Module constants

Expand description

Compile-time constants: embedding dimensions, limits and thresholds. Compile-time constants shared across the crate.

Grouped into embedding configuration, length and size limits, SQLite pragmas and retrieval tuning knobs. Values are taken from the PRD and must stay in sync with the migrations under migrations/.

§Dynamic concurrency permit calculation

The maximum number of simultaneous instances can be adjusted at runtime using the formula:

permits = min(cpus, available_memory_mb / EMBEDDING_LOAD_EXPECTED_RSS_MB) * 0.5

where available_memory_mb is obtained via sysinfo::System::available_memory() converted to MiB. The result is capped at MAX_CONCURRENT_CLI_INSTANCES and floored at 1.

Constants§

BATCH_PARTIAL_FAILURE_EXIT_CODE: Exit code for partial batch failure (PRD line 1822). Conflicts with DbBusy in v1.x; in v2.0.0 DbBusy migrates to 15 and this code takes 13 per PRD.
BUSY_TIMEOUT_MILLIS: PRAGMA busy_timeout value applied on every connection.
CACHE_SIZE_KB: PRAGMA cache_size value in kibibytes (negative means KiB).
CHUNK_OVERLAP_TOKENS: Token overlap between consecutive chunks.
CHUNK_SIZE_TOKENS: Chunk size expressed in tokens for body splitting.
CLI_LOCK_DEFAULT_WAIT_SECS: Maximum time in seconds an instance waits to acquire a concurrency slot.
CLI_LOCK_EXIT_CODE: Process exit code returned when the lock is busy and no wait was requested (EX_TEMPFAIL).
CLI_LOCK_FILE: Filename used for the advisory exclusive lock that prevents parallel invocations.
CLI_LOCK_POLL_INTERVAL_MS: Polling interval in milliseconds used by --wait-lock between try_lock_exclusive attempts.
CURRENT_SCHEMA_VERSION: Current schema version, equal to the highest migration number in migrations/Vnnn__*.sql.
DAEMON_AUTO_START_INITIAL_BACKOFF_MS: Initial polling interval to check whether the daemon became healthy.
DAEMON_AUTO_START_MAX_BACKOFF_MS: Ceiling on backoff between automatic daemon spawn attempts.
DAEMON_AUTO_START_MAX_WAIT_MS: Maximum wait time for the daemon to become healthy after auto-start.
DAEMON_IDLE_SHUTDOWN_SECS: Idle duration in seconds before the daemon shuts itself down.
DAEMON_PING_TIMEOUT_MS: Timeout in milliseconds for a single ping probe against the daemon socket.
DAEMON_SPAWN_BACKOFF_BASE_MS: Base backoff used after daemon spawn/health failures.
DAEMON_SPAWN_LOCK_WAIT_MS: Maximum wait time to acquire the daemon spawn lock.
DB_BUSY_EXIT_CODE: Exit code para DbBusy em v2.0.0 (migrado de 13 para liberar 13 para batch failure).
DEDUP_FUZZY_THRESHOLD: Jaccard threshold above which two memories are considered fuzzy duplicates.
DEDUP_SEMANTIC_THRESHOLD: Cosine distance threshold below which two memories are semantic duplicates.
DEFAULT_K_RECALL: Default k used by recall when the caller omits --k.
DEFAULT_MAX_HOPS: Default traversal depth for related when --hops is omitted.
DEFAULT_MIN_WEIGHT: Default minimum weight filter applied during graph traversal.
DEFAULT_RELATION_WEIGHT: Default weight assigned to newly created relationships.
EMBEDDING_DIM: Embedding vector dimensionality produced by multilingual-e5-small.
EMBEDDING_LOAD_EXPECTED_RSS_MB: Expected RSS in MiB for a single instance with the ONNX model loaded via fastembed.
EMBEDDING_MAX_TOKENS: Maximum tokens accepted by an embedding input before chunking.
FASTEMBED_BATCH_SIZE: Batch size for fastembed encoding calls.
FASTEMBED_MODEL_DEFAULT: Default fastembed model identifier used by remember and recall.
K_ENTITIES_SEARCH: Default k for entity KNN searches during graph expansion.
K_GRAPH_ENTITIES_DEFAULT_LIMIT: Default --limit para graph entities quando omitido.
K_GRAPH_MATCHES_LIMIT: Maximum result count from the recursive graph CTE in recall.
K_HISTORY_DEFAULT_LIMIT: Default --limit para history quando omitido.
K_LIST_DEFAULT_LIMIT: Default --limit para list quando omitido.
K_MEMORIES_DEFAULT: Default k for memory KNN searches when the caller omits --k.
K_RELATED_DEFAULT_LIMIT: Default --limit para related quando omitido.
LOW_MEMORY_EXIT_CODE: Process exit code returned when available memory is below MIN_AVAILABLE_MEMORY_MB.
MAX_BODY_CHARS_BEFORE_CHUNK: Body character count above which the body is split into chunks.
MAX_CONCURRENT_CLI_INSTANCES: Maximum number of CLI instances running simultaneously.
MAX_ENTITIES_PER_MEMORY: Upper bound on distinct entities persisted per memory.
MAX_GRAPH_HOPS: Maximum number of hops allowed in graph traversals.
MAX_MEMORY_BODY_LEN: Hard upper bound on memory body length in bytes.
MAX_MEMORY_DESCRIPTION_LEN: Maximum character length for a memory description field.
MAX_MEMORY_NAME_LEN: Maximum byte length for a memory name field in kebab-case.
MAX_NAMESPACES_ACTIVE: Maximum number of simultaneously active namespaces (deleted_at IS NULL). Exit 5 when exceeded.
MAX_RELATIONSHIPS_PER_MEMORY: Upper bound on distinct relationships persisted per memory.
MAX_SQLITE_BUSY_RETRIES: Maximum attempts when a statement returns SQLITE_BUSY.
MIN_AVAILABLE_MEMORY_MB: Minimum available memory in MiB required before starting model loading.
MIN_RELATION_WEIGHT: Minimum relationship weight required for traversal inclusion.
MMAP_SIZE_BYTES: PRAGMA mmap_size value in bytes applied to each connection.
NAME_SLUG_REGEX: PRD-canonical regex that validates names and namespaces. Allows 1 char [a-z0-9] OR a 2-80 char string starting with a letter and ending with a letter/digit, containing only [a-z0-9-]. Rejects the __ prefix (internal reserved).
OMP_NUM_THREADS_DEFAULT: Default value injected into OMP_NUM_THREADS when not set by the user.
ORT_INTRA_OP_NUM_THREADS_DEFAULT: Default value injected into ORT_INTRA_OP_NUM_THREADS when not set.
ORT_NUM_THREADS_DEFAULT: Default value injected into ORT_NUM_THREADS when not set by the user.
PASSAGE_PREFIX: Prefix prepended to bodies before embedding as required by E5 models.
PURGE_RETENTION_DAYS_DEFAULT: Default retention period (days) used by purge when --retention-days is omitted.
QUERY_PREFIX: Prefix prepended to queries before embedding as required by E5 models.
QUERY_TIMEOUT_MILLIS: Query timeout applied to statements in milliseconds.
REMEMBER_MAX_CONTROLLED_BATCH_CHUNKS: Ceiling on chunks per controlled micro-batch in remember.
REMEMBER_MAX_CONTROLLED_BATCH_PADDED_TOKENS: Maximum padded-token budget per controlled micro-batch in remember.
REMEMBER_MAX_SAFE_MULTI_CHUNKS: Explicit operational guard for multi-chunk documents in remember.
RRF_K_DEFAULT: Default k constant used by Reciprocal Rank Fusion in hybrid-search.
SCHEMA_USER_VERSION: Canonical value of PRAGMA user_version written after migrations.
SQLITE_BUSY_BASE_DELAY_MS: Base delay in milliseconds for the first SQLITE_BUSY retry.
SQLITE_GRAPHRAG_VERSION: Crate version string sourced from CARGO_PKG_VERSION at build time.
TEXT_BODY_PREVIEW_LEN: Character size of the body preview emitted in text/markdown formats.
TEXT_DESCRIPTION_PREVIEW_LEN: Character length of the description preview shown in list output.
WAL_AUTOCHECKPOINT_PAGES: PRAGMA wal_autocheckpoint threshold in pages.
WEIGHT_FTS_DEFAULT: Default weight for the BM25 text contribution in the hybrid-search RRF formula.
WEIGHT_VEC_DEFAULT: Default weight for the vector contribution in the hybrid-search RRF formula.

Functions§

max_relationships_per_memory: Resolves the per-memory relationship cap, honouring the env-var override.
ner_batch_size: Batch size for BERT NER forward passes.