v0.13.0:3 - proxy /v1/chat/completions through Spark Control to vLLM

Recap Relay dev caught that all audio endpoints route through Spark
Control but chat-completions didn't — clients had to know about both
SC AND the direct vLLM URL on Spark 1. Closes that last gap.

New endpoints:
  POST /v1/chat/completions   — OpenAI-shape, forwards to vLLM on Spark 1
  POST /v1/completions        — legacy OpenAI completions, same path

Implementation (image/app/llm_proxy.py):
  - Dumb forwarder: request body passed through verbatim, response body
    streamed back chunk-by-chunk. No transformation. vLLM already speaks
    the same shape; adding any logic here would just create skew.
  - Streaming: parses body for `stream: true` and uses httpx.AsyncClient
    .stream() + FastAPI StreamingResponse if so. Non-streaming path is
    a simple post-and-return.
  - 30-minute timeout to accommodate large-context completions (default
    httpx 5s would kill anything substantial).
  - On upstream non-200 in streaming mode: emits one SSE `error` event
    so the client's parser doesn't hang on an empty stream forever.
  - On upstream connection error: HTTP 502 with "vllm unreachable" detail.

Now clients can use ONE host for everything:
  POST https://spark-control/api/audio/diarize-chunk
  POST https://spark-control/v1/audio/transcriptions
  POST https://spark-control/v1/chat/completions
  GET  https://spark-control/api/endpoints  (still works for clients that
                                              prefer the direct URLs)

No parakeet container changes. No Reapply patches needed.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

package/startos/versions/v0_1_0.ts

@@ -1,10 +1,10 @@
 import { VersionInfo, IMPOSSIBLE } from '@start9labs/start-sdk'
 
 export const v0_1_0 = VersionInfo.of({
-  version: '0.13.0:2',
+  version: '0.13.0:3',
   releaseNotes: {
     en_US:
-      'v0.13.0:2 — per-segment confidence in diarize-chunk. Sortformer outputs per-frame per-speaker sigmoid probabilities (~12.6 fps) that we previously discarded. Now: for each diarization segment, compute mean probability of the assigned speaker across the segment\'s frames → confidence in [0, 1]. Recap Relay (and other consumers) can threshold this to render uncertain segments as "Speaker_0?" with a question mark, or to skip them entirely. Endpoint shape is otherwise unchanged — segments[].confidence is a new field, value may be None on derivation failure. Click Reapply patches on the Speech Models card after install to pick up the updated diarizer.py + main.py.',
+      'v0.13.0:3 — chat-completions proxy. Adds POST /v1/chat/completions (and /v1/completions for the legacy endpoint) to Spark Control that forwards to whichever vLLM is currently loaded on Spark 1. Supports SSE streaming when stream=true in the request body. Request body is passed through unchanged — any vLLM-supported field works (model, messages, max_tokens, temperature, response_format, chat_template_kwargs, tools, ...). Closes the last gap that forced clients to know about both Spark Control AND the direct vLLM URL — recap-relay and friends can now use one trusted host for everything (transcribe, diarize, analyze) with one cert and one allowlist. 30-min request timeout to accommodate large-context completions. No parakeet container changes; no Reapply patches needed.',
   },
   migrations: {
     up: async ({ effects }) => {},