## Summary
- Add the v0.0.59 release notes from the GitHub announcement discussion.
- Refresh local inference and credential-storage guidance for the
current release behavior.
- Regenerate the user skills from the updated Fern docs.
- Tighten release-prep and docs review guidance for generated skills, PR
labels, and shared `$$nemoclaw` command placeholders.

## Verification
- `python3 scripts/docs-to-skills.py docs/ .agents/skills/ --prefix
nemoclaw-user --doc-platform fern-mdx`
- `rg "permissive mode|shields down|shields up|shields status|config
rotate-token|rotate-token" --glob '*.{md,mdx}'`
- `git diff --check`
- `npm run docs` (rerun outside sandbox after sandbox-only `tsx` IPC
permission failure)
- `npm run typecheck:cli`
- Pre-commit hooks during commit passed, including markdownlint,
docs-to-skills verification, gitleaks, commitlint, and skills YAML
tests.

## Source Summary
- #3679, #4437, #4681, #4766, #4772, #4775, #4786 ->
`docs/about/release-notes.mdx`, `docs/reference/commands.mdx`,
`docs/reference/troubleshooting.mdx`: Summarize OpenClaw 2026.5.27
compatibility, runtime path pinning, plugin registry recovery, live
gateway reconciliation, and clearer host-alias/startup diagnostics.
- #4332, #4402, #4769, #4776, #4779 -> `docs/about/release-notes.mdx`,
`docs/inference/inference-options.mdx`,
`docs/inference/use-local-inference.mdx`,
`docs/inference/switch-inference-providers.mdx`: Document the release
inference changes covering Local NIM waits, Hermes Anthropic routing,
Nemotron 3 Ultra, the current Ollama starter fallback, and Spark
managed-vLLM context length.
- #4628, #4652, #4733, #4745 -> `docs/about/release-notes.mdx`,
`docs/security/credential-storage.mdx`,
`docs/manage-sandboxes/messaging-channels.mdx`,
`docs/reference/troubleshooting.mdx`: Capture permission healing,
gateway-stored credential reuse, cross-sandbox messaging credential
conflict checks, and CDI preflight diagnostics.
- #4728, #4737, #4743, #4744, #4782 -> `.agents/skills/nemoclaw-user-*`:
Regenerate the user skill references from the updated source docs.
- Follow-up maintenance ->
`.agents/skills/nemoclaw-contributor-update-docs/SKILL.md`,
`.coderabbit.yaml`: Add release-prep area labels for docs and skills
PRs, and teach docs review guidance that `$$nemoclaw` is the correct
shared command placeholder for examples that work across agent aliases.

Note: the `documentation` label was not present in the repository, so
this PR is labeled with `v0.0.59` only.

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **Documentation**
  * Updated default model for local Ollama inference setup to qwen3.5:9b
  * Added Nemotron 3 Ultra 550B as an NVIDIA Endpoints model option
* Clarified credential storage and reuse behavior for post-deployment
(day-two) operations
* Added v0.0.59 release notes covering OpenClaw compatibility, inference
options, Hermes messaging sync, and troubleshooting
* Clarified CLI selection guidance and updated OpenClaw version example
in status output
* Revised release-prep instructions and docs review guidance for CLI
alias usage
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

## Summary
- Resolve the managed inference API family during `nemoclaw inference
set` / `nemohermes inference set` before patching in-sandbox config.
- Set Hermes `model.api_mode` for Anthropic Messages and OpenAI
Responses routes, and clear stale `api_mode` when switching back to
OpenAI-style chat completions.
- Preserve the Bedrock Runtime adapter exception: same-provider
compatible-Anthropic routes that were resolved as OpenAI-compatible stay
on `/v1/chat/completions`.
- Add hermetic Anthropic Messages switch coverage for both Hermes and
OpenClaw: the E2E scripts can register a compatible Anthropic mock
provider, verify `/v1/messages` through `inference.local`, then exercise
the agent path after the switch.

## Why
#4809 reported a `403 connection not allowed by policy` while the agent
was calling `https://inference.local`, so the right fix is not to open
direct sandbox egress to the upstream inference host. #4402 fixed fresh
Hermes onboarding by allowing managed `/v1/messages` and baking
`api_mode: anthropic_messages`. This PR covers the remaining
runtime-switch path so both Hermes and OpenClaw keep using
OpenShell-managed inference correctly after `inference set`.

## References
- Refs #4809
- Related #4230
- Builds on #4402

## Validation
- `npx vitest run src/lib/actions/inference-set.test.ts`
- `npx vitest run src/lib/actions/inference-set.test.ts
src/lib/inference/config.test.ts test/generate-hermes-config.test.ts
test/generate-openclaw-config.test.ts` (initial combined run hit two
existing 5s per-test timeouts in
`test/generate-openclaw-config.test.ts`; rerun below passed with a
larger timeout)
- `npx vitest run test/generate-openclaw-config.test.ts --testTimeout
20000`
- `npx vitest run test/validate-e2e-coverage.test.ts`
- `shellcheck test/e2e/test-hermes-inference-switch.sh
test/e2e/test-openclaw-inference-switch.sh
test/e2e/lib/anthropic-switch-provider.sh
test/e2e/lib/inference-switch-retry.sh`
- `bash -n test/e2e/test-hermes-inference-switch.sh
test/e2e/test-openclaw-inference-switch.sh
test/e2e/lib/anthropic-switch-provider.sh
test/e2e/lib/inference-switch-retry.sh`
- `npx biome check src/lib/actions/inference-set.ts
src/lib/actions/inference-set.test.ts`
- `npm run build:cli`
- `npm run validate:configs`
- `git diff --check`
- PR checks green on head `e21952d57e8ef23caa266d6862e7367ec3bd3814`,
including commit-lint and DCO.
- Targeted E2E run `27014755537` passed both new agent-path proofs:
  - `hermes-anthropic-inference-switch-e2e / run`
  - `openclaw-anthropic-inference-switch-e2e / run`


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

## Release Notes

* **New Features**
* Added support for switching between OpenAI and Anthropic inference API
modes in sandbox configurations.

* **Tests**
* Introduced nightly E2E test jobs for validating Anthropic inference
switching across agents.
* Expanded test coverage for inference API configuration validation and
provider switching scenarios.
  * Added mock Anthropic provider support for local E2E testing.

* **Chores**
* Updated CI/CD workflow to include new inference-switch E2E test jobs
and orchestration.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>