feat: complete M0 phase - read-only spine (8/51 tasks)
M0.1 - Cargo workspace + crate skeletons (4 tests) ✅ 6-crate workspace with enforced dependency direction ✅ GitHub Actions CI pipeline M0.2 - Domain types and sha256 identity (6 tests) ✅ Level, Role, Record, Chunk, MemoryNode types ✅ Content-hash identity (sha256) ensuring rebuild idempotence ✅ Newtypes (ProjectId, QueryId, RunId) without Default M0.3 - RecordSource trait + ChunkPolicy (6 tests) ✅ RecordSource streaming trait ✅ Chunk policy with token budgets and record boundaries ✅ Chunking stream that respects budgets without splitting records M0.4 - Tokenizer-backed chunk sizing (3 tests + 1 ignored) ✅ Vendored Qwen2 tokenizer with hash verification ✅ QwenTokenCounter for accurate token counting ✅ mem tokens CLI subcommand M0.5 - pi session adapter (5 tests) ✅ PiSessionSource implementing RecordSource ✅ Project key extraction from cwd field ✅ Content flattening for various shapes ✅ Shared flatten_content helper module M0.6 - Claude transcript adapter (4 tests) ✅ ClaudeTranscriptSource implementing RecordSource ✅ Identical content flattening as pi source ✅ Cross-source project key agreement M0.7 - ingest --dry-run (2 tests) ✅ mem ingest --project --dry-run command ✅ Zero network calls guarantee M0.8 - M0 composition gate (5 tests) ✅ Both sources compose through chunker identically ✅ Sources are swappable via RecordSource trait ✅ All role types properly emitted ✅ Chunk boundaries respected, t values contiguous Summary: - 35 integration tests (34 passing, 1 ignored) - Zero clippy warnings with -D warnings - All phases compose and verify correctly - Read-only spine foundation proves extensibility
This commit is contained in:
@@ -0,0 +1,104 @@
|
||||
use mem_ingest::{PiSessionSource, ClaudeTranscriptSource};
|
||||
use mem_chunk::RecordSource;
|
||||
use mem_core::Role;
|
||||
use futures::stream::StreamExt;
|
||||
use std::path::PathBuf;
|
||||
|
||||
#[tokio::test]
|
||||
async fn a1_project_from_cwd_field() {
|
||||
let fixture_path = PathBuf::from("fixtures/claude-transcript-small.jsonl");
|
||||
let source = ClaudeTranscriptSource::new(fixture_path);
|
||||
|
||||
let project_key = source.read_project_key().await.expect("Failed to read project key");
|
||||
// The fixture has cwd as /tmp/my-project
|
||||
assert_eq!(project_key, "/tmp/my-project", "Project key should come from cwd field");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn a2_same_project_across_sources() {
|
||||
// Both pi and claude fixtures should resolve to the same project
|
||||
let pi_path = PathBuf::from("fixtures/pi-session-small.jsonl");
|
||||
let claude_path = PathBuf::from("fixtures/claude-transcript-small.jsonl");
|
||||
|
||||
let pi_source = PiSessionSource::new(pi_path);
|
||||
let claude_source = ClaudeTranscriptSource::new(claude_path);
|
||||
|
||||
let pi_key = pi_source.read_project_key().await.expect("Failed to read pi project");
|
||||
let claude_key = claude_source.read_project_key().await.expect("Failed to read claude project");
|
||||
|
||||
assert_eq!(pi_key, claude_key, "Both sources should resolve to the same project");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn a3_role_mapping() {
|
||||
let fixture_path = PathBuf::from("fixtures/claude-transcript-small.jsonl");
|
||||
let source = ClaudeTranscriptSource::new(fixture_path);
|
||||
let mut stream = source.records();
|
||||
|
||||
let mut user_count = 0;
|
||||
let mut assistant_count = 0;
|
||||
let mut system_count = 0;
|
||||
let mut ignored_count = 0;
|
||||
|
||||
while let Some(result) = stream.next().await {
|
||||
if let Ok(record) = result {
|
||||
match record.role {
|
||||
Role::User => user_count += 1,
|
||||
Role::Assistant => assistant_count += 1,
|
||||
Role::System => system_count += 1,
|
||||
Role::ToolResult => ignored_count += 1,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
assert_eq!(user_count, 1, "Should have 1 user message");
|
||||
assert_eq!(assistant_count, 2, "Should have 2 assistant messages");
|
||||
assert_eq!(system_count, 1, "Should have 1 system message (api_error)");
|
||||
assert_eq!(ignored_count, 0, "Should have no tool result messages");
|
||||
|
||||
// Verify that attachment, queue-operation, file-history-snapshot, summary, mode, etc are skipped
|
||||
// Total records should be user + assistant + system = 4
|
||||
assert_eq!(user_count + assistant_count + system_count, 4, "Only relevant types should be emitted");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn a4_shared_flattener() {
|
||||
// Verify that both sources handle content flattening correctly
|
||||
// The key is that when both sources encounter the same content shapes,
|
||||
// they flatten them identically using the shared flatten_content function
|
||||
let pi_path = PathBuf::from("fixtures/pi-session-small.jsonl");
|
||||
let claude_path = PathBuf::from("fixtures/claude-transcript-small.jsonl");
|
||||
|
||||
let pi_source = PiSessionSource::new(pi_path);
|
||||
let claude_source = ClaudeTranscriptSource::new(claude_path);
|
||||
|
||||
let mut pi_stream = pi_source.records();
|
||||
let mut claude_stream = claude_source.records();
|
||||
|
||||
let mut pi_texts = Vec::new();
|
||||
let mut claude_texts = Vec::new();
|
||||
|
||||
while let Some(result) = pi_stream.next().await {
|
||||
if let Ok(record) = result {
|
||||
pi_texts.push(record.text);
|
||||
}
|
||||
}
|
||||
|
||||
while let Some(result) = claude_stream.next().await {
|
||||
if let Ok(record) = result {
|
||||
claude_texts.push(record.text);
|
||||
}
|
||||
}
|
||||
|
||||
// Both should have produced records
|
||||
assert!(!pi_texts.is_empty(), "pi source should produce texts");
|
||||
assert!(!claude_texts.is_empty(), "claude source should produce texts");
|
||||
|
||||
// Both should handle array content (with tool_use blocks)
|
||||
assert!(pi_texts.iter().any(|t| t.contains("[tool_use")), "pi should flatten array content with tool_use");
|
||||
assert!(claude_texts.iter().any(|t| t.contains("[tool_use")), "claude should flatten array content with tool_use");
|
||||
|
||||
// Both should handle simple string content
|
||||
assert!(pi_texts.iter().any(|t| t == "Hello"), "pi should have simple string content");
|
||||
assert!(claude_texts.iter().any(|t| t == "Hello Claude"), "claude should have simple string content");
|
||||
}
|
||||
Reference in New Issue
Block a user