* fix(security): resolve model aliases before audit classification
Before classification, model strings are now resolved through the alias
index so that configured aliases (e.g. 'gpt-prev') are translated to
their canonical provider/key form (e.g. 'openai/gpt-5.4') before hygene
and tier checks run.
Fixes#74455.
Signed-off-by: Blasius Patrick <blasius.patrick@gmail.com>
* fix(security): share audit model alias resolution
---------
Signed-off-by: Blasius Patrick <blasius.patrick@gmail.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Previously, models from unconfigured providers were shown with an
"auth missing" hint, flooding the picker with 900+ unusable entries.
Now addModelSelectOption early-returns when the provider has no auth,
so only usable models appear in /models and the web chat dropdown.
Fixes#74423
* feat(nvidia): add NVIDIA provider with onboarding flow
Add the NVIDIA build.nvidia.com API as a bundled provider. Default model
is nvidia/nvidia/nemotron-3-super-120b-a12b: first segment is the provider
id, remaining "nvidia/nemotron-3-super-120b-a12b" is the literal upstream
model id (which happens to start with "nvidia/" because NVIDIA is also the
model maker).
Supporting core change: introduce a provider capability flag
nativeIdsIncludeProviderPrefix so providers whose native catalog ids
intentionally include their provider prefix (OpenRouter) opt into self-prefix
dedupe in modelKey, without hardcoding provider names in core. Providers
whose ids merely happen to start with their own name (NVIDIA) leave the flag
unset and get the full <provider>/<model-id> concatenation.
- extensions/nvidia/*: new plugin, catalog, onboarding, tests, docs
- extensions/openrouter/index.ts: declare nativeIdsIncludeProviderPrefix
- src/plugins/types.ts: add field to ProviderPlugin
- src/plugins/registry.ts: populate self-prefix set on registration
- src/agents/provider-self-prefix.ts: sync accessor used by modelKey
- src/agents/model-ref-shared.ts: modelKey consults the flag
- test updates for affected surfaces
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* refactor(model-picker): simplify literal-prefix display to label-only
* fix(model-picker): pass workspaceDir/env to allowlist literal-prefix resolution
* chore: untrack generated baseline JSON artifacts (gitignored)
* fix(nvidia): show literal model ref in picker and onboarding notes
* fix(nvidia): show hint whenever display label differs from stored config
* fix(nvidia): drop redundant hint from Keep current label
* fix(nvidia): restore literal double-prefix display labels
* fix(picker): handle literal-prefix fast path
* fix(picker): show literal keep label
* fix(docs): update nvidia provider docs
* fix(nvidia): update test helper imports
* fix(changelog): add nvidia provider entry
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* Prevent hidden channel lifecycle runs from staying stuck as running
Hidden channel-routed runs were dropping session keys on lifecycle events at
our shared agent-event bus. Gateway lifecycle persistence then had to rely on
run-context lookup surviving until the terminal event, which is unnecessarily
fragile for the exact sessions that are intentionally hidden from Control UI.
This keeps session keys on hidden lifecycle events only, preserving the existing
privacy boundary for assistant/tool traffic while making terminal session-state
persistence explicit and test-covered.
Constraint: Hidden channel runs must stay out of Control UI chat/tool streams
Rejected: Broaden sessionKey preservation to every hidden event | would expose more hidden traffic than needed
Confidence: medium
Scope-risk: narrow
Reversibility: clean
Directive: If hidden-run event redaction changes again, keep lifecycle persistence independent from ephemeral run-context lookup
Tested: pnpm exec oxfmt --check --threads=1 CHANGELOG.md src/infra/agent-events.ts src/infra/agent-events.test.ts; pnpm tsgo:core; pnpm tsgo:extensions; pnpm tsgo:core:test; pnpm tsgo:extensions:test; pnpm test src/infra/agent-events.test.ts; pnpm test src/gateway/server-chat.agent-events.test.ts; pnpm test src/gateway/session-lifecycle-state.test.ts; pnpm lint:extensions:bundled; codex exec review returned ship it
Not-tested: Live gateway reproduction against Knox's local stuck-session install
* Clarify hidden lifecycle redaction and cover context fallback
The follow-up review asked for two things: document why the separate error
stream stays redacted for hidden runs, and cover the registered-context fallback
branch for hidden lifecycle events when callers omit sessionKey.
Constraint: Hidden assistant/tool/error diagnostics must remain redacted from Control UI
Rejected: Preserve sessionKey on the generic error stream | terminal persistence already flows through lifecycle phase:error, so widening the visible identity surface is unnecessary
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep hidden-run identity exceptions tightly scoped to terminal lifecycle persistence unless a concrete downstream consumer requires more
Tested: pnpm exec oxfmt --write --threads=1 src/infra/agent-events.ts src/infra/agent-events.test.ts; pnpm test src/infra/agent-events.test.ts; pnpm test src/gateway/server-chat.agent-events.test.ts; pnpm test src/gateway/session-lifecycle-state.test.ts
Not-tested: Full repo gate rerun; previous branch-wide gates remain from the parent PR commit
* fix(gateway): keep hidden agent broadcasts redacted
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
`shouldRemoveRuntimeDepsLock` previously trusted `isAlive(owner.pid)`
alone when deciding whether a lock could be reclaimed. That works fine
on a normal host: when the writer dies the PID is gone and `isAlive`
returns false. Inside Docker it does not — every Node gateway process
runs as PID 1 (or PID 7 with `init: true`) in its container PID
namespace, so a stale lock left behind by a previous incarnation looks
"alive" to the new one. The 5-minute lock-wait timeout then fires and
the supervisor restarts, and the cycle repeats indefinitely. Operators
have to manually remove `.openclaw-runtime-deps.lock` to recover.
This change records `pidStartTimeMs` alongside `pid` and `createdAtMs`
when the lock is acquired, and consults it in the staleness check.
When both sides have start-time evidence and they disagree, the lock
is treated as stale; otherwise the existing PID-alive-means-fresh
behavior is preserved exactly. The capture point uses
`Date.now() - process.uptime() * 1000` once at module load, and the
read side uses `/proc/<pid>/stat` field 22 on Linux (returning null
elsewhere so legacy semantics still apply on macOS/Windows hosts).
This is strictly additive on the wire format and the predicate:
existing lock files without `pidStartTimeMs` continue to take the same
code path they did before, and platforms that cannot resolve a live
PID's start-time fall back to the same legacy behavior.
Refs #74346.
