mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
7da4af622f
## Summary This PR adds `memchr` for some low-hanging performance improvements (namely, in MCP stdio, Ollama streaming, and full message-history newline counts). Codex produced the following release benchmarks: | Operation | Before | After | Speedup | | --- | ---: | ---: | ---: | | MCP 1 MiB chunked line | 2.172 s | 3.984 ms | 545x | | Ollama 1 MiB chunked line | 1.673 s | 2.790 ms | 600x | | Count newlines in 10 MiB history | 132.83 ms | 20.05 ms | 6.6x | With a "real" MCP setup (`ExecutorStdioServerLauncher` started a Python MCP server, completed `initialize`, requested `tools/list`, and deserialized a 1 MiB tool description over newline-delimited stdio), it's about 16x faster end-to-end: | Branch | 50 calls | Per call | | --- | ---: | ---: | | `main` | 862.53 ms | 17.25 ms | | this branch | 53.89 ms | 1.08 ms | `memchr` is already in our dependency tree and extremely widely used for this kind of optimized scanning.
38 lines
856 B
TOML
38 lines
856 B
TOML
[package]
|
|
name = "codex-ollama"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
license.workspace = true
|
|
|
|
[lib]
|
|
name = "codex_ollama"
|
|
path = "src/lib.rs"
|
|
doctest = false
|
|
|
|
[lints]
|
|
workspace = true
|
|
|
|
[dependencies]
|
|
async-stream = { workspace = true }
|
|
bytes = { workspace = true }
|
|
codex-core = { workspace = true }
|
|
codex-model-provider-info = { workspace = true }
|
|
futures = { workspace = true }
|
|
memchr = { workspace = true }
|
|
reqwest = { workspace = true, features = ["json", "stream"] }
|
|
semver = { workspace = true }
|
|
serde_json = { workspace = true }
|
|
tokio = { workspace = true, features = [
|
|
"io-std",
|
|
"macros",
|
|
"process",
|
|
"rt-multi-thread",
|
|
"signal",
|
|
] }
|
|
tracing = { workspace = true, features = ["log"] }
|
|
wiremock = { workspace = true }
|
|
|
|
[dev-dependencies]
|
|
assert_matches = { workspace = true }
|
|
pretty_assertions = { workspace = true }
|