tinyhumansai/openhuman · error

invalid arguments for memory_vector_search: {e}

Error message

invalid arguments for memory_vector_search: {e}

What it means

The `memory_vector_search` arguments failed serde deserialization into the tool's typed `Args` struct. The schema is descriptive, not enforced by JSON Schema itself — the Rust parse is the real gate — so this fires on wrong types (query not a string, limit outside 1–50 declared bounds at the type level, min_score not a number) or unexpected fields, with `{e}` naming the exact mismatch.

Source

Thrown at src/openhuman/memory/tools/search/vector_search.rs:100

                    "description": "Minimum cosine similarity threshold (default 0.3)."
                },
                "limit": {
                    "type": "integer",
                    "minimum": 1,
                    "maximum": 50,
                    "description": "Max results to return (default 10)."
                },
                "diverse": {
                    "type": "boolean",
                    "description": "Apply MMR diversity to reduce redundancy among results (default false)."
                }
            }
        })
    }

    async fn execute(&self, args: serde_json::Value) -> anyhow::Result<ToolResult> {
        let parsed: Args = serde_json::from_value(args)
            .map_err(|e| anyhow::anyhow!("invalid arguments for memory_vector_search: {e}"))?;

        if parsed.query.trim().is_empty() {
            return Err(anyhow::anyhow!(
                "memory_vector_search: query cannot be empty"
            ));
        }

        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,

View on GitHub (pinned to 7491200858)

Solutions

1. Match every argument's type to the schema: query as string, limit as integer 1–50, min_score as number, diverse as boolean
2. Read the serde error `{e}` — it names the field and the expected type
3. Drop unknown fields not present in the schema

When it happens

Trigger: Thrown at src/openhuman/memory/tools/search/vector_search.rs:100 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/8cca5ca84060517b. Report an issue: GitHub.