litellm/.github
yujonglee 95ecfbbac6
feat(proxy): supervise the opt-in Rust forwarding server (#49606)
* feat(proxy): supervise the opt-in Rust forwarding server

With LITELLM_RUST on, `litellm` and `python -m gateway.launch` start a
supervisor that runs the Rust gateway on the public port and Python on a
private loopback listener. Python still serves every route and sees each
request as if the client had connected to it directly.

Rust sends the client's TCP peer in `x-litellm-rust-peer`. The supervised
server turns server-level proxy headers off, and a middleware restores
the peer and then applies the operator's own trust, so client IPs,
trusted proxies and every IP-based setting behave the same with Rust on
or off.

The supervisor is transparent to Python. Signals pass through, Python's
exit status is the result, and both children shut down when the
supervisor's end of their stdin closes, so nothing outlives it. Rust
starts only once Python listens. When forwarding cannot start (no
gateway binary, TLS, a Unix socket, Hypercorn or Granian), the entry
point warns and serves from Python alone.

Every forwarding decision lives in litellm/proxy/rust_forward, paired
with the gateway-forward crate. OS differences sit behind a Platform
protocol, with Windows supported for local CLI runs. AGENTS.md files in
the touched folders state the boundary. The `--rust_gateway` flag is
gone in favor of the environment variable.

* refactor(proxy): switch Rust forwarding on with LITELLM_RUST_FIRST

Forwarding gets its own switch, independent of LITELLM_RUST, which keeps
selecting only the Rust paths inside the SDK. Neither turns the other on.

---------

Co-authored-by: narmstrong-berri <narmstrong@berri.ai>
2026-11-11 19:40:00 +00:00
..
actions ci: split slow unit shards and build the Rust bridge once per run (#44622) 2026-10-05 23:43:01 +00:00
assets/scaledown feat(scaledown): add native text provider support (#44168) 2026-10-10 14:01:17 -07:00
codeql ci(codeql): run the default suite on full scans and security-extended on PRs (#45149) 2026-10-07 13:24:28 -07:00
e2e-stack test(mcp): replace the live Linear MCP OAuth e2e tests with integration coverage (#47154) 2026-10-17 14:29:59 -07:00
ISSUE_TEMPLATE ci: classify new issues into domain, provider, kind, priority and lift labels 2026-09-18 11:37:55 -07:00
observatory Add observatory test workflow for RC/stable releases 2026-03-01 15:30:09 -03:00
prompts ci: classify new issues into domain, provider, kind, priority and lift labels 2026-09-18 11:37:55 -07:00
PULL_REQUEST_TEMPLATE docs(pr-template): require rerunnable proof setup and collapsed long output (#50258) 2026-11-05 13:24:50 -08:00
screenshots fix(team_endpoints): auto-add SSO team members to org on move (proxy admin only) (#26377) 2026-04-24 08:36:25 -07:00
scripts refactor(rust_bridge): route every Rust-to-Python call through host modules (#50822) 2026-11-11 01:57:54 +00:00
workflows feat(proxy): supervise the opt-in Rust forwarding server (#49606) 2026-11-11 19:40:00 +00:00
ci-coverage-allowlist.yml feat(docker)!: one shipped image and one entrypoint beside the Dockerfile (#43332) 2026-11-10 18:32:16 -08:00
CODEOWNERS fix(cost_map): mark fireworks_ai/minimax-m3 as vision and pin capabilities verified against live calls (#43390) 2026-10-29 00:23:11 -07:00
dependabot.yaml chore: fixes 2026-04-05 01:30:57 -07:00
deploy-on-aws.png feat: add LiteLLM Rust workspace with Mistral OCR bridge (#31033) 2026-06-23 13:16:47 -07:00
deploy-on-gcp.png feat: add LiteLLM Rust workspace with Mistral OCR bridge (#31033) 2026-06-23 13:16:47 -07:00
deploy-to-aws.png Add files via upload 2023-10-25 16:33:53 -07:00
FUNDING.yml Update FUNDING.yml 2023-09-22 09:51:35 -07:00
issue-labels.json ci(issue-classifier): name every workflow, script and job after the issue it works on 2026-09-18 11:37:55 -07:00
mutmut-coverage.rc fix(ci): let the mutation workflow find covered lines so it generates mutants 2026-08-25 23:16:40 -07:00
template.yaml fix(proxy): drop legacy telemetry key from persisted WORKER_CONFIG before initialize 2026-09-20 03:14:11 +00:00