Use for general or specialist questions that do not require a more specific Bee tool. Returns generated text from the selected domain and model tier. The gateway enforces the API key's plan, tenant policy, token allowance, and usage metering.

Use for code explanation, bug fixing, refactoring, or test generation. Returns text and proposed code; it does not read files, execute commands, or modify a repository. Choose the intended operation with action.

Use for defensive code audits, threat models, authorized penetration-test support, or smart-contract review. Returns analysis and remediation guidance only; it does not scan a target or execute exploits and refuses unauthorized weaponization.

Commission Smith for an evidence-first critical-systems assurance review of a customer-owned or explicitly authorized target. A Bee-operated run is internal automated assurance, not government certification or an external-independent audit.

Use to draft a NISQ-honest quantum-circuit design or critique an ML/CS paper. Returns research text or sample framework code; it does not submit QPU work. Use bee_quantum_reasoning_run for a durable hosted Lab job.

Use to verify a Bee agentic coding session by session_id. Returns verification status, sealed-turn count, and ML-DSA-65 (NIST FIPS 204) signature details; it does not alter or replay the session.

Use to inspect the authenticated caller's Bee plan and metered consumption. Returns pooled tokens, per-tier allowances, reset times, and a 24-hour or 7-day breakdown. It never changes billing, credits, or entitlements.

Use to retrieve relevant excerpts from the authenticated tenant's hosted Bee document library. Returns ranked chunks and source labels without changing the library; requires a RAG-entitled plan.

Use only when the user intends to persist supplied text in the authenticated tenant's hosted Bee knowledge base. Creates a searchable document and consumes the plan's document allowance; it does not read local files by itself.

Use to recall facts, preferences, projects, or skills from the authenticated user's Bee memory. Returns ranked memories without changing them and honors the user's memory setting and tenant policy.

Use only when the user intends Bee to persist a fact for future conversations. Writes to the authenticated user's memory, honors opt-in and tenant policy, and automatically suppresses near-duplicates.

Use only after the user chooses an eligible hosted quantum product. Creates a durable, tenant-encrypted, metered Quantum Reasoning Lab job that may incur simulator or QPU cost. Returns a job record; inspect it with bee_quantum_reasoning_get.

Use to list the authenticated tenant's retained Quantum Reasoning Lab jobs and capabilities. Returns paginated metadata without creating or changing jobs.

Use to inspect one tenant-scoped Lab job. Returns status, candidates, scores, result, QPU or fallback evidence, usage, and receipt ID without changing the job.

Use only after explicit user intent to cancel an eligible queued job or permanently erase content from a terminal job. This is a destructive, tenant-scoped operation.

Use to validate a real Bee computer-use host capability report and optional governed action request at the hosted gateway. This tool does not observe a screen, control input, automate a device, or create a local driver; execution must happen in a verified host runtime with explicit capability evidence.