> ## Documentation Index > Fetch the complete documentation index at: https://docs.lilfella.app/llms.txt > Use this file to discover all available pages before exploring further. # Limitations > Current boundaries for correctness, formats, scale, security, and platforms. # Know what Fella does not promise Fella is an early, pre-1.0 personal analytics app. Its narrow scope makes the normal path inspectable, but it does not remove model, data, or operating-system risk. ## Correctness and evidence | Limit | Practical consequence | | --------------------------------------------- | -------------------------------------------------------------------------------------------- | | Not every response uses a tool | General answers can have no working fold or workspace evidence | | Verification is deterministic, not omniscient | It catches replay, grounding, and known query-shape problems, not every wrong interpretation | | Grounded can still be wrong | A valid query may use the wrong filter, join, unit, date boundary, or denominator | | Refusal is model-dependent | A model may forecast or infer when files do not support the answer | | Evidence is sampled/capped | Inspect the query and row counts, not only visible sample rows | For consequential decisions, validate the source and query independently. Fella is not a substitute for professional financial, medical, legal, or safety advice. ## Data and formats * Shipped builds support delimited/JSON tables, Excel workbooks, and text-layer documents listed in [Getting started](/getting-started#what-the-shipped-app-can-use). * There is no OCR. Image-only PDFs and standalone images are not readable data. * Word, OpenDocument, email, HTML, XML, archive, media, and database files are not supported inputs. * JSON must be table-shaped enough to ingest; arbitrary deeply nested documents may not become useful columns. * Excel formulas are not recalculated by Fella; workbook parsing depends on stored values the parser can read. * Parquet requires the optional DuckDB backend. DuckDB is not part of published installers or CI and has known ingestion-parity gaps relative to SQLite. ## Scale and output | Guardrail | Default | | ------------------------- | -------------------------------------------------------------------------------------------------------: | | Workspace scan depth | 8 levels | | Delimited-file ingest cap | 2,000,000 rows per file | | SQL result cap | 1,000 rows | | SQL timeout | 15 seconds | | Python execution budget | 1 billion Wasmi fuel; host SQL keeps its 15-second watchdog | | Chart size | Category charts are bounded; time-series charts can cover longer periods, with output and rendering caps | Fella targets MB-scale personal folders and everyday lookups, aggregates, comparisons, and small joins. It is not a warehouse, distributed query engine, notebook, ETL system, or multi-user server. ## Security boundaries ### Base file and SQL tools The model has no built-in write, move, copy, or delete tool. Document reads resolve through the workspace catalog, and SQLite queries use a read-only connection plus a single-statement guard. ### Python Python runs without a per-call permission prompt inside an embedded `wasm32-unknown-unknown` RustPython guest under Wasmi. It has no filesystem, network, environment, or subprocess capability. The host provides captured output and bounded read-only SQL, and applies fuel, memory, stack, source, output, row, and response limits. The guest contains the core language and Fella's small analytics helpers; it does not contain pandas, NumPy, SciPy, or a package installer. ### Context The user may edit `fella.md` in the Workspace surface. This is a human-driven write path, not an agent tool. The agent can read the file as context, but it cannot create or modify it. ### Experimental MCP `/mcp` is inert in the personal release. The default build has no MCP client, connector authentication, dynamic tools, or outbound connector path. A fork that adds a connector must review its permissions and network behavior separately. ## Privacy and network activity * Fella is BYOK-only: the provider you connect receives prompts and tool results for each question. * `/update` contacts GitHub and downloads an installer only when the user invokes it. * `/mcp` introduces no network activity. The embedded Python guest has no network capability. * Fella does not proxy hosted model requests through a Fella service, but cannot control a provider's logging, retention, or training policy. ## Releases and platforms Published builds are currently unsigned, so macOS and Windows can show unknown-developer warnings. Integrity depends on HTTPS and `SHA256SUMS`, not code signing or notarization. macOS requires 10.15+, Windows requires 10+, and Linux requires WebKitGTK 4.1. Release automation builds macOS universal plus Windows and Linux artifacts on GitHub-hosted runners, but every apply/update path has not been manually exercised on every OS. ## Experimental compatibility boundary The pack and connector designs are archived in the repository for future forks. They are not part of the default runtime. See [Experimental MCP](/extensions-and-mcp) for the exact inert command and reopening criteria. ## Benchmarks Published scores are dated measurements on fixed synthetic batteries, providers, models, prompts, and grading code. They do not predict correctness for your folder. The 2026-09-10 64-case comparison and 2026-09-12 16-case hard run should be rerun after material harness, fixture, model, or endpoint changes. ## Next steps Use bounded recipes and inspect the resulting queries. Learn what deterministic tests and live model evaluations each establish.