feat: add SSE streaming support (OpenAI-compatible)

- Token-by-token streaming via Server-Sent Events
- tokio::sync::mpsc channel + ReceiverStream for clean async
- OpenAI SSE format: role chunk → content chunks → finish chunk
- Non-streaming still works with the same code path
- Uses spawn_blocking pattern for CPU-bound inference

Cargo.lock

@@ -264,6 +264,21 @@ dependencies = [
  "percent-encoding",
 ]
 
+[[package]]
+name = "futures"
+version = "0.3.33"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a88cf1f829d945f548cf8fec32c61b1f202b6d93b45848602fc02af4b12ad218"
+dependencies = [
+ "futures-channel",
+ "futures-core",
+ "futures-executor",
+ "futures-io",
+ "futures-sink",
+ "futures-task",
+ "futures-util",
+]
+
 [[package]]
 name = "futures-channel"
 version = "0.3.33"
@@ -271,6 +286,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "262590f4fe6afeb0bc83be1daa64e52657fe185690a958af7f3ad0e92085c5ae"
 dependencies = [
  "futures-core",
+ "futures-sink",
 ]
 
 [[package]]
@@ -279,6 +295,40 @@ version = "0.3.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2cd50c473c80f6d7c3670a752354b8e569b1a7cbfdc0419ec88e5edad85e0dc7"
 
+[[package]]
+name = "futures-executor"
+version = "0.3.33"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6754879cc9f2c66f88c6e5c35344bb0bdb0708b0352b1201815667c7eabc7458"
+dependencies = [
+ "futures-core",
+ "futures-task",
+ "futures-util",
+]
+
+[[package]]
+name = "futures-io"
+version = "0.3.33"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4577ecaa3c4f96589d473f679a71b596316f6641bc350038b962a5daf0085d7a"
+
+[[package]]
+name = "futures-macro"
+version = "0.3.33"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2d6d3cde68c518367be28956066ddfef33813991b77a55005a69dae04bf3b10b"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+]
+
+[[package]]
+name = "futures-sink"
+version = "0.3.33"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e34418ac499d6305c2fb5ad0ed2f6ac998c5f8ca209b4510f7f94242c647e307"
+
 [[package]]
 name = "futures-task"
 version = "0.3.33"
@@ -291,8 +341,13 @@ version = "0.3.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a77a90a256fce34da66415271e30f94ee91c57b04b8a2c042d9cf3220179deaa"
 dependencies = [
+ "futures-channel",
  "futures-core",
+ "futures-io",
+ "futures-macro",
+ "futures-sink",
  "futures-task",
+ "memchr",
  "pin-project-lite",
  "slab",
 ]
@@ -511,10 +566,12 @@ dependencies = [
  "anyhow",
  "axum",
  "chrono",
+ "futures",
  "llama-cpp-2",
  "serde",
  "serde_json",
  "tokio",
+ "tokio-stream",
  "tower-http",
  "tracing",
  "tracing-subscriber",
@@ -958,6 +1015,17 @@ dependencies = [
  "syn 2.0.119",
 ]
 
+[[package]]
+name = "tokio-stream"
+version = "0.1.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a3d06f0b082ba57c26b79407372e57cf2a1e28124f78e9479fe80322cf53420b"
+dependencies = [
+ "futures-core",
+ "pin-project-lite",
+ "tokio",
+]
+
 [[package]]
 name = "tower"
 version = "0.5.3"