Executes an agent using its currently deployed revision.

A dictionary of input parameters for the agent execution. Keys correspond to parameter names defined in the agent's entry point flow step.

A list of file attachments included with the execution request. These are files sent by the user (e.g., via a connector) that the agent can access during execution.

P0-3 — inbound media references stamped at the webhook without downloading the bytes there. The worker resolves these into Fruxon.Model.Agents.AgentExecutionRequest.Attachments (and weaves their prompt-links into the Fruxon.Model.Agents.AgentExecutionRequest.UserQueryParameter) just before execution, off the inbound hot path. Empty for the eager path and for non-chat runs. See Fruxon.Model.Storage.DeferredAttachment and the worker's DeferredMediaResolver.

P0-3 — the raw message text the rendered Fruxon.Model.Agents.AgentExecutionRequest.UserQueryParameter ends with when this request carries Fruxon.Model.Agents.AgentExecutionRequest.DeferredAttachments (links not yet appended). The worker uses it to splice resolved attachment prompt-links into the query exactly where the eager path would have. Null unless attachments were deferred. See InboundAttachmentPrompt.AppendResolvedLinks.

An optional session ID for maintaining execution context across requests. When provided, the agent can resume a previous conversation session.

The resolved participant id for this run's inbound venue, lifted from the task's ParticipantContext metadata by Fruxon.Model.Agents.AgentExecutionService.ExecuteFromQueueAsync and threaded onto Fruxon.Model.Agents.AgentContext.ParticipantId. The venue-precedence winner (the group in a group, the person in a DM). Null on non-queue paths (sync API / test, scheduler) and inbound from senders that matched no participant. See docs/design/identity-profile-normalization.md §6.4.

§15.3 — the individual sender's participant id (distinct from Fruxon.Model.Agents.AgentExecutionRequest.ParticipantId, the venue, in a group), threaded onto Fruxon.Model.Agents.AgentContext.SenderParticipantId. Null when the sender isn't a known participant. Drives "who am I talking to" / memory subject, never routing.

Network operating boundary selected for this run. I1 resolves the tenant's Default Network at the execution choke point and carries it through queued/resumed requests; later routing may supply a non-default network. Nullable for legacy queue payloads during the dual-read window.

Stable conversational deployment principal selected for this run. When present it must identify a membership of the requested Agent in Fruxon.Model.Agents.AgentExecutionRequest.NetworkId; the execution choke point validates that tuple before building or retrieving an Application-dependent plan.

The runnable binding that scheduled this execution — for a collection pipeline it is the pipeline id (the pipeline is the shipped runnable binding, build-plan artifact B). Part of the §10 RunnableExecutionContext; null for conversational/ad-hoc runs, which resolve via an Agent membership instead.

Identifies the environment this execution targets. Enables per-environment cost tracking, quota enforcement, and analytics. For system agents, this is automatically set to the calling tenant's slug.

Selects which integration-config variant an execution uses. Sandbox falls back to production per-config when no sandbox variant is configured. Callers normally send PRODUCTION or SANDBOX; UNSPECIFIED is the zero value and exists only so the field can be omitted on the wire without misrepresenting the user's intent — the host DTO supplies the real default (typically PRODUCTION).

Provider-reported receipt time of the inbound message (Unix ms), the customer's actual send time — set by M:Fruxon.Model.Agents.AgentExecutionRequest.CreateForInboundMessage(Fruxon.Model.Messaging.Dispatch.InboundMessage,System.String) from InboundMessage.Date and threaded onto Fruxon.Model.Agents.AgentContext.OccurredAt so the persisted inbound userFruxon.Model.AgentSessions.AgentMessage.OccurredAt carries the real event time rather than the batch persist time. Null for non-chat runs (API, subtask, scheduler) and when the provider reported no timestamp. Survives the queued-payload round-trip.

How the agent appears on the channel this run originated from — the provider bot handle (e.g. "@daria_bot"). Set by the inbound receivers from the integration config's Fruxon.Model.Integrations.Configs.BotIdentity; surfaced to the model via Fruxon.Model.Agents.AgentContext.ChannelHandle in the identity preamble. Null for non-channel runs (API, test chat, triggers).

When this run was spawned as a sub-task (e.g. spawn_subtask), the spawning run's execution-record id. Carried on the queued request so the child's execution record can be stamped with it when the worker eventually runs it, connecting the two traces. Null for top-level runs. See Fruxon.Model.ExecutionTraces.AgentExecutionRecord.ParentExecutionRecordId.

The parent run's async-operation id this sub-task satisfies (pins the exact spawning call). Null for top-level runs.

Top-level ancestor of this run's spawn tree (the parent's root, or the parent's own id for a first-level child). Null for top-level runs (the record then roots itself).

Reversibility classification of a tool's side effects. Wire form is UPPER_SNAKE per project convention; Unspecified = 0 is the AIP-126 zero-sentinel.

Optional pinned agent revision to run (the IRunnable binding's (AgentId, Revision)): when set, the queue execution runs this exact revision instead of resolving the agent's current one. Set by collection-pipeline fan-out so every item in a run executes the same revision — pinned at run start (design §10.8, "a pipeline pins the whole batch run to one release"); null for ordinary runs, which keep resolving the current revision. Survives the queue payload round-trip so a suspended item resumes on the same revision.