tinyhumansai/openhuman · error

memory_vector_search: load config failed: {e}

Error message

memory_vector_search: load config failed: {e}

What it means

The vector search tool could not load the core TOML config via `config_rpc::load_config_with_timeout()` before querying memory. Every search needs config to resolve the workspace and memory settings, so a config load timeout or parse failure aborts the tool here. `{e}` carries the underlying config error (timeout, unreadable file, or invalid TOML).

Source

Thrown at src/openhuman/memory/tools/search/vector_search.rs:123

            ));
        }

        let limit = parsed.limit.clamp(1, 50);
        let min_score = parsed.min_score.unwrap_or(0.3);

        log::debug!(
            "[tool][memory_vector_search] query_len={} source_kind={:?} window={:?} min_score={} limit={} diverse={}",
            parsed.query.len(),
            parsed.source_kind,
            parsed.time_window_days,
            min_score,
            limit,
            parsed.diverse,
        );

        let config = config_rpc::load_config_with_timeout()
            .await
            .map_err(|e| anyhow::anyhow!("memory_vector_search: load config failed: {e}"))?;

        // Chunks are read through the bound driver, not by opening the store
        // in this process. Before the module port this called
        // `list_chunks(&config, …)` directly, which resolved the workspace path
        // and opened the same SQLite database the loaded module already had
        // open — two engine instances over one file, with the module not
        // authoritative. See `docs/specs/2026-08-13-memory-module-port.md` §2.1.
        let guard = active_memory_guard()
            .await
            .map_err(|e| anyhow::anyhow!("memory_vector_search: {e}"))?;
        let chunk_reader = guard.as_chunks().ok_or_else(|| {
            anyhow::anyhow!("memory_vector_search: memory driver does not support the chunk family")
        })?;

        let embedder = provider_from_config(&config)
            .map_err(|e| anyhow::anyhow!("memory_vector_search: embedding provider failed: {e}"))?;

        let query_vec = embedder

View on GitHub (pinned to 7491200858)

Solutions

1. Retry — the loader is timeout-bounded and transient contention can cause this
2. Check that the workspace config.toml exists and parses
3. Look at `{e}` to distinguish timeout from parse failure
4. Verify the workspace/config paths the harness or shell passed at startup

When it happens

Trigger: Thrown at src/openhuman/memory/tools/search/vector_search.rs:123 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of tinyhumansai/openhuman@7491200858 (2026-08-17). Data as JSON: /api/errors/4049ca0517eb217f. Report an issue: GitHub.