in gRPC rate limiter (#1872)
Signed-off-by: Adrien Langou <alangou@nvidia.com> |
||
|
alangou
|
b6c87a76ab |
feat(server): add grpc rate limiting gateway-wide (#1566)
Signed-off-by: Adrien Langou <alangou@nvidia.com> |
||
|
Evan Lezar
|
1dc59853ff |
feat(gpu): move device selection to driver config (#1815)
* refactor(kubernetes): use shared proto struct helpers Signed-off-by: Evan Lezar <elezar@nvidia.com> * refactor(docker): extract sandbox template validation * feat(gpu)!: move device selection to driver config BREAKING CHANGE: The openshell sandbox create --gpu-device flag and corresponding API field were removed. Select specific GPUs through driver-specific driver_config fields instead. Signed-off-by: Evan Lezar <elezar@nvidia.com> * fix(kubernetes): reject unknown driver config fields Signed-off-by: Evan Lezar <elezar@nvidia.com> --------- Signed-off-by: Evan Lezar <elezar@nvidia.com> |
||
|
Drew Newberry
|
530aaf1360 |
feat(drivers): support docker and podman config mounts (#1785)
* feat(drivers): support docker and podman config mounts Signed-off-by: Drew Newberry <anewberry@nvidia.com> * docs(drivers): trim mount docs Signed-off-by: Drew Newberry <anewberry@nvidia.com> * test(e2e): cover local driver volume mounts Signed-off-by: Drew Newberry <anewberry@nvidia.com> * fix(podman): satisfy linux clippy lint Signed-off-by: Drew Newberry <anewberry@nvidia.com> * feat(drivers): gate bind mounts behind gateway config * docs(sandbox): simplify mount examples * cleanup * test(e2e): stabilize branch checks * fix(drivers): tighten local mount validation Signed-off-by: Drew Newberry <anewberry@nvidia.com> --------- Signed-off-by: Drew Newberry <anewberry@nvidia.com> |
||
|
Taylor Mutch
|
702cbc4f63 |
feat(providers): support SPIFFE-backed token grants (#1784)
* feat(providers): support SPIFFE-backed token grants Add provider profile token_grant metadata and expand endpoint-specific dynamic credentials so sandbox supervisors can request SPIFFE JWT-SVIDs, exchange them with an OAuth-style token endpoint, cache returned access tokens, and inject bearer tokens into matching HTTP requests. Wire Kubernetes and Helm deployments to mount the provider SPIFFE Workload API socket into sandbox pods for token grant exchange. Signed-off-by: Taylor Mutch <taylormutch@gmail.com> Signed-off-by: Gordon Sim <gsim@redhat.com> * test(examples): add SPIFFE token grant demo Add a reusable alpha/beta demo that deploys a SPIFFE-verifying token issuer and protected services, imports a token-grant provider profile, creates a sandbox, and verifies endpoint-specific bearer tokens. The script leaves Kubernetes workloads in place, deletes sandboxes through openshell unless KEEP_SANDBOX=1, and prints protected service logs as proof of life. Signed-off-by: Taylor Mutch <taylormutch@gmail.com> * fix(providers): harden SPIFFE token grants * fix(providers): harden dynamic token grants Signed-off-by: Taylor Mutch <taylormutch@gmail.com> * fix(providers): harden token grant handling --------- Signed-off-by: Taylor Mutch <taylormutch@gmail.com> Signed-off-by: Gordon Sim <gsim@redhat.com> |
||
|
LateNightHackathonandlatenighthackathon
|
c1d3b43ddb |
fix(policy): classify advisory private-IP notes with the canonical is_internal_ip (#1777) (#1824)
generate_security_notes() flagged a destination as internal/private using naive
string prefixes. host.starts_with("172.") matched all of 172.0.0.0/8 even
though only 172.16.0.0/12 is private (RFC 1918), so the advisory flagged public
addresses (172.15/172.32) and missed CGNAT (100.64.0.0/10), IPv6 ULA, and the
other reserved ranges; it also flagged non-IP hostnames that merely start with
10./172.. The two copies of the check (openshell-sandbox mechanistic_mapper.rs
and openshell-server grpc/policy.rs) now parse the host as an IP and defer to
openshell-core net::is_internal_ip, the same RFC-accurate, unit-tested classifier
the runtime SSRF enforcement path uses, so the proposed-rule advisory matches
actual enforcement.
Per review, is_internal_v4 now uses the stable Ipv4Addr predicates as far as
they go: is_documentation() (RFC 5737) replaces the two manual TEST-NET-2/3
checks and also closes a gap, since 192.0.2.0/24 (TEST-NET-1) was previously
unflagged, and is_broadcast() (RFC 919) is added. Manual checks remain only for
the ranges without a stable predicate: CGNAT 100.64.0.0/10, IETF protocol
assignments 192.0.0.0/24, and benchmarking 198.18.0.0/15.
Adds regression coverage: both note suites now assert hostname-prefix false
positives (10.example.com, 172.example.com) are not flagged and IPv6 ULA
(fd00::1) is flagged; net.rs covers the newly classified TEST-NET-1 and
broadcast addresses.
Closes #1777
Signed-off-by: latenighthackathon <latenighthackathon@users.noreply.github.com>
Co-authored-by: latenighthackathon <latenighthackathon@users.noreply.github.com>
|
||
|
Russell Bryant
|
7274a6bea3 |
feat(cli): add --env flag to sandbox create/exec and fix env var passthrough (#1730)
* feat(cli): add --env flag to sandbox create and exec
Add `--env KEY=VALUE` (repeatable) to `openshell sandbox create` and
`openshell sandbox exec`, wiring user-specified environment variables
into the existing `SandboxSpec.environment` and
`ExecSandboxRequest.environment` protobuf fields which were previously
only accessible via the SDK/gRPC API.
Fix a bug where user-specified environment variables set via
`SandboxSpec.environment` were silently dropped inside sandbox SSH
sessions. The SSH handler's `apply_child_env()` calls `env_clear()` to
strip supervisor-internal secrets before spawning user shells, but this
also wiped container-level env vars including user-specified ones. This
was introduced in
|
||
|
Eric Curtin
|
1399f371e0 |
refactor: deduplicate OCSF builder setters and persistence helpers (#1800)
Eliminate three categories of repeated code:
1. OCSF builder setter methods
Add six macros to builders/mod.rs (impl_activity_setter!,
impl_action_disposition_setters!, impl_actor_process_setter!,
impl_dst_endpoint_setter!, impl_src_endpoint_addr_setter!,
impl_firewall_rule_setter!) that generate the identical one-liner
setters duplicated across network, http, ssh, process, finding,
and lifecycle builders. Removes ~55 hand-written method bodies.
2. Persistence protobuf decode-and-hydrate block
Extract a private decode_record<T>() helper that decodes an
ObjectRecord into a protobuf message and hydrates resource_version.
The identical three-line block was repeated in get_message,
get_message_by_name, list_messages, and list_messages_with_selector.
Each method now delegates to decode_record via .map().transpose()
or .into_iter().map().collect().
3. Store enum dispatch arms
Add a store_dispatch! macro that expands
match self { Postgres(s) => s.method(...).await, Sqlite(s) => ... }.
Applied to all 13 dispatch-only methods on Store, removing ~80
lines of mechanical match arms with zero logic.
|
||
|
Shiju
|
25abc9e3c7 |
feat(inference): allow local embeddings route (#1774)
* feat(inference): allow local embeddings route Route OpenAI-compatible embeddings through the local inference proxy so sandboxed vector workloads reach a configured provider via the same route classification and auth path that chat, completion, and model discovery already use. - Add openai_embeddings to the OpenAI-compatible protocol set so providers (openai, nvidia) advertise embeddings routing. - Classify POST /v1/embeddings as the openai_embeddings protocol in the sandbox L7 patterns. - Serve embeddings buffered with an accurate Content-Length, since the response is a single JSON object rather than an SSE token stream. The streaming path appends an SSE error frame on a size-cap or idle-timeout truncation, which would corrupt a one-object body the client parses whole. protocol_returns_buffered_body() selects the path. - Probe an embeddings-only backend against /v1/embeddings during validation, after the chat and completion protocols so a multi-protocol route still prefers those. - Extract two shared helpers. http_status_text() backs both response formatters and adds 401/422/429/503 for embeddings passthrough and router error mapping; write_inference_router_error() backs the streaming and buffered routing paths. - Return an OpenAI-shaped embeddings body from the mock route. Tests cover profile lookup, L7 pattern detection, the mock body, and buffered Content-Length framing with no chunked transfer-encoding and no SSE error frame. Signed-off-by: Shiju <shiju@nvidia.com> * fix(inference): cap buffered inference response body The buffered proxy path read the whole upstream response into memory with no size bound. The route timeout bounds elapsed time but not memory, so a misbehaving or oversized upstream could force unbounded allocation in the sandbox proxy. The streaming path already caps each response at 32 MiB; the buffered path did not. Cap the buffered read at the same 32 MiB. An advertised over-cap body is rejected from its Content-Length before any bytes are read, and chunks accumulate under the same bound so a chunked or mislabeled body cannot slip past. An over-cap response fails as an upstream protocol error, surfaced as HTTP 502 at the proxy boundary, and is never partially returned. Tests - cargo test -p openshell-router \ proxy_to_backend_rejects_over_cap_response_body Signed-off-by: Shiju <shiju@nvidia.com> * fix(inference): validate embeddings models against all advertised protocols A managed route resolves to its provider profile's full protocol set, so an embeddings model such as text-embedding-3-small lists openai_chat_completions alongside openai_embeddings. Route verification probed only the first writable protocol and stopped on its failure. It sent a chat probe with the embedding model, the provider rejected it as wrong-shape, and the route failed validation before the embeddings probe ran. Embeddings-only configs could not be verified. Try the advertised protocols in preference order. A request-shape rejection (HTTP 400, 404, 405, 422) falls through to the next protocol, so an embeddings model validates against /v1/embeddings even when the chat probe rejects it. Credential, rate-limit, connectivity, and upstream-health failures stay terminal and stop validation at the first probe, so a bad key or a down backend is reported as itself rather than masked by a later probe. validation_probe becomes validation_probes, which returns the ordered list, and the per-probe fallback retry (max_completion_tokens versus max_tokens) moves into a shared helper. Tests - cargo test -p openshell-router \ verify_embeddings_model_falls_through_chat_probe - cargo test -p openshell-router verify_stops_on_credentials_failure Signed-off-by: Shiju <shiju@nvidia.com> * fix(inference): serve model discovery responses buffered GET /v1/models returns a single JSON model list, the same response shape as embeddings. The sandbox inference proxy was routing it through the SSE streaming path. A streaming size-cap or idle-timeout truncation appends an SSE error frame to the body, which corrupts a payload the client parses as one JSON object. Make response framing a property of the protocol. A new ResponseFraming field on InferenceApiPattern is set once per pattern in default_patterns. model_discovery and openai_embeddings are now Buffered, while chat completions, completions, responses, and Anthropic messages stay Streaming. The proxy dispatch gates on pattern.is_buffered(), which replaces the stringly-typed protocol_returns_buffered_body predicate so the streaming-versus-buffered decision lives in one place and cannot drift across the sites that read it. Model discovery now flows through the same buffered path as embeddings, framed with an accurate Content-Length and bounded by the buffered-read size cap that path already enforces. Tests - cargo test -p openshell-sandbox protocol_framing_classification - cargo test -p openshell-sandbox \ inference_model_discovery_served_buffered_with_content_length Signed-off-by: Shiju <shiju@nvidia.com> * docs(inference): document embeddings route in supported patterns Signed-off-by: Shiju <shiju@nvidia.com> --------- Signed-off-by: Shiju <shiju@nvidia.com> |
||
|
Calum Murray
|
b392b2eefe |
feat(providersv2): add path auth_style (#1622)
Signed-off-by: Calum Murray <cmurray@redhat.com> |
||
|
Evan Lezar
|
c3964a6513 |
feat(kubernetes): support driver config passthrough (#1744)
* test(docker): default sandbox template fixtures Signed-off-by: Evan Lezar <elezar@nvidia.com> * feat(cli): add driver config json plumbing Signed-off-by: Evan Lezar <elezar@nvidia.com> * feat(kubernetes): tolerate invalid driver config Signed-off-by: Evan Lezar <elezar@nvidia.com> * feat(kubernetes): prototype driver config specifics Signed-off-by: Evan Lezar <elezar@nvidia.com> * docs(kubernetes): note driver-local config schema boundary Signed-off-by: Evan Lezar <elezar@nvidia.com> * feat(kubernetes): support runtime class driver config Signed-off-by: Evan Lezar <elezar@nvidia.com> --------- Signed-off-by: Evan Lezar <elezar@nvidia.com> |
||
|
Shiju
|
97986d9059 |
fix(server): resume unspecified sandbox phase (#1765)
Legacy or never-initialized sandbox rows decode to the proto-default Unspecified phase. The startup resume sweep skipped them, leaving the backend unreconciled: never resumed, never errored. Unspecified was the only non-terminal phase skipped, since unrecognized values already fall through to Unknown and get resumed. Treat Unspecified as running so the sweep reconciles it from live driver state: resume when the backend resource exists, mark Error when it is gone. Tests - cargo test -p openshell-server \ resume_persisted_sandboxes_resumes_running_phases Signed-off-by: Shiju <shiju@nvidia.com> |
||
|
LateNightHackathonandlatenighthackathon
|
c26d4e8e1f |
fix(grpc): allow credential rotation when legacy provider.type exceeds current limit (#1350)
Closes #1347. Reported by @KodeDaemon in the NVIDIA Developer Discord after upgrading NemoClaw 0.0.38 -> 0.0.39 left the inference provider stranded with `provider.type exceeds maximum length (79 > 64)` on every credential update. `update_provider_record` rebuilt the merged Provider from `existing.r#type` and ran `validate_provider_fields` over it. The CLI's `provider update` sends `r#type: ""`, so the existing value is preserved without modification, but the validator still measured it. Any record whose stored type predates current MAX_PROVIDER_TYPE_LEN (or was written by a path that bypassed validation, e.g. the TUI form which forwards r#type to the request without going through normalize_provider_type) became unupdateable: the only escape was `provider delete` + recreate, which loses any provider.config entries the caller never sees. Split the validator into create-time (validate_provider_fields, full check including immutable name/type) and update-time (validate_provider_mutable_fields, checks only credentials/config maps). The update path validates only what the caller is mutating; immutable fields carried forward from existing are trusted because they passed validation when stored. Tests: new regression in `update_provider_allows_credential_rotation_on_legacy_oversized_type` inserts a Provider with a 79-char type directly via `store.put_message` (bypassing gRPC validation), updates a credential, asserts the update succeeds and the original type is preserved. Existing `update_provider_validates_merged_result` still covers the case where incoming credential entries push the merged map past limits. Signed-off-by: latenighthackathon <latenighthackathon@users.noreply.github.com> Co-authored-by: latenighthackathon <latenighthackathon@users.noreply.github.com> |
||
|
Eric Curtin
|
69764d8a91 | refactor: deduplicate shared driver and TUI helpers (#1741) | ||
|
Taylor Mutch
|
5f58cb018f |
fix(helm): create sandbox JWT secret when cert-manager is enabled (#1700)
* fix(helm): create sandbox JWT secret under cert-manager The cert-manager install path (certManager.enabled=true, pkiInitJob.enabled=false) left the gateway StatefulSet unable to start because nothing created the openshell-jwt-keys Secret: cert-manager owns TLS Secrets but does not mint the sandbox JWT signing key, and the certgen hook only rendered when pkiInitJob.enabled was true. Separate JWT signing-key provisioning from TLS PKI provisioning: - certgen: add a --jwt-only mode that creates only the Opaque JWT signing Secret, for use when another controller owns TLS Secrets. - certgen.yaml: render the hook when pkiInitJob.enabled OR certManager.enabled is true. cert-manager takes precedence and runs the hook with --jwt-only even if pkiInitJob.enabled remains true. Remove the mutual-exclusion failure between the two values. - _helpers.tpl: add openshell.sandboxJwtSecretName, shared by the hook and the StatefulSet mount. - Update values, README, docs, architecture, and the debug-openshell-cluster skill to reflect the new precedence; the documented cert-manager install no longer needs pkiInitJob.enabled=false. Closes #1691 * fix(helm): honor cert-manager precedence for client CA volume The client CA volume logic treated pkiInitJob.enabled as proof that built-in PKI owns the client CA. With cert-manager precedence now allowing certManager.enabled=true alongside the default pkiInitJob.enabled=true, that assumption mounts the server TLS cert secret as the client CA and ignores certManager.clientCaFromServerTlsSecret=false, which can break mTLS or trust the wrong CA. Gate the pkiInitJob.enabled term with (not certManager.enabled) in all three client CA conditions (volume mount, volume definition, and secret selection) so cert-manager owns TLS when enabled. Add a Helm test suite covering built-in PKI, cert-manager shared CA, the regression config (cert-manager + clientCaFromServerTlsSecret=false + default pkiInitJob), and the no-client-CA case. |
||
|
Taylor Mutch
|
e4bcfdfaaa | fix(gateway): allow local sandbox jwt to not expire (#1721) | ||
|
Eric Curtin
|
d5b79e5ba1 |
refactor(server): deduplicate test helpers and grpc utilities (#1708)
Remove three groups of copy-pasted code in openshell-server: 1. grpc/mod.rs had a private current_time_ms() wrapper identical to the one already exported from persistence/mod.rs. Remove the duplicate and update the three grpc sub-modules (policy, sandbox, service) to import directly from crate::persistence. 2. test_store() was repeated verbatim in seven #[cfg(test)] blocks. Promote a single canonical version to persistence/mod.rs (cfg-gated) and replace all copies with crate::persistence::test_store() calls or a thin Arc wrapper in supervisor_session. 3. grpc_client_mtls() and build_tls_root() were copy-pasted across edge_tunnel_auth.rs and multiplex_tls_integration.rs. Move both into the existing tests/common/mod.rs shared module and import from there. |
||
|
John T. Myers
|
62c421b21e |
feat(providers): add profile-backed policy visibility (#1640)
* chore: wip providers v2 tui and codex profile * chore: wip effective policy get and codex profile * chore: wip provider profiles and tui detail views * feat(tui): annotate policy proposal review status |
||
|
Adam Miller
|
f061b1d923 |
feat(providers): add Google Vertex AI inference provider (#1568)
* feat(providers): add Google Vertex AI provider Adds Vertex AI provider profiles, routing, credential refresh plumbing, CLI support, docs, and regression coverage. Keeps the related NETLINK_ROUTE seccomp allowance needed by Vertex client tooling that calls getifaddrs. * docs: add Vertex AI sandbox usage for Claude Code and OpenCode Cover the full end-to-end setup for running Claude Code and OpenCode inside an OpenShell sandbox via inference.local with a Vertex AI backend: - google-vertex-ai.mdx: add 'Use from a Sandbox' section with tabbed examples for Claude Code (--bare flag, no /v1 suffix) and OpenCode (/v1 suffix required). Add providers_v2_enabled prerequisite and --no-verify note for global region. Document policy proposals table covering metadata.google.internal (always blocked), downloads.claude.ai, and storage.googleapis.com. - inference-routing.mdx: expand 'Use the Local Endpoint' section with tabbed examples for Claude Code, OpenCode, Python OpenAI SDK, and Python Anthropic SDK. Add notes explaining the /v1 path suffix difference between clients. - supported-agents.mdx: update Claude Code and OpenCode rows to mention inference.local support and correct base URL requirements. * fix: address vertex review findings * test(sandbox): retry on spurious Ok in fork-exec ambiguity test On arm64 under heavy CI load, the /proc fd scan in find_socket_inode_owners can transiently miss the parent process's socket fd entry, returning only the child as an owner. This causes resolve_process_identity to return Ok (single owner, no ambiguity check fires) instead of the expected ambiguous-ownership Err. Extend the retry loop to also handle unexpected Ok results, mirroring the existing retry for transient Err results. 10 retries at 50ms gives a 500ms settling window, which is sufficient for procfs to stabilize on loaded arm64 runners. * fix: address vertex review regressions * docs(router): clarify stream_response semantics for Vertex rawPredict routing Document the three call sites of prepare_backend_request and their stream_response values in a caller table: - send_backend_request: false → :rawPredict (unary endpoint) - send_backend_request_streaming: true → :streamRawPredict - verify_backend_endpoint: explicitly false to probe the unary endpoint Cross-reference the table from build_provider_url and is_vertex_anthropic_rawpredict_route so the stream_response=true guard in the suffix upgrade branch is understood in full context. Also note that is_vertex_anthropic_rawpredict_route is a structural predicate (model_in_path + anthropic_messages + :rawPredict suffix), not a named-provider check, so any future provider with the same route shape inherits the transforms automatically. |
||
|
Evan Lezar
|
79aa355dd0 |
refactor(driver): trim compute capability response (#1402)
Signed-off-by: Evan Lezar <elezar@nvidia.com> |
||
|
Piotr Mlocek
|
3d441e73ac |
fix(config): reject unknown fields in nested gateway config tables (#1666)
* fix(config): reject unknown fields in nested gateway config tables The gateway TOML loader silently ignored keys placed under the wrong table header. PR #1661 fixed one instance of this (supervisor_image under [openshell.gateway.gateway_jwt]) but the root cause remained: the nested gateway config tables did not deny unknown fields, so a misplaced key was accepted and dropped instead of erroring. Concretely, tasks/scripts/gateway.sh emitted `sandbox_namespace` right after the [openshell.gateway.gateway_jwt] heredoc, so it landed inside the gateway_jwt table rather than [openshell.gateway]. The k8s driver already receives the namespace via [openshell.drivers.kubernetes], so the stray line was dead config that parsed without complaint. Changes: - Add #[serde(deny_unknown_fields)] to the nested gateway config tables that are part of the config-file parse tree: TlsConfig, OidcConfig, MtlsAuthConfig, GatewayAuthConfig, GatewayJwtConfig. - Remove the misplaced sandbox_namespace line from gateway.sh. - Drop the unused Serialize/Deserialize derives from Config and ServiceRoutingConfig (see below). - Add a regression test asserting a key under the wrong nested table is rejected. |
||
|
Kirit ThadakaandJohn Myers
|
c63ac76d06 |
feat(telemetry): add anonymous opt-out OpenShell usage telemetry (#1433)
* feat(telemetry): add anonymous opt-out usage telemetry Signed-off-by: Kirit93 <kthadaka@nvidia.com> * Removed enums from schema Signed-off-by: Kirit Thadaka <kthadaka@nvidia.com> * Updated telemetry URL Signed-off-by: Kirit93 <kthadaka@nvidia.com> * ci(kubernetes): pin mise installer for e2e --------- Signed-off-by: Kirit93 <kthadaka@nvidia.com> Signed-off-by: Kirit Thadaka <kthadaka@nvidia.com> Co-authored-by: John Myers <9696606+johntmyers@users.noreply.github.com> |
||
|
Alexander Watson
|
e98ea3ee93 | feat(policy): add agentic approval loop (#1528) | ||
|
Taylor Mutch
|
0f73d117a5 |
fix(podman): avoid host-gateway on macOS machines (#1637)
Closes #1307 Default the Podman host gateway alias override to gvproxy's host-loopback IP on macOS while preserving host-gateway resolution on Linux. Wire the setting through Podman config, gateway TOML inheritance, and the standalone driver, and document the platform behavior. Signed-off-by: Taylor Mutch <taylormutch@gmail.com> |
||
|
Derek Carr
|
d01d10650b |
refactor(proto): move phase and current_policy_version into status (#1565)
* refactor(proto): move phase and current_policy_version into SandboxStatus Move phase and current_policy_version from SandboxSpec into SandboxStatus to correctly model mutable runtime state. Update all callers in the gateway server, TUI, and Python SDK to read and write these fields through SandboxStatus accessors. Signed-off-by: Derek Carr <decarr@redhat.com> * fix(server): preserve sandbox status on statusless driver updates When a driver update arrives without a status payload (e.g. before Kubernetes populates the status subresource), preserve the stored phase, conditions, and current policy version instead of resetting them. Adds a regression test covering the edge case. Signed-off-by: Derek Carr <decarr@redhat.com> --------- Signed-off-by: Derek Carr <decarr@redhat.com> |
||
|
Mrunal Patel
|
3f520dd4e2 |
feat(server): declare gRPC auth (mode + scope + role) at the handler, enforce at the router (#1596)
* feat(server): per-handler gRPC auth annotations Move scope, role, and auth-mode metadata to the handler definition site via #[rpc_authz] + #[rpc_auth] proc macros. The previously hand-maintained SCOPED_METHODS, ADMIN_METHODS, UNAUTHENTICATED_METHODS, and ALLOWED_SANDBOX_METHODS tables are now generated from per-method annotations on the tonic service impls, with canonical gRPC paths derived from the service name and method name. Adds a new openshell-server-macros proc-macro crate, an aggregator in auth/method_authz.rs, and an exhaustiveness test that decodes the protobuf FileDescriptorSet (now emitted by openshell-core/build.rs) and verifies every RPC has an annotation. Signed-off-by: Mrunal Patel <mrunalp@gmail.com> * refactor(server): rename `sandbox-secret` auth mode to `sandbox` PR #1404 replaced the shared sandbox secret with per-sandbox gateway-minted JWTs. A handler marked `sandbox` now authenticates as a specific `Principal::Sandbox`, not as a holder of a shared credential. Rename `auth = "sandbox-secret"` to `auth = "sandbox"` and `AuthMode::SandboxSecret` to `AuthMode::Sandbox` so the name matches the post-#1404 identity model. Signed-off-by: Mrunal Patel <mrunalp@gmail.com> * fix(server): enforce per-handler AuthMode at the router Addresses review feedback on the per-handler auth-annotation work. - Router-level enforcement of #[rpc_auth] auth mode (HIGH). The previous router only checked is_sandbox_callable() for Principal::Sandbox; user principals still flowed into AuthzPolicy::check() and bypassed the per-handler declaration. A user with `openshell:all` could therefore reach `sandbox`-only handlers like GetSandboxProviderEnvironment, ReportPolicyStatus, PushSandboxLogs, and SubmitPolicyAnalysis even though their annotations said sandbox-only. Adds an is_user_callable() predicate and rejects User principals at the router for `sandbox` / `unauthenticated` methods. - Proc macro now errors on duplicate keys in #[rpc_auth(...)] (LOW). A second `auth`, `scope`, or `role` previously silently overwrote the first value; now it fails to compile. - Regression tests: a unit test for is_user_callable() and a router test that proves a user with admin role + openshell:all cannot reach the nine sandbox-only handlers. Signed-off-by: Mrunal Patel <mrunalp@gmail.com> * docs(server): finish renaming sandbox-secret to sandbox in method_authz doc comments Signed-off-by: Mrunal Patel <mrunalp@gmail.com> * refactor(server-macros): drop standalone `rpc_auth` stub The stub was a safety net that fired only when a method had `#[rpc_auth(...)]` without an enclosing `#[rpc_authz]`. Triggering it required `rpc_auth` to be imported, which is why both call sites carried `#[allow(unused_imports)] use openshell_server_macros::{rpc_auth, rpc_authz};`. Drop the stub and the unused-import workaround. A missing `#[rpc_authz]` now surfaces as rustc's standard "cannot find attribute `rpc_auth` in this scope" — clear enough, and one fewer import + lint exception. Addresses review comment on PR #1596. Signed-off-by: Mrunal Patel <mrunalp@gmail.com> * refactor(server-macros): emit fixed `AUTH_METADATA` const per service The previous trait-derived const name turned `OpenShell` into `OPEN_SHELL_AUTH_METADATA`, splitting the project name across an underscore. Each impl already lives in its own module (`crate::grpc::`, `crate::inference::`), so the module path is enough to disambiguate between services — a fixed `AUTH_METADATA` name reads more naturally. Aggregator in `auth/method_authz.rs` now references `crate::grpc::AUTH_METADATA` and `crate::inference::AUTH_METADATA` directly. Addresses review comment on PR #1596. Signed-off-by: Mrunal Patel <mrunalp@gmail.com> * docs(server-macros): fix typo in AUTH_METADATA_CONST doc comment OpenShell is one word; reference name in the doc should be OPENSHELL_AUTH_METADATA, not OPEN_SHELL_AUTH_METADATA. Addresses review nit on PR #1596. Signed-off-by: Mrunal Patel <mrunalp@gmail.com> --------- Signed-off-by: Mrunal Patel <mrunalp@gmail.com> |
||
|
alangou
|
2bdc968ed9 |
fix(gateway): make readiness health checks dependency-aware (#1328)
* feat(gateway): add readiness probe metrics and test-only store close Emit Prometheus readiness metrics for database probes (healthy gauge and outcome-labeled latency histogram) with coverage in health HTTP tests. Restrict Store::close behind test support cfg to prevent accidental runtime pool shutdown under live traffic. Signed-off-by: Adrien Langou <alangou@nvidia.com> * test(e2e): add simple e2e test with kubernetes to test /readyz Signed-off-by: Adrien Langou <alangou@nvidia.com> --------- Signed-off-by: Adrien Langou <alangou@nvidia.com> |
||
|
Taylor Mutch
|
7d38aa8b8e |
fix(homebrew): repair local driver bootstrap state (#1527)
* fix(homebrew): repair local driver bootstrap state * fix(bootstrap): satisfy default SAN doc lint |
||
|
John T. Myers
|
0cef26521a |
feat(providers): derive discovery from profiles (#1503)
* feat(providers): derive discovery from profiles Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> * fix(providers): keep v2 discovery profile-only Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> * docs(providers): update providers v2 behavior Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> * fix(providers): make github profile read-only Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> --------- Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> |
||
|
Taylor Mutch
|
a3b16c18ab | feat(auth): per-sandbox authentication to gateway (#1404) |