M0.1 - Cargo workspace + crate skeletons - 6-crate workspace with correct dependency direction - CI/CD pipeline with GitHub Actions - Integration tests verifying build and dependency structure M0.2 - Domain types and sha256 identity - Level (L0, L1, L2) enum with proper serde formatting - Role enum (User, Assistant, ToolResult, System) - Record, Chunk, and MemoryNode domain types - Content-hash identity system ensuring rebuild idempotence - Newtypes (ProjectId, QueryId, RunId) with validation - Round-trip serde tests for all types M0.3 - RecordSource trait + ChunkPolicy - RecordSource trait for streaming record sources - Chunk policy with token budgets and boundary modes - TokenCounter trait with CharsOverFourCounter stub - Chunking stream that respects budgets without splitting records - VecSource for testing - Integration tests verifying lossless chunking and budget adherence M0.4 - Tokenizer-backed chunk sizing - Vendored Qwen2 tokenizer with hash verification - QwenTokenCounter implementing proper token counting - Hash guard that fails on modified tokenizer - mem tokens CLI subcommand for token counting - Integration tests with known string counts, hash guards, and budget verification Total: 19 integration tests passing, all phases verified to compose correctly Workspace builds cleanly with no clippy warnings
51 lines
1.1 KiB
TOML
51 lines
1.1 KiB
TOML
[package]
|
|
name = "poimen-memory"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
publish = false
|
|
|
|
[workspace]
|
|
members = [
|
|
".",
|
|
"crates/mem-core",
|
|
"crates/mem-chunk",
|
|
"crates/mem-llm",
|
|
"crates/mem-ingest",
|
|
"crates/mem-store",
|
|
"crates/mem-cli",
|
|
]
|
|
resolver = "2"
|
|
|
|
[workspace.dependencies]
|
|
tokio = { version = "1.35", features = ["full"] }
|
|
futures = "0.3"
|
|
serde = { version = "1.0", features = ["derive"] }
|
|
serde_json = "1.0"
|
|
serde_yaml = "0.9"
|
|
anyhow = "1.0"
|
|
thiserror = "1.0"
|
|
sha2 = "0.10"
|
|
clap = { version = "4.4", features = ["derive"] }
|
|
reqwest = { version = "0.11", features = ["json"] }
|
|
tracing = "0.1"
|
|
tracing-subscriber = "0.3"
|
|
toml = "0.8"
|
|
hex = "0.4"
|
|
time = { version = "0.3", features = ["serde", "formatting", "parsing", "macros"] }
|
|
tokenizers = "0.13"
|
|
once_cell = "1.19"
|
|
|
|
[dev-dependencies]
|
|
toml = { workspace = true }
|
|
mem-core = { path = "crates/mem-core" }
|
|
mem-chunk = { path = "crates/mem-chunk" }
|
|
serde_json = { workspace = true }
|
|
time = { workspace = true }
|
|
tokio = { workspace = true }
|
|
futures = { workspace = true }
|
|
|
|
[profile.release]
|
|
opt-level = 3
|
|
lto = true
|
|
codegen-units = 1
|