feat(providers): add DeepInfra as a built-in inference provider

[mmilutinovic371]

Summary

DeepInfra is one of the top open source LLM providers and a perfect fit for agent frameworks with its low cost and high performance. This PR promotes it from a documented workaround to a core built-in provider in OpenShell.

• Adds deepinfra as a built-in inference provider alongside nvidia, openai, and anthropic
• DEEPINFRA_API_KEY is now discovered automatically via --from-existing
• openshell provider list-profiles shows DeepInfra in the INFERENCE section
• Fixes build_backend_url to correctly strip /v1 from request paths when the provider base URL contains /v1/ as an internal path segment (e.g. https://api.deepinfra.com/v1/openai) — without this fix, requests were routed to .../v1/openai/v1/chat/completions (404) instead of .../v1/openai/chat/completions

Related Issue

N/A

Changes

• providers/deepinfra.yaml — new built-in profile (inference category, api.deepinfra.com:443, Bearer auth, DEEPINFRA_API_KEY)
• crates/openshell-core/src/inference.rs — DEEPINFRA_PROFILE, normalization, profile_for entries + tests
• crates/openshell-providers/src/providers/deepinfra.rs — discovery spec + env-var test
• crates/openshell-providers/src/{lib,profiles,providers/mod}.rs — registration (alphabetical module order)
• crates/openshell-router/src/backend.rs — URL construction fix + test
• docs/sandboxes/providers-v2.mdx, docs/sandboxes/manage-providers.mdx — DeepInfra rows

Testing

• mise run pre-commit passes (rust, helm, markdown, license; python:proto is a pre-existing failure unrelated to this PR)
• 262 Rust unit tests pass across openshell-core, openshell-providers, openshell-router (cargo test -p openshell-core -p openshell-providers -p openshell-router)
• openshell provider list-profiles shows deepinfra in INFERENCE section
• openshell provider create --name di --type deepinfra --from-existing discovers DEEPINFRA_API_KEY
• openshell inference set --provider di --model <model> --no-verify configures route
• curl https://inference.local/v1/chat/completions from inside sandbox returns a valid completion from DeepInfra

Unit test results

test result: ok. 164 passed; 0 failed; 0 ignored  (openshell-core)
test result: ok. 37 passed;  0 failed; 0 ignored  (openshell-providers)
test result: ok. 44 passed;  0 failed; 0 ignored  (openshell-router)
test result: ok. 17 passed;  0 failed; 0 ignored  (openshell-router integration)

Includes inference::tests::profile_for_deepinfra, providers::deepinfra::tests::discovers_deepinfra_env_credentials, and backend::tests::build_backend_url_dedupes_v1_for_base_with_v1_subpath.

Provider list-profiles

INFERENCE
  deepinfra         DeepInfra         endpoints: 1  inference
  google-vertex-ai  Google Vertex AI  endpoints: 4  inference
  nvidia            NVIDIA            endpoints: 1  inference

End-to-end inference from inside sandbox

$ curl -s https://inference.local/v1/chat/completions --insecure \
    -H "Content-Type: application/json" \
    -d '{"model":"Qwen/Qwen3-30B-A3B","messages":[{"role":"user","content":"Say hello"}],"max_tokens":50}'

{"id":"chatcmpl-RvC46ezaN8prTxquYHZZJLMX","object":"chat.completion","model":"Qwen/Qwen3-30B-A3B",
 "choices":[{"message":{"role":"assistant","content":"<think>\nOkay, the user said \"Say hello.\" ..."}}],
 "usage":{"prompt_tokens":10,"total_tokens":60,"completion_tokens":50,"estimated_cost":2.34e-05}}

Screenshots / Logs

Checklist

• Follows Conventional Commits
• Commits are signed off (DCO)
• Architecture docs updated (docs/sandboxes/providers-v2.mdx, docs/sandboxes/manage-providers.mdx)

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[github-actions]

All contributors have signed the DCO ✍️ ✅
_{Posted by the DCO Assistant Lite bot.}

[github-actions]

Thank you for your interest in contributing to OpenShell, @mmilutinovic371.

This project uses a vouch system for first-time contributors. Before submitting a pull request, you need to be vouched by a maintainer.

To get vouched:

1. Open a Vouch Request discussion.
2. Describe what you want to change and why.
3. Write in your own words — do not have an AI generate the request.
4. A maintainer will comment /vouch if approved.
5. Once vouched, open a new PR (preferred) or reopen this one after a few minutes.

See CONTRIBUTING.md for details.

[mmilutinovic371]

I have read the DCO document and I hereby sign the DCO.

[mmilutinovic371]

recheck

[johntmyers]

Remove this, we will only support providers v2.

[johntmyers]

Please re-open the PR. Also please update the PR to only support Providers v2.