Query project documents, parsed business files, and shared context. Use this first for source truth and narrative documentation. Returns a source-grounded answer_pack plus retrieval_diagnostics and ranked sections within token budget. If a broad query times out, retry once with a narrow 3-8 term query, max_tokens 800-1500, search_mode='keyword', return_references=true, auto_decompose=false, and include_all_tiers=false. For exact text use snipara_search; for structural code context use snipara_code_neighbors, snipara_code_callers, or snipara_code_imports.

Answer one simple question from indexed project documentation with server-side synthesis. This is a read-only VIEWER operation and changes no project state. Use snipara_context_query when citations, answer packs, retrieval controls, or source sections matter; use snipara_search for an exact regex. Returns a concise answer or a bounded no-match/error result.

Search indexed project documentation with an exact regular expression. This is a read-only VIEWER operation and changes no project state. Use it for identifiers, paths, or literal wording; use snipara_context_query for semantic source retrieval and snipara_read after locating a relevant range. Returns capped matches with document and line context, or a validation/no-match result.

Read an exact line range from indexed project documentation. This is a read-only VIEWER operation and changes no project state. Use it after snipara_search or snipara_context_query when exact wording matters; use snipara_get_chunk instead when you already have a cited chunk ID. Returns the resolved range and text, or a validation/not-found error.

Read compact project documentation and retrieval statistics without changing project state. File samples and database-backed index health are opt-in to keep the response small. Use snipara_index_health for operational diagnosis rather than this overview. Returns counts, token/index summaries, and only the optional sections requested.

Discover the correct Snipara tool without executing that tool or changing project state. Use query for ranked recommendations, tool for one detailed contract, tier for a bounded category, or list_all for the deterministic catalog including specialists hidden from tools/list. Returns selection guidance, examples, access requirements, surface metadata, and related tools.

Store one durable Memory V2 record only when it is sufficiently different from existing reviewed memory. This EDITOR operation may write project, team, user, or agent state; duplicate calls normally skip the write, while auto_safe reconciliation may supersede high-confidence same-owner matches without deleting them. Use snipara_end_of_task_commit for multi-outcome workflow capture and context tools for source documents. Returns whether storage occurred, duplicate evidence, the memory ID, and reconciliation actions.

Persist a bounded end-of-task summary, optional structured Why Capture, and selected durable outcomes so another agent can resume the work. This EDITOR operation writes memory and workflow state and is non-idempotent; dry_run validates without writing. Use snipara_remember_if_novel for one reusable memory and document upload tools for source material. Unknown fields fail closed. Returns created or skipped records, review candidates, handoff metadata, and validation warnings.

Semantically recall durable Memory V2 decisions, learnings, preferences, and session carryover within the requested owner boundary. This is a read-only VIEWER operation and changes no memory authority. Use snipara_context_query for source documents and snipara_memories for lifecycle inventory. Returns ranked active memories, optional inactive warnings, authority metadata, and bounded retrieval diagnostics.

Fetch one complete indexed source chunk by the stable chunk ID returned from a reference-based context query. This is a read-only VIEWER operation and changes no project state. Use snipara_context_query first to discover relevant references; use snipara_read for an exact document line range instead. Returns the chunk text, source identity, position metadata, and a bounded not-found/error result.

List human-reviewable memory candidates and ProjectDecision drafts from the current user's team Dashboard Inbox. This is a read-only ADMIN operation and changes no authority or review state; credential-like material is redacted. Use snipara_inbox_review_plan to validate recommendations before any authorized mutation. Returns stable item IDs, project ownership, evidence, and current review status.

Validate evidence-backed recommendations for team Inbox memory candidates and ProjectDecision drafts without changing authority. This read-only ADMIN operation creates a snapshot-bound review_plan_id; approve/reject items enter the snapshot while needs_human items remain pending. Use snipara_inbox_review_queue first and never call apply without explicit human authorization. Returns the immutable plan, exclusions, and validation findings.

Atomically apply the exact memory-candidate and decision-draft actions from a prior team Inbox review plan. This destructive ADMIN operation requires explicit user authorization plus a real human team-admin identity, records authority audits, and fails closed if any item or snapshot changed. It is not idempotent and must follow snipara_inbox_review_plan. Returns per-item outcomes and the atomic apply receipt.