Files
optimclaw/tests/workspace_integration.rs
T
86ae12747b feat: LRU embedding cache for workspace search (#1423)
* feat: LRU embedding cache for workspace search (#165)

Add CachedEmbeddingProvider that wraps any EmbeddingProvider with an
in-memory LRU cache keyed by SHA-256(model_name + text). This avoids
redundant HTTP calls when the same text is embedded multiple times
(common during reindexing and repeated searches).

- Cache uses HashMap + last_accessed tracking with manual LRU eviction
  (same pattern as llm::response_cache::CachedProvider)
- Lock is never held during HTTP calls to prevent blocking
- embed_batch() partitions into hits/misses and only fetches misses
- Default 10,000 entries (~58 MB for 1536-dim vectors)
- Configurable via EMBEDDING_CACHE_SIZE env var
- Workspace.with_embeddings() auto-wraps; with_embeddings_uncached()
  available for tests

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address review comments on embedding cache

- Validate embed_batch return count matches expected miss count
- Replace unwrap_or_default() with proper error propagation
- Fix batch eviction: run final eviction pass after insert to enforce cap
- Fix test: use different-length inputs to verify ordering correctness
- Reject EMBEDDING_CACHE_SIZE=0 in config validation (minimum is 1)

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: replace .expect() with proper error handling in embed_batch

The all-cache-hits early-return path used .expect("all cache hits") which
violates the project convention of no .unwrap()/.expect() in production
code. Replaced with the same ok_or_else pattern used in the normal path.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: clarify memory sizing docs and use saturating_add for eviction

- Update memory comments in embedding_cache.rs, config/embeddings.rs,
  and workspace/mod.rs to note the ~58 MB figure is payload-only
  (actual memory is higher due to HashMap/key/allocation overhead)
- Use saturating_add(1) instead of + 1 for eviction threshold to
  prevent overflow if max_entries is usize::MAX

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address Copilot review on embedding cache

- Avoid double-clone per miss in embed_batch: move embedding into
  results, clone only for the cache entry
- Evict per-insert instead of after all inserts to keep peak memory
  bounded during large batches
- Clamp max_entries to at least 1 in constructor to prevent unexpected
  eviction behavior when set to 0 via the public API

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: reduce embedding_cache module visibility to private

Types are already re-exported via `pub use`, so the module itself
doesn't need to be public. Reduces unnecessary API surface.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address serrrfirat review feedback on embedding cache

- Add TODO comment for O(n) LRU eviction scalability
- Add thundering herd note at lock release in embed()
- Warn when cache max_entries exceeds 100k
- Use with_embeddings_uncached() in integration test
- Add tests: error_does_not_pollute_cache, embed_batch_empty_input
- Update README with cache-aware with_embeddings() docs

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: prevent u32 wrapping in FailThenSucceedMock failure counter

fetch_sub(1) wraps to u32::MAX when called past zero, silently
breaking the mock for 3+ calls. Switch to load-then-store to avoid
the wrapping bug in both embed() and embed_batch().

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address Copilot and serrrfirat review findings on embedding cache

- Switch tokio::sync::Mutex to std::sync::Mutex (lock never held across
  .await — cheaper synchronous lock)
- Extract DEFAULT_EMBEDDING_CACHE_SIZE constant to avoid 10_000 duplication
  between EmbeddingCacheConfig and EmbeddingsConfig

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* test: add all-misses batch test for embedding cache

Adds embed_batch_all_misses test covering the case where every text in a
batch is a cache miss — fulfilling the commitment from serrrfirat's review.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* chore: trigger CI re-check after rebase

* fix: use raw [u8;32] cache keys and pre-allocate HashMap capacity

Address Copilot review findings:
- cache_key() now returns [u8; 32] instead of hex String, avoiding a
  64-byte allocation per lookup
- HashMap::with_capacity(max_entries) avoids incremental reallocation
- Fix pre-existing staging compilation error in cli/routines.rs
  (missing max_tool_rounds/use_tools fields)

[skip-regression-check]

* fix: make cache accessors sync and update doc for [u8;32] keys

Address Copilot review:
- len(), is_empty(), clear() are now sync since they only take a
  std::sync::Mutex lock with no .await points
- Update cache_size doc comment to reflect [u8;32] keys instead of
  String keys

[skip-regression-check]

* fix: remove clone_on_copy for [u8; 32] cache keys

[skip-regression-check]

* ci: add safety comments to test code for no-panics check

The CI no-panics grep check cannot distinguish test code inside
src/ files from production code. Add // safety: test annotations
to .unwrap(), .expect(), and assert!() calls in #[cfg(test)] modules.

* fix: correct cache doc and demote hit/miss logs to trace

- Fix misleading "String keys" in memory comment (cache uses [u8; 32])
- Demote per-request hit/miss logs from debug to trace to reduce noise
  on hot paths (batch summary stays at trace too)

* docs: add missing Arc import in workspace README example

* perf: batch eviction in embed_batch to avoid O(n×m) cost

Replace per-insert evict_lru call with a single evict_k_oldest pass
that computes eviction count upfront and removes the k oldest entries
in one O(n) scan. Avoids O(n×m) HashMap iterations while holding the
mutex during batch inserts.

* fix: cap batch cache inserts at max_entries and use O(n) selection

- evict_k_oldest now uses select_nth_unstable_by_key for O(n) average
  partial selection instead of O(n log n) full sort
- embed_batch caps cached entries at max_entries when misses exceed
  capacity, preventing the cache from growing unbounded
- Added test: batch_exceeding_capacity_respects_max_entries

* fix: flatten test assert for fmt compatibility

Shorten assert message to fit single line so cargo fmt doesn't
split the safety annotation onto a separate line.

* fix: address review feedback and improve embedding cache (takeover #235)

- Fix merge conflict: add missing allow_always field in PendingApproval
- Thread EmbeddingCacheConfig through CLI memory commands so they respect
  EMBEDDING_CACHE_SIZE instead of silently using default (fixes #235 review)
- Cap HashMap pre-allocation at min(max_entries, 1024) to avoid upfront
  memory waste at large cache sizes
- Fix FailThenSucceedMock race: replace load+store with atomic fetch_update
- Remove noisy '// safety: test' comments (40+ lines of diff noise)
- Fix collapsed lines from comment removal
- Simplify redundant Ok(...collect()?) to just collect()

Co-Authored-By: ztsalexey <[email protected]>
Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix(embedding-cache): skip eviction on concurrent duplicate insert

When the lock is released for the HTTP call, another caller may insert
the same key. Re-check under lock and just update the existing entry
without evicting, avoiding unnecessary cache churn under concurrency.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

---------

Co-authored-by: ztsalexey <[email protected]>
Co-authored-by: Claude Opus 4.6 <[email protected]>
Co-authored-by: ztsalexey <[email protected]>
2026-03-19 13:37:55 -07:00

410 lines
11 KiB
Rust

#![cfg(feature = "postgres")]
//! Integration tests for the workspace module.
//!
//! Requires a running PostgreSQL with pgvector extension.
//! Set DATABASE_URL=postgres://localhost/ironclaw_test
use std::sync::Arc;
use ironclaw::workspace::{MockEmbeddings, SearchConfig, Workspace, paths};
fn get_pool() -> deadpool_postgres::Pool {
let database_url = std::env::var("DATABASE_URL")
.unwrap_or_else(|_| "postgres://localhost/ironclaw_test".to_string());
let config: tokio_postgres::Config = database_url.parse().expect("Invalid DATABASE_URL");
let mgr = deadpool_postgres::Manager::new(config, tokio_postgres::NoTls);
deadpool_postgres::Pool::builder(mgr)
.max_size(4)
.build()
.expect("Failed to create pool")
}
/// Try to get a connection, returning None if Postgres is unreachable.
/// Tests call this to skip gracefully in CI where no database is available.
async fn try_connect(pool: &deadpool_postgres::Pool) -> Option<()> {
match pool.get().await {
Ok(_) => Some(()),
Err(e) => {
eprintln!("skipping: database unavailable ({e})");
None
}
}
}
async fn cleanup_user(pool: &deadpool_postgres::Pool, user_id: &str) {
let conn = pool.get().await.expect("Failed to get connection");
conn.execute(
"DELETE FROM memory_documents WHERE user_id = $1",
&[&user_id],
)
.await
.ok();
}
#[tokio::test]
async fn test_workspace_write_and_read() {
let pool = get_pool();
if try_connect(&pool).await.is_none() {
return;
}
let user_id = "test_write_read";
cleanup_user(&pool, user_id).await;
let workspace = Workspace::new(user_id, pool.clone());
// Write a file
let doc = workspace
.write("README.md", "# Hello World\n\nThis is a test.")
.await
.expect("Failed to write");
assert_eq!(doc.path, "README.md");
assert!(doc.content.contains("Hello World"));
// Read it back
let doc2 = workspace.read("README.md").await.expect("Failed to read");
assert_eq!(doc2.content, "# Hello World\n\nThis is a test.");
// Cleanup
cleanup_user(&pool, user_id).await;
}
#[tokio::test]
async fn test_workspace_append() {
let pool = get_pool();
if try_connect(&pool).await.is_none() {
return;
}
let user_id = "test_append";
cleanup_user(&pool, user_id).await;
let workspace = Workspace::new(user_id, pool.clone());
// Write initial content
workspace
.write("notes.md", "Line 1")
.await
.expect("Failed to write");
// Append more
workspace
.append("notes.md", "Line 2")
.await
.expect("Failed to append");
// Read and verify
let doc = workspace.read("notes.md").await.expect("Failed to read");
assert_eq!(doc.content, "Line 1\nLine 2");
cleanup_user(&pool, user_id).await;
}
#[tokio::test]
async fn test_workspace_nested_paths() {
let pool = get_pool();
if try_connect(&pool).await.is_none() {
return;
}
let user_id = "test_nested";
cleanup_user(&pool, user_id).await;
let workspace = Workspace::new(user_id, pool.clone());
// Write nested files
workspace
.write("projects/alpha/README.md", "# Alpha")
.await
.expect("Failed to write alpha");
workspace
.write("projects/alpha/notes.md", "Notes here")
.await
.expect("Failed to write notes");
workspace
.write("projects/beta/README.md", "# Beta")
.await
.expect("Failed to write beta");
// List root
let root = workspace.list("").await.expect("Failed to list root");
assert_eq!(root.len(), 1); // just "projects/"
assert!(root[0].is_directory);
assert_eq!(root[0].name(), "projects");
// List projects
let projects = workspace
.list("projects")
.await
.expect("Failed to list projects");
assert_eq!(projects.len(), 2); // alpha/, beta/
// List alpha
let alpha = workspace
.list("projects/alpha")
.await
.expect("Failed to list alpha");
assert_eq!(alpha.len(), 2); // README.md, notes.md
cleanup_user(&pool, user_id).await;
}
#[tokio::test]
async fn test_workspace_delete() {
let pool = get_pool();
if try_connect(&pool).await.is_none() {
return;
}
let user_id = "test_delete";
cleanup_user(&pool, user_id).await;
let workspace = Workspace::new(user_id, pool.clone());
// Write and verify exists
workspace
.write("temp.md", "temporary")
.await
.expect("Failed to write");
assert!(workspace.exists("temp.md").await.expect("exists failed"));
// Delete
workspace.delete("temp.md").await.expect("Failed to delete");
// Verify gone
assert!(!workspace.exists("temp.md").await.expect("exists failed"));
cleanup_user(&pool, user_id).await;
}
#[tokio::test]
async fn test_workspace_memory_operations() {
let pool = get_pool();
if try_connect(&pool).await.is_none() {
return;
}
let user_id = "test_memory_ops";
cleanup_user(&pool, user_id).await;
let workspace = Workspace::new(user_id, pool.clone());
// Append to memory
workspace
.append_memory("User prefers dark mode")
.await
.expect("Failed to append memory");
workspace
.append_memory("User's timezone is PST")
.await
.expect("Failed to append memory");
// Read memory
let memory = workspace.memory().await.expect("Failed to get memory");
assert!(memory.content.contains("dark mode"));
assert!(memory.content.contains("PST"));
// Entries should be separated by double newline
assert!(memory.content.contains("\n\n"));
cleanup_user(&pool, user_id).await;
}
#[tokio::test]
async fn test_workspace_daily_log() {
let pool = get_pool();
if try_connect(&pool).await.is_none() {
return;
}
let user_id = "test_daily_log";
cleanup_user(&pool, user_id).await;
let workspace = Workspace::new(user_id, pool.clone());
// Append to daily log (timestamped)
workspace
.append_daily_log("Started working on feature X")
.await
.expect("Failed to append daily log");
// Read today's log
let log = workspace
.today_log()
.await
.expect("Failed to get today log");
assert!(log.content.contains("feature X"));
// Should have timestamp prefix like [HH:MM:SS]
assert!(log.content.contains("["));
cleanup_user(&pool, user_id).await;
}
#[tokio::test]
async fn test_workspace_fts_search() {
let pool = get_pool();
if try_connect(&pool).await.is_none() {
return;
}
let user_id = "test_fts_search";
cleanup_user(&pool, user_id).await;
let workspace = Workspace::new(user_id, pool.clone());
// Write some documents
workspace
.write(
"docs/authentication.md",
"# Authentication\n\nThe system uses JWT tokens for authentication.",
)
.await
.expect("write failed");
workspace
.write(
"docs/database.md",
"# Database\n\nWe use PostgreSQL with pgvector for vector search.",
)
.await
.expect("write failed");
workspace
.write(
"docs/api.md",
"# API\n\nThe REST API uses JSON for request and response bodies.",
)
.await
.expect("write failed");
// Search for JWT (FTS only since no embeddings)
let results = workspace
.search_with_config("JWT authentication", SearchConfig::default().fts_only())
.await
.expect("search failed");
assert!(!results.is_empty(), "Should find results for JWT");
assert!(
results[0].content.contains("JWT"),
"Top result should contain JWT"
);
// Search for PostgreSQL
let results = workspace
.search_with_config("PostgreSQL database", SearchConfig::default().fts_only())
.await
.expect("search failed");
assert!(!results.is_empty(), "Should find results for PostgreSQL");
assert!(
results[0].content.contains("PostgreSQL"),
"Top result should contain PostgreSQL"
);
cleanup_user(&pool, user_id).await;
}
#[tokio::test]
async fn test_workspace_hybrid_search_with_mock_embeddings() {
let pool = get_pool();
if try_connect(&pool).await.is_none() {
return;
}
let user_id = "test_hybrid_search";
cleanup_user(&pool, user_id).await;
// Create workspace with mock embeddings (1536 dimensions to match OpenAI)
let embeddings = Arc::new(MockEmbeddings::new(1536));
let workspace = Workspace::new(user_id, pool.clone()).with_embeddings_uncached(embeddings);
// Write documents
workspace
.write(
"memory.md",
"The user prefers dark mode and vim keybindings.",
)
.await
.expect("write failed");
workspace
.write(
"prefs.md",
"Settings: theme=dark, editor=vim, font=monospace",
)
.await
.expect("write failed");
// Hybrid search
let results = workspace
.search("dark theme preference", 5)
.await
.expect("search failed");
assert!(!results.is_empty(), "Should find results");
// At least one result should be a hybrid match (found by both FTS and vector)
// or we should have results from either method
cleanup_user(&pool, user_id).await;
}
#[tokio::test]
async fn test_workspace_list_all() {
let pool = get_pool();
if try_connect(&pool).await.is_none() {
return;
}
let user_id = "test_list_all";
cleanup_user(&pool, user_id).await;
let workspace = Workspace::new(user_id, pool.clone());
// Write files at various depths
workspace.write("README.md", "root").await.unwrap();
workspace.write("docs/intro.md", "intro").await.unwrap();
workspace.write("docs/api/rest.md", "rest").await.unwrap();
workspace.write("src/main.md", "main").await.unwrap();
// List all
let all = workspace.list_all().await.expect("list_all failed");
assert_eq!(all.len(), 4);
assert!(all.contains(&"README.md".to_string()));
assert!(all.contains(&"docs/intro.md".to_string()));
assert!(all.contains(&"docs/api/rest.md".to_string()));
assert!(all.contains(&"src/main.md".to_string()));
cleanup_user(&pool, user_id).await;
}
#[tokio::test]
async fn test_workspace_system_prompt() {
let pool = get_pool();
if try_connect(&pool).await.is_none() {
return;
}
let user_id = "test_system_prompt";
cleanup_user(&pool, user_id).await;
let workspace = Workspace::new(user_id, pool.clone());
// Write identity files
workspace
.write(paths::AGENTS, "You are a helpful assistant.")
.await
.unwrap();
workspace
.write(paths::SOUL, "Be kind and thorough.")
.await
.unwrap();
workspace.write(paths::USER, "Name: Alice").await.unwrap();
// Get system prompt
let prompt = workspace
.system_prompt()
.await
.expect("system_prompt failed");
assert!(
prompt.contains("helpful assistant"),
"Should include AGENTS.md"
);
assert!(
prompt.contains("kind and thorough"),
"Should include SOUL.md"
);
assert!(prompt.contains("Alice"), "Should include USER.md");
cleanup_user(&pool, user_id).await;
}