ReadonlyIsObservable indicating if the ambient agent is currently processing — delegated to the runtime's AgentRunner.
Synchronous read of the cached conversation-manager-agent name. Returns
null until getConversationManagerAgent has been called at least
once and resolved successfully. Used by MessageItemComponent.isConversationManager
to flag messages from the routing agent without hardcoding 'Sage'.
Use IsProcessing$.
The metadata provider this service uses. When unset, falls back to Metadata.Provider. Setting it re-initializes the AI client and forwards the provider to the runtime's runner.
OptionalbranchId: string | nullCheck if user's latest message should continue with the previous agent or route through Sage. Uses fast inference (<500ms) to determine intent and avoid unnecessary Sage overhead.
Stays on the Angular shim because it directly uses GraphQLAIClient. Could move to the runtime in a follow-up.
OptionalbranchId: string | nullThe active branch. Only the agent's artifacts on its path are listed for the classifier; null or omitted reads the trunk.
Clear the session for a conversation (useful when starting a new topic)
Every artifact this agent produced on the active branch path, newest version first, for decision routing's artifact question. Resolved by query, as findAllAgentArtifacts explains.
OptionalhistoryFrom: Date | nullThe chat's history floor. When set, only artifacts on replies written at or after it count, as with FindLatestAgentOutputVersion.
OptionalbranchId: string | nullThe active branch. Only artifacts on its path count, as with FindLatestAgentOutputVersion; null or omitted reads the trunk.
One artifact version by ID, as a payload source.
Used by the continuity path after the intent check names a specific version: that ID may belong to a message below the loaded window, so it cannot be resolved from the window's artifact maps.
Configuration preset an agent was pinned to by a previous @mention in this conversation.
Resolved by QUERY, not by scanning the display array. The pinning @mention is normally
the FIRST message of an exchange and everything after it is follow-up, so it is the
message most likely to fall below the loaded transcript window — and undefined is a
legal value for configurationPresetId, so the miss is silent. The visible consequence
is a run executed under the default configuration (a different model tier) instead of the
one the user explicitly chose, with a plausible-looking result and no error.
There is no column to filter on: the preset lives inside the message body as a JSON
mention blob (@{"type":"agent","id":"…","configId":"…"}). So SQL narrows and the parser
decides — both configId and the agent id appear verbatim in that blob, which makes the
two LIKEs a tight prefilter, and parseMentions is what actually confirms a match.
OptionalbranchId: string | nullThe active branch. Only messages on its path count; null or omitted reads the trunk.
Newest OUTPUT artifact version an agent produced in this conversation — resolved by QUERY, not by scanning the display array.
The array scan this replaces was correct only while conversationHistory held the whole
conversation. Under transcript windowing it holds one page, so the scan silently returns
null for any artifact below the window's oldest row — exactly the long "modify this
again" exchanges where payload continuity matters most. A null payload is a LEGAL agent
input, so the failure is silent: the agent regenerates from scratch instead of modifying.
Two reads: the agent's replies, then their newest Output version. Versions carry
__mj_CreatedAt, so "newest" is expressible without joining back for Sequence.
OptionalhistoryFrom: Date | nullThe chat's history floor. When set, only artifacts on replies written at or after it count: a run that may not read earlier messages must not pick up their work as its payload either.
OptionalbranchId: string | nullThe active branch. Only replies on its path count, so an artifact made on another branch is never the latest here; null or omitted reads the trunk.
Resolve the conversation manager agent via the runtime's 4-step DefaultAgentResolver chain (explicit input → app-scoped Application Setting → global Application Setting → code-const Sage fallback). The result is cached on this service for use by the synchronous ConversationManagerAgentName getter.
Existing callers expect a Promise<MJAIAgentEntityExtended | null> — we preserve that shape (returning null on failure rather than throwing) so the call sites don't need to change.
Optionalpayload: Record<string, unknown> | nullOptionalonProgress: AgentExecutionProgressCallbackOptionalsourceArtifactId: stringOptionalsourceArtifactVersionId: stringOptionalagentConfigurationPresetId: stringOptionalappContext: Record<string, unknown> | nullOptionalplanMode: booleanOptionalrequestedSkillIDs: string[]OptionalagentHistoryFrom: Date | nullUse InvokeSubAgent.
Invoke a sub-agent based on Sage Agent's payload. This is called when Sage decides to delegate to a specialist agent.
Stays on the Angular shim because it directly uses AgentClientService. Could move to the runtime in a follow-up if needed.
Optionalpayload: Record<string, unknown> | nullOptionalonProgress: AgentExecutionProgressCallbackOptionalsourceArtifactId: stringOptionalsourceArtifactVersionId: stringOptionalagentConfigurationPresetId: stringOptionalappContext: Record<string, unknown> | nullOptionalplanMode: booleanOptionalrequestedSkillIDs: string[]OptionalagentHistoryFrom: Date | nullThe first moment of the conversation the run may read. Null or omitted reads all of it.
Returns true if the supplied agent identifier (UUID or name) matches the
currently cached conversation manager agent. Robust to either input.
OptionalonProgress: AgentExecutionProgressCallbackOptionalappContext: Record<string, unknown> | nullOptionalplanMode: booleanOptionalrequestedSkillIDs: string[]OptionalallowedAgentIDs: readonly string[] | nullOptionalagentHistoryFrom: Date | nullUse ProcessMessage.
Process a message through the conversation manager agent. Delegates to
ConversationsRuntime.Instance.AgentRunner.processMessage(...).
Signature is preserved verbatim from the original service so existing
call sites continue to compile. The unused conversationHistory
parameter is kept for backwards compatibility (it was already
documented as "kept for backwards compatibility but not used" in the
original).
OptionalonProgress: AgentExecutionProgressCallbackOptionalappContext: Record<string, unknown> | nullOptionalplanMode: booleanOptionalrequestedSkillIDs: string[]OptionalallowedAgentIDs: readonly string[] | nullThe agents the conversation manager may delegate to. Null or omitted allows every agent.
OptionalagentHistoryFrom: Date | nullThe first moment of the conversation the run may read. Null or omitted reads all of it.
Runs a typed decision on the server in one round trip, through
GraphQLAIClient.RunDecision. Decision routing (EnableDecisionRouting) asks its
routing questions here.
Never throws: without an AI client, or on any failure, it resolves with Success: false and
no answers.
Angular DI service for conversation-level agent orchestration.
After PR 2 of the conversations-runtime extraction, the core
processMessageflow and the conversation-manager-agent resolution are delegated to@memberjunction/conversations-runtime. This service is primarily a shim for those operations PLUS the holder of the helpers that haven't been ported yet:invokeSubAgent(...)— used by Sage's routing decisions inmessage-input.component.checkAgentContinuityIntent(...)— fast intent classification when the user replies to a previous-agent thread.FindConfigurationPresetForAgent(...)— locates an agent's preset from priorMentions
in the conversation.
clearSession(...)— per-conversation session-id bookkeeping.These can move to the runtime in a follow-up; they aren't strictly needed to invoke an agent end-to-end and stay here so the shim has zero behavior difference vs. the original.