3936258146
* Implement Weaver AI Copilot core * Address Greptile review feedback * Address Greptile persistence feedback * Address Greptile orchestration feedback * Address Greptile tool isolation feedback * Wire chat audit events * Stream chat events over SSE * Use server identity for AI endpoints * Validate AI proposal persistence * Isolate AI audit failures * Enforce AI tool lookup scope * Support AI tool result continuations * Handle AI chat reconnects safely * Tighten AI context and reconnect behavior * Guard AI conversation and persistence setup * Persist AI tool-loop progress * Tighten AI tool registry and reconnect cleanup * Handle AI preparation failures cleanly * Order AI tool messages after assistant turns * Initialize AI provider sessions * Align AI context capabilities * Prevent completed AI reconnect replay * Enforce AI conversation ownership * Default AI proposal creation time * Persist AI session and retention defaults * Allow AI context provider overrides * Scope AI tool results per turn * Apply AI provider configuration * Scope AI proposal reads * Avoid duplicate AI tool continuations * Resolve AI tool registry scopes * Tighten AI reconnect cleanup * Honor default AI proposal tools * Pass AI provider session to turns * Close AI observability gaps * Fix AI capabilities options alias * Harden AI orchestration lifetimes * Track actual AI reconnect conversation * Address AI audit and context review findings * Fix AI reconnect and persistence capabilities * Handle AI session startup failures * Tighten AI orchestration review gaps * Warn on placeholder AI context * Filter disabled AI provider tools * Add durable AI conversation persistence * Fix AI orchestrator persistence lifetime * Handle failed AI reconnect edge cases * Harden AI reconnect failure handling * Address AI reconnect and cleanup review gaps * Tighten AI audit and cleanup persistence * Keep expired AI cleanup best effort * Tighten AI tool lookup and cleanup fallback * Handle AI provider and tenant edge cases * Tighten AI proposal and agent authorization * Address AI tool scope cleanup review * Close remaining AI greptile findings * Harden AI stores and tool defaults * Harden AI conversation persistence edge cases * Cover AI proposal and tool visibility guards * Fix AI capabilities and audit batch resilience * Fix AI conversation truncation for unicode * Resolve remaining AI persistence review nits * Wire AI conversation persistence option * Address AI audit and proposal style review * Fix AI stream truncation surrogate handling * Address AI context and cleanup review * Preserve AI titles and tenant tool defaults * Guard AI conversation user ownership * Align in-memory AI conversation ownership * Fix expired AI conversation cleanup tracking * Harden AI proposal persistence retry * Tighten AI proposal reads and cleanup SQL * Harden AI reconnect and provider defaults * Optimize AI tool listing and message trimming * Preserve AI conversation timestamps * Address final AI persistence review nits * Normalize AI acronym casing * Address Copilot AI review comments * Normalize default tenant handling for AI stores * Harden AI registry and message truncation * Make AI tool filtering explicit * Align AI contracts with implementation * Align remaining AI review contracts * address greptile ai persistence feedback * Address Copilot AI persistence feedback * Address Copilot AI host feedback * Order persisted AI conversation messages * Address Copilot chat and cleanup feedback * Release unused AI reconnect reservations * Address Copilot AI review feedback * Address Copilot tool and conversation feedback * Address Copilot governance feedback * Address Copilot tool test feedback * Address AI review follow-ups * Address Copilot AI follow-ups * Clean up AI persistence tests * Address IAITool disposal review * Address AI integration review follow-ups * Address AI chat persistence review * Address AI registry and truncation review * Enable read-only AI tools by default * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
4.5 KiB
Data Model: Weaver AI Copilot Platform
AIConversation
Represents a Weaver chat thread visible to a user.
Fields: Id, TenantId, UserId, Title, Status, CreatedAt, UpdatedAt, ProviderSessionId, RetentionMode, RetentionExpiresAt.
Relationships: Has many AIMessage, AIContextAttachment, AIToolInvocation, and AIAuditEvent records.
Rules:
- Conversation access is tenant- and actor-scoped.
- Provider session IDs are internal server metadata and never exposed as provider objects.
- Retention policy controls conversation history visibility, durability, and cleanup.
AIMessage
Represents user, assistant, system, or tool-visible content in a conversation.
Fields: Id, ConversationId, Role, Content, CreatedAt, StreamSequence, Metadata.
Rules:
- Stored content must already be redacted.
- Tool result details may be summarized for model context and preserved separately for display when safe.
AIContextAttachment
Represents a client-supplied reference to server-resolved context.
Fields: Id, ConversationId, Kind, ReferenceId, TenantId, Scope, TimeRange, ActivityId, Metadata.
Supported Kinds: WorkflowDefinition, WorkflowInstance, ActivitySelection, Tenant, DiagnosticsScope, TimeRange.
Rules:
- Studio sends references only.
- Server resolves attachments per request and validates authorization before use.
- Context resolution applies size limits and redaction.
AIToolDefinition
Represents a registered Weaver tool.
Fields: Name, DisplayName, Description, Schema, Mutability, DangerLevel, Permissions, TenantBehavior, AuditBehavior, AgentScopes, Provider, EnabledByDefault, IsEnabled.
Rules:
- Tool names are stable and namespaced, such as
workflow.getDefinition. - Mutating tools are either proposal-only or administrative; administrative tools are out of MVP scope.
- Tool metadata is validated during registration.
- Read-only module tools may be enabled by default; proposal, administrative, and MCP-backed tools require explicit administrator enablement.
AIToolInvocation
Represents a single attempted tool execution.
Fields: Id, ConversationId, ToolName, Arguments, AuthorizationResult, StartedAt, CompletedAt, Status, ResultSummary, Error, TraceId, TenantId, ActorId.
Rules:
- Authorization is checked before execution.
- Arguments and results are redacted before audit and stream output.
- Failed and denied invocations are audited.
AIProposal
Represents a reviewable AI-generated workflow creation or update.
Fields: Id, TenantId, ConversationId, Kind, Status, BaselineWorkflowDefinitionId, BaselineVersionId, WorkflowPayload, Rationale, Warnings, ValidationDiagnostics, GraphDiff, CreatedBy, CreatedAt, ReviewedBy, ReviewedAt, AppliedBy, AppliedAt.
States: Draft, Validated, Blocked, Approved, Rejected, Applied, Expired.
Rules:
- Proposals are the only AI path to workflow writes.
- Apply requires approval, authorization, validation pass, and baseline match.
- The same authorized user may create, approve, reject, and apply a proposal in MVP.
- Proposals are durable governance artifacts.
- Proposal payloads are structured workflow definitions or patches, not free-form text.
AIAuditEvent
Represents durable governance evidence.
Fields: Id, TenantId, ActorId, ConversationId, ProposalId, ToolInvocationId, Type, Timestamp, TraceId, Summary, Data.
Rules:
- Audit data is redacted.
- Prompt, context resolution, tool call, denial, proposal, approval, rejection, and apply events are recorded.
AIAgentDefinition
Represents a named Weaver agent contributed by Core or a module.
Fields: Name, DisplayName, Description, Instructions, AllowedTools, AllowedContextProviders, AllowedMcpServers, Permissions, Enabled.
Rules:
- Agents operate with least-privilege tool and context scopes.
- Agent instructions cannot grant permissions or bypass server enforcement.
AIMcpServerRegistration
Represents a governed external tool server registration.
Fields: Name, Transport, Endpoint, ToolAllowlist, AgentScopes, Permissions, TenantBehavior, AuditBehavior, Enabled.
Rules:
- Only allowlisted MCP tools are exposed.
- Local and remote servers are configured server-side.
- Per-agent scoping is mandatory.
- MCP-backed tools require explicit administrator enablement before use.