Glossary
Section ID: Glossary/u2rmmllhvi#glossary
Terms
Section ID: Glossary/u2rmmllhvi#terms
Agent profile
Section ID: Glossary/u2rmmllhvi#agent-profile
A reusable persona with model configuration, tools and metadata describing when it should be used.
Read the canonical explanation.
Allocation
Section ID: Glossary/u2rmmllhvi#allocation
A modeled share of compute, storage, idle capacity or shared services assigned to a project or customer; it answers a different question from provider-reported usage, an estimate or a customer charge.
Read the canonical explanation.
Annotation queue
Section ID: Glossary/u2rmmllhvi#annotation-queue
A named work queue assigning score configurations to human annotation items.
Read the canonical explanation.
Callback
Section ID: Glossary/u2rmmllhvi#callback
The request a scheduled job’s firing sends to its receiver: the configured body plus a signed identity token whose signature does not bind that body, so the receiver validates the payload against the registered schedule and acknowledges only after durable acceptance.
Read the canonical explanation.
Client tool result
Section ID: Glossary/u2rmmllhvi#client-tool-result
The result the caller submits for a tool call executed on the client side.
Read the canonical explanation.
Compaction
Section ID: Glossary/u2rmmllhvi#compaction
The recorded reduction of a conversation’s retained context, described by compaction metadata.
Read the canonical explanation.
Connected account
Section ID: Glossary/u2rmmllhvi#connected-account
An external user’s OAuth connection to an app.
Read the canonical explanation.
Conversation history
Section ID: Glossary/u2rmmllhvi#conversation-history
The stored messages of a conversation, from which the context management strategy selects or summarizes what the model sees.
Read the canonical explanation.
Conversation state
Section ID: Glossary/u2rmmllhvi#conversation-state
The bounded read of a conversation used to retrieve a reply after an asynchronous send; it cannot correlate every queued or concurrent operation.
Read the canonical explanation.
Conversation thread
Section ID: Glossary/u2rmmllhvi#conversation-thread
The registry record for one conversation, kept so a user’s threads can be listed and managed together.
Read the canonical explanation.
Dataset
Section ID: Glossary/u2rmmllhvi#dataset
An evaluation dataset: its metadata, item counts, run history and input/output schemas.
Read the canonical explanation.
Dataset item
Section ID: Glossary/u2rmmllhvi#dataset-item
One evaluation input with its expected output and source trace references.
Read the canonical explanation.
Dataset run
Section ID: Glossary/u2rmmllhvi#dataset-run
One execution of an evaluation dataset.
Read the canonical explanation.
Delivery attempt
Section ID: Glossary/u2rmmllhvi#delivery-attempt
One try by the delivery backend to deliver a webhook event to an endpoint, recorded with its status and response on the event delivery.
Read the canonical explanation.
Durable acceptance
Section ID: Glossary/u2rmmllhvi#durable-acceptance
A callback receiver’s acknowledgement of a scheduler firing only after it has stored one durable work item; return 2xx only after durable acceptance.
Read the canonical explanation.
Durable work item
Section ID: Glossary/u2rmmllhvi#durable-work-item
The single stored record a callback receiver creates from a scheduler firing; repeated identical deliveries produce one, and a worker completes the business action from it.
Read the canonical explanation.
End user
Section ID: Glossary/u2rmmllhvi#end-user
A tenant’s end user: captured identity claims and editable profile values, named on backend requests by the X-On-Behalf-Of header.
Read the canonical explanation.
Event delivery
Section ID: Glossary/u2rmmllhvi#event-delivery
The delivery-attempt state and response information for one webhook event.
Read the canonical explanation.
Event provenance
Section ID: Glossary/u2rmmllhvi#event-provenance
The event context in a signed webhook body: the event name, id and routing metadata that identify where an emitted event came from.
Read the canonical explanation.
Event type
Section ID: Glossary/u2rmmllhvi#event-type
The named kind of webhook event; the event name inside the signed body is the authoritative one, not a routing header.
Read the canonical explanation.
Execution
Section ID: Glossary/u2rmmllhvi#execution
A single firing record for a scheduled job.
Read the canonical explanation.
Experiment context
Section ID: Glossary/u2rmmllhvi#experiment-context
Dataset-run attribution attached when a scripted evaluation turn is sent.
Read the canonical explanation.
File
Section ID: Glossary/u2rmmllhvi#file
A stored object described by its file metadata and organised in folders.
Read the canonical explanation.
Generation config
Section ID: Glossary/u2rmmllhvi#generation-config
The canonical generation configuration applied to a request.
Read the canonical explanation.
In flight
Section ID: Glossary/u2rmmllhvi#in-flight
Accepted work that has started and not completed; a dispatch already admitted or in flight can still complete, and pausing it is not remote-effect cancellation.
Read the canonical explanation.
Inbox acknowledgment
Section ID: Glossary/u2rmmllhvi#inbox-acknowledgment
A user’s acknowledgement of an inbox message; it neither performs nor rolls back the business operation.
Read the canonical explanation.
Inbox message
Section ID: Glossary/u2rmmllhvi#inbox-message
Notification content and interaction state displayed in a subscriber’s inbox.
Read the canonical explanation.
MCP connection
Section ID: Glossary/u2rmmllhvi#mcp-connection
The connection a registered custom MCP server is invoked over; refer to the MCP server itself.
Read the canonical explanation.
Deprecated; use MCP server.
MCP server
Section ID: Glossary/u2rmmllhvi#mcp-server
A Model Context Protocol server an agent connects to for its available tools; a custom server is one the tenant registered and is invoked with the tenant’s credentials.
Read the canonical explanation.
Memory
Section ID: Glossary/u2rmmllhvi#memory
A stored statement associated with a user and, when recorded, an agent or conversation and a run or session.
Read the canonical explanation.
Memory extraction
Section ID: Glossary/u2rmmllhvi#memory-extraction
The pipeline that runs after a generation, derives new memory facts from the run’s messages and updates existing ones.
Read the canonical explanation.
Memory relation
Section ID: Glossary/u2rmmllhvi#memory-relation
A directed edge from a source entity to a destination entity, labelled by an open relationship string.
Read the canonical explanation.
Memory retrieval
Section ID: Glossary/u2rmmllhvi#memory-retrieval
The search that supplies stored memories to a generation from the query text submitted for it.
Read the canonical explanation.
Message
Section ID: Glossary/u2rmmllhvi#message
A chat message in a conversation thread, sent by the user or generated by the assistant.
Read the canonical explanation.
Message feedback
Section ID: Glossary/u2rmmllhvi#message-feedback
One user’s feedback on an assistant-generated message.
Read the canonical explanation.
Model catalog
Section ID: Glossary/u2rmmllhvi#model-catalog
The catalog metadata that filters candidate models, including price, through catalog-price filters, and the context window.
Read the canonical explanation.
Model routing
Section ID: Glossary/u2rmmllhvi#model-routing
The selection of the model and provider that serve a request: explicit model ids must pass platform validation, metadata filters narrow the eligible candidates, and provider availability and run outcomes decide whether generation succeeds.
Read the canonical explanation.
Model routing filter
Section ID: Glossary/u2rmmllhvi#model-routing-filter
Metadata-based criteria for filtering the model candidates eligible for a request.
Read the canonical explanation.
Notification channel
Section ID: Glossary/u2rmmllhvi#notification-channel
One channel registered for notification delivery, with its registration state and credential count.
Read the canonical explanation.
Observation
Section ID: Glossary/u2rmmllhvi#observation
A timed evaluation span or generation record with model usage, inputs, outputs and scores.
Read the canonical explanation.
On-behalf-of user
Section ID: Glossary/u2rmmllhvi#on-behalf-of-user
The end user a backend call made with a secret key acts for, identified by a request header; the key must carry the users:impersonate scope.
Read the canonical explanation.
Profile version pin
Section ID: Glossary/u2rmmllhvi#profile-version-pin
A nonzero profile version that keeps the selected profile content fixed; fragments still resolve from the latest fragment set even when the profile is pinned.
Read the canonical explanation.
Project
Section ID: Glossary/u2rmmllhvi#project
The scope an application’s resources and keys belong to; the current public API uses the legacy default project.
Read the canonical explanation.
Prompt cache
Section ID: Glossary/u2rmmllhvi#prompt-cache
The input-side cache of prompt tokens; tokens served from it are reported in the usage breakdown of prompt tokens.
Read the canonical explanation.
Prompt fragment
Section ID: Glossary/u2rmmllhvi#prompt-fragment
Project-scoped reusable prompt-template text that profiles and other fragments include.
Read the canonical explanation.
Provider
Section ID: Glossary/u2rmmllhvi#provider
One of the model providers eligible for a request; provider preferences restrict and order them.
Read the canonical explanation.
Provider preferences
Section ID: Glossary/u2rmmllhvi#provider-preferences
Routing preferences that restrict and order the model providers eligible for a request.
Read the canonical explanation.
Publishable key
Section ID: Glossary/u2rmmllhvi#publishable-key
A key configured for an accepted identity provider that lets a browser or mobile app call Travila directly with the signed-in user’s token, so the secret key never ships to the client.
Read the canonical explanation.
Queued send
Section ID: Glossary/u2rmmllhvi#queued-send
A send accepted behind an in-flight run; an accepted or queued response is not a completed reply, and the conversation can be idle without a correlated outcome for it.
Read the canonical explanation.
Recipient
Section ID: Glossary/u2rmmllhvi#recipient
The person a notification is sent to; the requesting person must be permitted to notify that recipient, and an accepted token or supplied user id alone is not that permission.
Read the canonical explanation.
Replay
Section ID: Glossary/u2rmmllhvi#replay
A repeated delivery of the same scheduler firing; the receiver compares the firing identity and the payload binding before accepting it.
Read the canonical explanation.
Response format
Section ID: Glossary/u2rmmllhvi#response-format
The structured response control that constrains the shape of the model’s output.
Read the canonical explanation.
Response schema
Section ID: Glossary/u2rmmllhvi#response-schema
The JSON schema a response format sets; when set, server validation of the model’s output defaults to enabled, with one validation retry unless configured otherwise.
Read the canonical explanation.
Retention
Section ID: Glossary/u2rmmllhvi#retention
Configurable retention of stored data is planned and not yet available.
Read the canonical explanation.
Run
Section ID: Glossary/u2rmmllhvi#run
One accepted generation of a reply to a sent message; retaining the accepted run lets a disconnected client recover the reply without sending the question again.
Read the canonical explanation.
Sampled coverage
Section ID: Glossary/u2rmmllhvi#sampled-coverage
The share of a fixed dataset’s eligible cases that were evaluated; not the proportion of every turn reviewed.
Read the canonical explanation.
Schedule
Section ID: Glossary/u2rmmllhvi#schedule
The canonical representation of a scheduled job.
Read the canonical explanation.
Scope
Section ID: Glossary/u2rmmllhvi#scope
A label attached to an API key; where an operation enforces its scope, a missing grant returns 403 insufficient_scope.
Read the canonical explanation.
Score
Section ID: Glossary/u2rmmllhvi#score
An evaluation score with its value, source, target identity and generation attribution.
Read the canonical explanation.
Score config
Section ID: Glossary/u2rmmllhvi#score-config
A score definition specifying its value type, bounds and allowed categories.
Read the canonical explanation.
Secret
Section ID: Glossary/u2rmmllhvi#secret
A stored value scoped to one tenant and project, referenced by the resources that use it; read APIs return only its metadata.
Read the canonical explanation.
Secret key
Section ID: Glossary/u2rmmllhvi#secret-key
A backend API key (sk_*) that identifies the tenant and stays on the server; with the users:impersonate scope it acts for the user named in X-On-Behalf-Of.
Read the canonical explanation.
Self-hosted
Section ID: Glossary/u2rmmllhvi#self-hosted
An installation of Travila your own team installs and operates, as opposed to a Travila-managed dedicated single-tenant deployment; not an Enterprise-only entitlement.
Read the canonical explanation.
Storage
Section ID: Glossary/u2rmmllhvi#storage
The file store behind the Storage APIs: Travila provides file storage, metadata and temporary upload and download URLs for objects your application owns.
Read the canonical explanation.
Subscriber
Section ID: Glossary/u2rmmllhvi#subscriber
The recipient of notifications, described by the contact, locale and custom attributes delivery uses.
Read the canonical explanation.
Tool
Section ID: Glossary/u2rmmllhvi#tool
A canonical tool or function definition, shared across all services, that the model can call.
Read the canonical explanation.
Tool approval
Section ID: Glossary/u2rmmllhvi#tool-approval
The approval decision recorded for a specific tool call.
Read the canonical explanation.
Tool call
Section ID: Glossary/u2rmmllhvi#tool-call
A single structured call to a tool emitted by the model during a run.
Read the canonical explanation.
Tool execution policy
Section ID: Glossary/u2rmmllhvi#tool-execution-policy
Per-run policy for tool approvals, MCP execution concurrency and the admitted tool-call budget.
Read the canonical explanation.
Trace
Section ID: Glossary/u2rmmllhvi#trace
The evaluation record of one conversation turn, including its recorded conversation and message.
Read the canonical explanation.
Turn
Section ID: Glossary/u2rmmllhvi#turn
One position within an agentic generation run, counted against the run’s configured maximum.
Read the canonical explanation.
Usage
Section ID: Glossary/u2rmmllhvi#usage
Usage accounting for a generation: the tokens it consumed and the cost attributed to it.
Read the canonical explanation.
Voice session
Section ID: Glossary/u2rmmllhvi#voice-session
A Daily/Pipecat voice session and its session metadata.
Read the canonical explanation.
Webhook endpoint
Section ID: Glossary/u2rmmllhvi#webhook-endpoint
The provider record describing a webhook delivery destination and its delivery settings.
Read the canonical explanation.
Webhook subscription
Section ID: Glossary/u2rmmllhvi#webhook-subscription
The webhook event selection and retry settings associated with an endpoint.
Read the canonical explanation.
Workspace
Section ID: Glossary/u2rmmllhvi#workspace
In the upcoming project model, not yet available, the container for your company, with a project per application; today the public API uses the legacy default project.
Read the canonical explanation.
Document ID: Glossary/u2rmmllhvi