Skip to content
Tracon

Tracon

Tracon.Testing

AcceptedRunResponse

202 Accepted response for a queued run.

AgentCallGraph

Validates an agent call graph at save time.

AgentDecoratorPipeline

Applies every registered IAgentDecorator to an agent, in the same order Tracon.CompositeAgentCatalog uses.

AgentDefinition

The full definition of an agent. The same type is used whether the agent is declared in code or stored in the database; AgentDefinition.Origin tells the two apart.

AgentDefinitionCompiler

Chat agent, child agent (sub-agent), and harness agent production.

AgentDefinitionRequest

Request to create or update an agent definition.

AgentDescriptor

A summary view of an agent listed in the catalog. It carries everything the user interface needs to draw the agent list, without having to build the agent. A source must not mutate a descriptor or its nested collections after returning it.

AgentDetailResponse

Detailed view of a single agent.

AgentParameter

A single named placeholder an AgentDefinition’s instructions can reference as {{name}}.

AgentParameterValidationError

A single parameter value violation.

AgentParameterValidationResult

The outcome of AgentParameterValidator.ValidateValues.

AgentParameterValidator

Validates an AgentDefinition’s parameter schema, and validates a run’s supplied values against it.

AgentResponseFormat

The definition of a structured output.

AgentRollbackRequest

Request to roll back a definition to a previous version.

AgentRunBudget

A run budget shared across an entire call tree.

AgentRunDocument

A piece of reference text attached to a single run, kept apart from the model’s instructions.

AgentRunRequest

Request for a trial run made from the UI.

AgentRunScope

Represents the view of a running run that is exposed to the helper components in the run path.

AgentSessionIdentity

Stamps an AI.AgentSession with, and reads back, its Tracon session identity.

AgentSessionManager

Manages the lifecycle of named sessions: loads, restores, and saves them through ISessionStore.

AgentSkillCatalog

Combines code and run-time skill sources with a precedence rule.

AgentSkillDefinition

A markdown-based skill definition that can be loaded into an agent at run time.

AgentSkillRequest

Request to create or update a skill.

AgentSkillResourceDefinition

A readable resource carried with an AgentSkillDefinition.

AgentSkillScriptDefinition

A server-executable script stored together with an AgentSkillDefinition.

AgentSourceDiagnostic

Describes one agent source registered in the catalog.

AgentSourcePriority

The priority values Tracon’s own built-in agent sources use.

AgentValidationReport

The result of a validation that builds an agent definition without saving it and without calling any model.

AgentVersionDiffResponse

Raw JSON response for comparing two definition versions. The diff is not computed on the server; the client compares the two raw definitions field by field.

AmbientRunAttributionScope

The ambient pass-through for attributing a run that does not run inside an HTTP request to a user and a set of labels.

AmbientTenantScope

The ambient passing mechanism for running an operation executed in the background (outside an HTTP request) as a specific tenant.

AnthropicChatClientFactory

Builds an Anthropic.AnthropicClient from settings and produces AI.IChatClient instances from model bindings.

AnthropicModelCatalog

Builds the catalog shown to the UI from the model definitions in provider settings.

AnthropicProviderExtensions

Extensions that add the Anthropic (Claude) provider to the Tracon chain.

AnthropicProviderNames

The provider name registered by UseAnthropic and the ModelBinding.ProviderSettings keys.

AnthropicProviderOptions

Tracon’s Anthropic (Claude) provider settings.

ApiKeyCreateRequest

The request body for creating an API key.

ApiKeyCreationResult

The result of a key creation operation.

ApiKeyDraft

A draft for creating an API key.

ApiKeyGenerator

A helper that produces a raw API key value and its hash.

ApiKeyRecord

An API key’s database-stored view, which CARRIES no raw VALUE.

ApprovalDecisionRequest

Request body for deciding a pending approval request.

ArchiveRow

The JSON representation of a single row to write to the archive.

AttachmentContent

The content of a new attachment to be saved into the store.

AttachmentDescriptor

The metadata of an uploaded attachment.

AttachmentQuery

The filter used to list attachments.

AttachmentTypeGuard

Validates an attachment candidate against size and media-type allow lists.

AttachmentUriReference

Converts an attachment to a AI.UriContent reference and resolves that reference back.

AuditActorContext

An ambient context that carries the user of the current call.

AuditChainHasher

Computes the hash chain link for an audit trail entry. The single place the canonical form is defined; both the write path and the verify path call it, so the two can never drift apart.

AuditChainQuery

The criteria that scope a hash chain verification.

AuditChainVerification

The result of verifying one tenant’s audit trail hash chain.

AuditChainWalker

Walks an ordered list of audit entries and reports the chain status. Shared by Tracon.InMemoryAuditLog and the SQL providers so the two verify algorithms can never drift apart.

AuditEntry

A row in the audit trail that records who changed which entity and when.

AuditPayload

Builds a small JSON object for the audit trail.

AuditQuery

The criteria that filter an audit trail query.

AuditRecorder

A helper that supplies the common write path for all code that writes audit entries, including store decorators and endpoint-layer exceptions.

AuditSecretFilter

Redacts potential secrets from before and after payloads before they are written to the audit trail.

AuthorizingAIFunction

Wraps an AI.AIFunction with an IToolAuthorizationHandler check that runs before every call.

AzureOpenAIChatClientFactory

Builds an AzureOpenAIClient from options and produces AI.IChatClient instances from model bindings.

AzureOpenAIImageBuilderExtensions

Adds Azure OpenAI image generation to the Tracon chain.

AzureOpenAIModelCatalog

Builds the catalog shown to the UI from the deployment definitions in the provider options.

AzureOpenAIProviderExtensions

Extensions that add the Azure OpenAI provider to the Tracon chain.

AzureOpenAIProviderNames

The provider name registered by the UseAzureOpenAI call, and the ModelBinding.ProviderSettings keys.

AzureOpenAIProviderOptions

Tracon’s Azure OpenAI provider options.

CallableAgentResolver

Resolves, from the catalog, the other agents an agent may call.

CanaryEvaluation

Represents the result of evaluating a canary policy against the current results of the canary and control variants.

CanaryEvaluator

Pure decision logic that evaluates a CanaryPolicy against the current results of the canary and control arms.

CanaryOptions

Options for the canary evaluation background service.

CanaryPolicy

Defines automatic rollback and gradual traffic-increase rules for an experiment canary variant.

ChatHistoryState

The state the chat history provider stores within a session.

ChildAgentInvoker

Wraps a sub-agent an agent may call; enforces depth, budget, and tenant limits and links the sub-run into the tree.

ChildRunApproval

Determines whether a response carries a tool call pending approval.

ClientToolResult

The result of a single client-side tool call, sent back so the run can continue.

CodeAgentRegistration

A code-defined agent registration. Use one of two forms: declarative CodeAgentRegistration.Definition or CodeAgentRegistration.Factory, which gives full control.

CompactionSettings

Determines how an agent compacts its conversation history.

CompiledAgentCache

Caches compiled agents keyed by (tenant, name, version, skill fingerprint, culture).

ConfigurationDiagnostic

Reports whether a configuration key resolves. It does not carry the value.

ConfigurationKeyGuard

Verifies that a configuration key name a stored record points at sits under an allowed prefix.

ContentGuardContext

The context of an IContentGuard call.

ContentGuardPipeline

Pipeline that runs the registered IContentGuard implementations in sequence and records their decisions.

ContentGuardResult

The result of an IContentGuard check.

ContextWindowEstimate

The result of a pre-flight context-window check, computed without calling the model provider.

CronExpression

A hand-written parser for the standard five-field cron subset (minute hour day-of-month month day-of-week).

CurrentTenantResponse

Tenant of the current request.

DataSubjectErasureResult

The outcome of a data subject erasure request.

DataSubjectExport

A data subject’s exported content.

DataSubjectScope

The sessions, runs, and conversations that belong to one data subject.

DefaultProviderRetryClassifier

Tracon’s built-in provider retry classifier — the same closed-set rules Tracon.FallbackRetryClassifier has always applied.

DefaultRunAttributionContext

The built-in IRunAttributionContext. It reports whatever AmbientRunAttributionScope carries, and nothing otherwise.

DefaultRunErrorClassifier

Tracon’s built-in error classifier.

DocumentChannelMessageBuilder

Builds the AI.ChatMessage a document is carried in and lets the recording path tell such a message apart from ordinary instructions text.

EgressAddressValidator

The single place that decides whether an outbound target address is safe.

EgressSocketGuard

Validates the address a socket is about to connect to, and opens the socket only to an allowed address.

EvalCase

A single test case inside an EvalSuite.

EvalCaseAddResult

The result of IEvalStore.AddCaseAsync.

EvalCaseDiff

One case’s outcome on both sides of an EvalRunDiff.

EvalCaseDraft

Carrier for adding a single EvalCase.

EvalCaseInput

Input shape of an eval case (in a request).

EvalCasePromotionRequest

Request to promote a run to a case.

EvalCaseResult

The result of a single EvalCase within an EvalRun.

EvalRun

A single execution record and summary of an EvalSuite.

EvalRunCompletion

The information needed to finalize a run.

EvalRunDetailResponse

Detailed view of a single eval run: summary and case results together.

EvalRunDiff

The case-by-case difference between two completed EvalRun records of the same suite.

EvalRunDiffBuilder

Aligns two eval runs’ per-case results into an EvalRunDiff.

EvalRunDiffQuery

Which two eval runs to compare, and which page of the result to read.

EvalRunDiffUnavailableException

Thrown by IEvalStore.DiffRunsAsync when two eval runs exist but cannot be compared.

EvalRunQuery

A query for filtering the run list.

EvalRunTriggerRequest

Request to trigger an eval run immediately.

EvalSuite

An evaluation (eval) suite defined for an agent: carries which agent is measured, with which checks.

EvalSuiteSaveRequest

Request to create/update an eval suite.

Experiment

Represents an A/B experiment that splits traffic between two or more definition versions of the same agent.

ExperimentAssignment

Represents the experiment variant to which a run request is deterministically assigned.

ExperimentCanaryResponse

Response for GET /api/experiments/{name}/canary — the rule AND its current evaluation together.

ExperimentResultsQuery

Defines a query for experiment results.

ExperimentResultsResponse

Per-variant results view of an experiment.

ExperimentSaveRequest

Request to create/update an experiment. The name comes from the path.

ExperimentVariant

Defines one experiment variant: its definition version and traffic weight.

ExperimentVariantResult

Summarizes run results for an experiment variant (calculated in the store).

ExtensionPointDiagnostic

One host-bound extension point and whether the host replaced its built-in default.

FixedTenantContext

An immutable tenant context that always returns the same tenant.

GeneratedApiKey

The generated raw API key value and its derived forms.

GoogleChatClientFactory

Builds a Google GenAI GenAI.Client from settings and produces AI.IChatClient instances from model bindings.

GoogleImageBuilderExtensions

Adds Google image generation to the Tracon chain.

GoogleModelCatalog

Builds the catalog shown in the UI from the model definitions in provider settings.

GoogleProviderExtensions

Extensions that add the Google Gemini provider to the Tracon chain.

GoogleProviderNames

Provider name registered by the UseGoogle call, and the ModelBinding.ProviderSettings keys.

GoogleProviderOptions

Tracon’s Google Gemini provider settings.

HarnessSettings

Settings for the harness capabilities. It mirrors a safe subset of the HarnessAgentOptions structure of Microsoft Agent Framework.

HttpTenantContext

Resolves the tenant from the current HTTP request.

IdempotencyRequest

An idempotency reservation request.

IdempotencyReservation

The result of an IIdempotencyStore.ReserveAsync call.

IdempotencyResponse

The stored HTTP response.

ImageGenerationOperatorRequest

The request body for an operator image-generation action.

ImageGenerationOperatorResponse

The result of an operator image-generation action.

ImagePriceOverride

Defines the configured price for one image-generation model.

InMemoryWorkflowCheckpointStore

Stores workflow checkpoints in process memory.

InboundTrigger

An inbound trigger definition: an external event that starts a queued run.

InboundTriggerAcceptedResponse

The response for a successfully accepted inbound trigger event.

InboundTriggerDispatchResult

The result of InboundTriggerDispatcher.EnqueueAsync.

InboundTriggerRateLimiter

Applies a fixed-window rate limit per inbound trigger.

InboundTriggerResponse

The response describing an inbound trigger definition.

InboundTriggerSaveRequest

The request body for creating or replacing an inbound trigger.

InboundTriggerSecretResolver

Resolves an InboundTrigger’s signing secret by reading its configured configuration key.

InboundTriggerValidatedRequest

A request that passed every check and is ready to be queued.

InboundTriggerValidationResult

The result of InboundTriggerDispatcher.ValidateAsync.

InstructionCultureResolver

Resolves the instructions text a run should use from an AgentDefinition’s culture dictionary.

InstructionParameterBinder

Substitutes {{name}} placeholders in an instructions text with concrete values.

JobCompletion

The information needed to finalize a job.

JobContext

The context available during an IJobHandler execution.

JobDetailResponse

Detailed view of a single job: record and items together.

JobErrorCodes

The stable codes a job’s JobRecord.ErrorMessage carries when the failure comes from the queue itself rather than from a handler.

JobHandlerKeys

The built-in job handler keys, plus validation for the keys a consumer registers.

JobItemRecord

A single input of a batch job and that input’s processing result.

JobItemResult

The result of a processed job item. Reported with IJobStore.ReportItemAsync.

JobLanes

Well-known values and validation for job lane identifiers.

JobPayload

Extracts the job item input list from the free-form JSON in JobRecord.Payload/JobSchedule.Payload.

JobQuery

A filter for querying the job list.

JobQueueDepth

The number of open jobs in one lane/status pair.

JobRecord

The summary of a queued job. The header of its items (JobItemRecord).

JobRequest

The description of one job to queue through IJobDispatcher.

JobRetryException

The exception an IJobHandler throws to signal that it wants the job retried after a specific delay.

JobSchedule

The schedule record defining when and how a job runs.

JobScheduleSaveRequest

Request to create/update a schedule.

JobTriggerRequest

Request to trigger a schedule immediately.

JudgeFailure

A normalized judge failure returned by manual scoring.

JudgeRunResponse

The result of manually scoring a run.

JudgeScore

One named score produced by an IRunJudge.

LiveVoiceAppend

Text sent into a live conversation’s context.

LiveVoiceBuilderExtensions

Extensions that enable the provider-hosted live voice layer.

LiveVoiceCreateRequest

The request that creates a live voice session.

LiveVoiceEvent

One event observed on a live voice session’s sideband.

LiveVoiceSessionCreateRequest

The request that opens a provider-hosted live voice session.

LiveVoiceSessionCreateResponse

The answer that opens a provider-hosted live voice session.

LiveVoiceSessionHandle

The result of creating a live voice session.

LiveVoiceSessionOptions

The settings of one live voice session.

LiveVoiceSessionStatusResponse

The status of a provider-hosted live voice session.

LoopCriterion

One declarative stop criterion of the harness loop (see LoopSettings).

LoopSettings

Turns the harness loop on: the agent is re-invoked until a stop criterion says the work is finished.

McpOAuthCompleteResult

The result of the OAuth callback.

McpOAuthStartResponse

Response for starting OAuth Mode 1.

McpOAuthStartResult

The result of an OAuth start request.

McpPromptArgumentSummary

The summary of an MCP prompt argument.

McpPromptArgumentsRequest

Request to resolve an MCP prompt with arguments.

McpPromptContent

The resolved content of a prompt.

McpPromptListResult

The result of listing prompts.

McpPromptSummary

The summary of an MCP prompt.

McpRefreshResponse

Result of an MCP tool refresh.

McpResourceContent

The content of a resource that was read.

McpResourceListResult

The result of listing resources.

McpResourceSummary

The summary of an MCP resource.

McpServerDefinition

A registered remote MCP server. Its tools are discovered at connection time and listed alongside the tools registered in code.

McpServerRequest

Request to create/update an MCP server.

MemorySettings

Determines the memory providers bound to an agent.

MigrationRunner

Applies the embedded SQL migrations to the database.

MigrationRunner

Applies the embedded SQL migrations to the database.

MigrationRunner

Applies the embedded SQL migrations to the database.

ModelBinding

Determines the provider and the model an agent runs with. It carries no credentials; the API key is resolved from configuration.

ModelDescriptor

A model’s capabilities and limits.

ModelFallback

One link of a ModelBinding.Fallbacks chain.

ModelPriceOverride

Defines a configured price override for one model.

ModelProviderCircuitBreaker

Circuit breaker that temporarily cuts off requests when a model provider fails consecutively. Holds state per provider name.

ModelProviderCredential

A resolved, in-memory credential used to call a model provider on behalf of a specific tenant.

ModelProviderDescriptor

A provider’s definition as shown in the UI.

ModelProviderHealth

A model provider’s status at the last check.

ModelProviderHealthCache

Caches the health-check results of the registered model providers.

ModelProviderRegistry

Registry that holds the registered IModelProvider implementations by name, and the single place that assembles the model-call pipeline.

ModelProviderSettings

Helpers that read and validate the ModelBinding.ProviderSettings dictionary.

ModelRunJudgeOptions

Options for the built-in model-based judge (Tracon.ModelRunJudge).

OnlineEvalSummaryService

Maintains a sliding-window summary of online evaluation scores and publishes WebhookEvents.RunScoreLow when its threshold is crossed.

OnlineEvaluationOptions

Online evaluation settings.

OnlineEvaluationSummary

Summarizes the online evaluation window (GET /api/evaluation/online).

OpenAIChatClientFactory

Builds an OpenAI.OpenAIClient from options and produces AI.IChatClient instances from model bindings.

OpenAICompatibleProviderExtensions

Extensions that add named providers with an OpenAI compatible chat API to the Tracon chain (OpenRouter, Groq, vLLM, Ollama, LM Studio, …).

OpenAICompatibleProviderOptions

Constants for the configuration path of the providers that UseOpenAICompatible registers.

OpenAIImageBuilderExtensions

Adds OpenAI image generation to the Tracon chain.

OpenAILiveOptions

Options of the OpenAI live voice provider.

OpenAILiveProviderExtensions

Extensions that add OpenAI’s live voice provider to the Tracon chain.

OpenAIModelCatalog

Builds the catalog shown in the user interface from the model definitions in the provider options.

OpenAIProviderExtensions

Extensions that add the OpenAI provider to the Tracon chain.

OpenAIProviderNames

The provider names that the UseOpenAI call registers.

OpenAIProviderOptions

The OpenAI provider options of Tracon.

PatternContentGuardOptions

Settings for the built-in pattern-based guard.

PendingApproval

The pending tool approval request of a run that executes from the queue.

ProviderConcurrencyLimiter

Limits concurrent outgoing calls per model provider.

ProviderCredentialClientCache<TFactory>

Builds and caches a provider-specific client factory keyed by a resolved ModelProviderCredential (BYOK).

ProviderDiagnostic

Summarizes diagnostics for a model provider.

QuotaConsumption

The consumption of a completed run to add to the quota counters.

QuotaDecision

The result of a quota check.

QuotaDefinition

A quota rule defined for a tenant or an agent.

QuotaEnforcer

Enforces quota rules and records the consumption of completed runs.

QuotaPeriodCalculator

Calculates which quota period an instant falls into, and when that period resets.

QuotaSaveRequest

Request body for saving a quota rule.

QuotaThresholdCrossing

A single quota threshold crossed by a period’s consumption.

QuotaUsageQuery

A filter for querying quota usage.

QuotaUsageRecord

A scope’s consumption in the current period.

QuotaUsageResponse

Response for the quota usage endpoint.

ReplayToolMismatchException

Replay could not find a recorded tool result.

ResolvedRetentionPolicy

Represents a resolved, applicable retention rule for a target.

ResponseCacheSettings

Response caching settings for a ModelBinding.

RetentionExecutor

Provides shared logic for preview and actual cleanup runs. Tracon.RetentionJobHandler and the RetentionEndpoints “run now” and “preview” endpoints use it.

RetentionPolicy

An age- and volume-based retention rule for a target.

RetentionPolicyResolver

Combines the database policy with the configuration default for a target.

RetentionPolicySaveRequest

Request body for saving a retention policy.

RetentionPreview

A preview of “how many rows would be deleted if run now” for a target.

RetentionRun

The history record of a cleanup run.

RetentionRunTriggerResponse

Response to a “run now” request.

RetentionTargetOptions

Defines a configuration-based retention default for one target.

RetentionTargets

The fixed table list a retention policy may target.

RunAgentStatistics

An agent’s run summary.

RunAttributionReader

Reads an IRunAttributionContext safely on a recording path.

RunAuthorizationRequest

Describes one run awaiting an authorization decision.

RunAuthorizationResult

The outcome of an authorization decision.

RunComparisonResponse

Side-by-side summary of two runs.

RunComparisonSide

One side of the comparison.

RunCompletion

Everything needed to close a run.

RunCost

Cost of a run. It is computed and written once when the run ends (a price snapshot) — a later change to the price list does not change past values.

RunCostRecalculationResult

Result of a cost recalculation.

RunError

Error information for a failed run.

RunErrorClassification

The result of an IRunErrorClassifier classification.

RunErrorCluster

The summary of runs sharing the same fingerprint.

RunErrorFingerprint

Produces the clustering digest Tracon’s built-in classifier uses.

RunErrorStatistics

An error class’s summary.

RunEvent

A single event produced during a run. Events are append-only: they are never updated, only added.

RunEventCustomTypes

Validation for the CustomType string that qualifies a RunEventType.Custom event.

RunEventWriter

Writes the events of a single run into IRunStore and produces the sequence number.

RunFeedbackRequest

Request body for writing a run/message score.

RunInputRecord

A run’s stored input.

RunInputResponse

HTTP response for a run’s recorded input.

RunJudgeContext

The limited context supplied to a judge.

RunJudgment

The judge’s verdict: the named scores it produced.

RunLabelStatistics

A label’s run summary; one entry per distinct key/value pair.

RunLabels

The limits a run’s attribution must obey, and the single place they are enforced.

RunModelStatistics

A model’s run summary. The input to cost computation.

RunPromotionOutcome

Represents the RunToCasePromoter.PromoteAsync outcome and its case, when present.

RunQuery

Query used to filter the run list.

RunReconciliationOptions

Orphaned-run reconciliation settings.

RunRecord

Summary of a run. It acts as the header of the event stream.

RunRecordingAgent

Run completion: usage/cost merging, error mapping, and the terminal store write. RunRecordingAgent.CompleteAsync fans out to the root-only notifications in RunRecordingAgent.Notifications.cs, but owns the outcome itself.

RunReplayPreparation

Represents a prepared replay plan.

RunReplayRequest

A replay request.

RunReplayResponse

Result of a replay.

RunSampleRequest

Represents the run summary required for a sampling decision.

RunSampler

Decides whether to sample a completed run for online evaluation and, when sampled, queues a JobHandlerKeys.OnlineEval job.

RunScore

A human (or judge) score for a run or for a single message within a run.

RunScoreAggregate

One aggregated group: every score sharing a breakdown key AND a RunScoreKind.

RunScoreBucketAggregate

One time bucket of the trend series (RunScoreSummary.Series).

RunScoreBucketing

Shared pure logic for score trend bucket truncation (RunScoreBucket).

RunScoreQuery

The filter for a score summary query (IRunScoreStore.SummarizeAsync).

RunScoreRules

The shared rules a RunScore must satisfy before it is stored.

RunScoreSummary

The result of IRunScoreStore.SummarizeAsync.

RunStartInfo

Everything needed to open a new run.

RunStatistics

A summary of the runs in a time range.

RunStatisticsQuery

The filter for a run statistics query.

RunTimeSeriesBucketing

The shared pure logic for time-series bucket computation. Both InMemoryRunStore and PostgresRunStore use this type, so the bucket limit and rounding rules never diverge between the two stores.

RunTimeSeriesQuery

Filter for a time-series query.

RunTrace

A run’s span tree. The waterfall view is built on top of this.

RunTraceCollector

Listens to Tracon spans, buffers them per run, and writes them to ITraceStore when the run completes, based on the sampling decision.

RunTreeCost

Total cost of a run tree (the root plus every child run).

RunUsage

Token usage of a run.

RunUserStatistics

A user’s run summary.

RunVersionStatistics

A definition version’s run summary.

SafeErrorText

Produces text that is safe to write to a persistent field or an external response, from an exception that may carry provider, network, or third-party detail.

SandboxedSkillScriptRunner

Tracon’s single script execution path, which runs skill scripts in an isolated operating-system process.

SchemaReadyGate

Delays background services until the SQL schema is ready.

SearchKnowledgeHit

A semantic search hit.

SearchKnowledgeRequest

A semantic search request.

SessionAuthorizationRequest

Describes one session access awaiting an authorization decision.

SessionBranchOutcome

The result of a branching attempt.

SessionBranchRequest

A request to branch a conversation from a specific point.

SessionBranchResult

The result of branching.

SessionDetailResponse

Detailed view of a single session: metadata and chat history.

SessionQuery

A filter for querying the session list.

SessionRecord

A stored session.

SingleTenantContext

The default tenant context for single-tenant deployments. It always returns TraconOptions.DefaultTenantId.

SingletonExecutionOptions

The settings of single-executor election.

SkillScriptExecutionResult

The result of one skill script execution.

SkillScriptGrant

The record carrying permission to execute a skill script.

SkillScriptGrantRequest

Request to grant script execution permission.

SkillScriptNaming

Validates the file name a stored script is written under.

SkillScriptSupport

The compile-path handle for skill script execution: sets up MAF’s file-based skill source and produces the execution delegate for stored scripts.

SpeakRequest

A speech synthesis request as an operator action.

SpeakResponse

The result of speech synthesis.

SpeechAlignment

One character’s position in the generated audio.

SpeechAudio

Generated audio.

SpeechRequest

A text-to-speech generation request.

SpeechTranscript

The result of speech-to-text conversion.

SpeechTranscriptionOptions

Speech-to-text conversion settings.

SqlPersistenceDiagnosticsSnapshot

Represents the current connection and migration status of an SQL persistence provider.

SqlPersistenceRegistrationMarker

Marks a registered SQL persistence provider.

StateGenerationCount

The number of stored rows carrying one schema generation, and whether this build can read them.

StateGenerationTally

The number of stored rows carrying one schema generation.

StatePreflight

Answers “can this build still read the state already in the database” WITHOUT writing anything and without starting the application.

StatePreflightReport

What a read-only state preflight found: how many rows carry each stored schema generation, and how a small sample of them behaved when this build tried to read them.

StateSample

One sampled row, read for a decode attempt.

StateSampleFailure

One sampled row the running build could not read.

StructuredResponseValidationContext

The response an IStructuredResponseValidator checks.

StructuredResponseValidationResult

The outcome of a structured response validation check.

SubAgentSettings

Determines how long an agent waits for the agents it calls.

TraconDiagnostics.Tags

Defines span and metric tag names. Changing them breaks dashboards.

TenantChatClientCacheKey

Builds the cache key for an AI.IChatClient produced for a tenant credential (BYOK).

TenantDescriptor

A registered tenant.

TenantEgressPolicy

The set of model providers a tenant’s agents are allowed to call (egress policy).

TenantEgressPolicyRequest

The request body for creating or replacing a tenant’s egress policy.

TenantEgressPolicyResponse

The response describing a tenant’s egress policy.

TenantProviderBinding

Binds a tenant to a model provider’s credential, by name only.

TenantProviderBindingRequest

The request body for creating or replacing a tenant provider binding.

TenantProviderBindingResponse

The response describing a tenant provider binding.

TenantProviderCredentialResolver

Resolves a tenant’s TenantProviderBinding into a ModelProviderCredential by reading the bound configuration key’s value.

TenantRequest

Request to create/update a tenant record.

TextChunker

Splits text into fixed-length chunks with overlap.

TextTrimming

Trims text to a UTF-8 byte limit.

TimeSeriesPoint

A summary of the runs in a time bucket. The result unit of /api/stats/timeseries; empty buckets are also returned (with zero events).

TimeoutAIFunction

Wraps an AI.AIFunction so a call that does not settle within a fixed duration ends in TraconToolTimeoutException instead of running unbounded.

ToolApprovalContext

The tool call a code-defined approval policy judges. Read-only.

ToolApprovalDecision

Tool approval decision sent from the UI.

ToolApprovalPolicyRegistration

A code-defined approval policy registered through ITraconBuilder.AddToolApprovalPolicy(...).

ToolApprovalPolicyRegistry

Holds the code-defined approval policies registered at startup, keyed by tool name.

ToolApprovalPresentation

A human-readable projection of one tool-approval request, produced by a consumer’s IToolApprovalPresenter.

ToolApprovalPresenterRunner

Calls the registered IToolApprovalPresenter for every pending approval request and turns its fail-open contract into an actual guarantee.

ToolApprovalRule

A persistent approval rule for a tool call the user said “do not ask again” for.

ToolApprovalRuleEvaluator

Applies persistent approval rules to a tool call.

ToolApprovalRuleRequest

Request to create a persistent, argument-conditioned approval rule.

ToolArgumentCondition

One comparison against a tool call argument: path · operator · value.

ToolArgumentConditionLimits

The size limits that keep ToolArgumentCondition a comparison, not a rule engine.

ToolArgumentsValidationResult

The outcome of a tool arguments validation check.

ToolAuthorizationRequest

Describes one tool call awaiting an authorization decision.

ToolAuthorizationResult

The outcome of an authorization decision.

ToolCallUsage

A single tool call’s non-token measurement and cost.

ToolDescriptor

The UI-facing definition of a tool registered in code. The agent editor shows a selection from this list; it does not accept free-text input.

ToolInvocationRecord

The summary of a single completed tool call.

ToolRegistrationOptions

Configures metadata for a tool registration.

ToolUsage

A tool’s usage summary. Shown by the UI’s Tools screen.

ToolUsageQuery

The filter for a tool usage summary.

ToolUsageUnits

The known unit names for ToolCallUsage.Unit.

TraceSpan

A single persisted OpenTelemetry span.

TraceSpanBatch

A span set belonging to a single trace.

TraconA2ABuilderExtensions

Extensions that register the services needed to publish Tracon agents over A2A.

TraconA2AExtensions

Extensions that connect the HTTP endpoint that publishes Tracon agents over A2A.

TraconA2AOptions

Settings for publishing Tracon agents over A2A.

TraconAgentGraphOptions

Defines limits that apply when an agent calls another agent.

TraconAgentSessionStore

Connects the Microsoft Agent Framework’s Hosting.AgentSessionStore abstraction to Tracon’s AgentSessionManager class.

TraconAgentSourceException

Represents a normalized failure from an IAgentSource.

TraconApprovalOptions

Options for asynchronous approvals.

TraconAsyncRunOptions

Defines queued, durable run options.

TraconAttachmentOptions

Defines attachment upload limits for size and media-type allow lists.

TraconAuditOptions

Defines options for audit-trail actor resolution.

TraconAuthenticationMeta

Reports which authentication layers are enabled.

TraconCircuitBreakerOptions

Defines circuit-breaker options that temporarily stop requests after a model provider returns consecutive failures.

TraconClientToolExtensions

Registers a client-side tool: its declaration (name, description, JSON schema) lives in code, like every other tool (the code-only tools rule), but its body runs on the caller instead of on the server.

TraconCompilationException

Thrown when an agent definition cannot be turned into a runnable agent.

TraconContentBlockedException

Thrown when an IContentGuard blocks content.

TraconContentFilteredException

Thrown when a model provider cuts the response short with its safety or content filter.

TraconContentGuardBuilderExtensions

Chain extensions that turn on content inspection.

TraconContentGuardOptions

Settings for the content inspection pipeline.

TraconContentProtectionExtensions

Chain extensions that turn on at-rest content protection.

TraconContentProtectionOptions

Settings for at-rest content protection.

TraconDiagnostics

Defines Tracon telemetry source and measurement names.

TraconDiagnosticsCollector

Collects the installation’s self-diagnostic summary report.

TraconDiagnosticsReport

Reports the self-diagnostics of the installation.

TraconDrainOptions

Graceful-shutdown draining settings.

TraconEgressOptions

Shared rules for the target address of outbound network requests.

TraconEndpointOptions

Access and behavior settings for the endpoints connected via MapTracon.

TraconEndpointRouteBuilderExtensions

Extensions that connect Tracon’s HTTP surface to the application.

TraconEvalCheckRegistration

A custom check registration added through ITraconBuilder.AddEvalCheck(...).

TraconException

Base class for every error Tracon raises.

TraconExternalCallException

Thrown when an external caller (over MCP or A2A) asked to invoke an agent from the catalog and the call was refused because it crosses a boundary.

TraconGeneratedToolArguments

The helper methods called by tool wrappers produced by the source generator while converting JSON arguments to CLR types.

TraconHealthCheckExtensions

Extensions that connect Tracon to the standard.NET health check system.

TraconHealthOptions

Defines model-provider health-check options.

TraconId

UUID version 7 generator for Tracon identifiers (RFC 9562).

TraconIdempotencyOptions

Options for Idempotency-Key support.

TraconImageOptions

Settings for the image-generation tool.

TraconInboundTriggerOptions

Options that constrain inbound triggers.

TraconKnowledgeOptions

Options for the knowledge base (semantic search).

TraconLoopEvaluatorRegistration

A code-defined loop stop criterion registered through ITraconBuilder.AddLoopEvaluator(...).

TraconMcpBuilderExtensions

Extensions that register tool discovery from remote MCP servers.

TraconMcpOptions

Options for connecting to remote MCP servers.

TraconMcpSecurityOptions

The security boundary applied to stored MCP server definitions.

TraconMcpServerBuilderExtensions

Extensions that register the services needed to publish Tracon agents as MCP tools.

TraconMcpServerExtensions

Extensions that connect the HTTP endpoint that publishes Tracon agents as MCP tools.

TraconMcpServerOptions

Settings for publishing Tracon agents as MCP tools.

TraconMetaResponse

Response for {prefix}/api/meta. Carries the minimum information the UI needs to configure itself.

TraconMetrics

Metrics emitted by Tracon. Consumers collect them with AddMeter(TraconDiagnostics.MeterName).

TraconModelConcurrencyOptions

Defines the outgoing concurrency limit applied per model provider.

TraconObservabilityOptions

Defines telemetry collection and persistence options.

TraconOnlineEvaluationBuilderExtensions

Chain extensions that turn on the built-in model-based judge.

TraconOptions

Defines Tracon run-time options.

TraconPolicies

Role-based authorization policy names that Tracon defines.

TraconPostgreSqlBuilderExtensions

Extensions that add PostgreSQL persistence to the Tracon chain.

TraconPostgreSqlOptions

Settings for Tracon’s PostgreSQL persistence layer.

TraconPreflightOptions

Defines options for the pre-flight context-window check.

TraconPricingOptions

Defines a run-cost price source. It is a secondary source for a model that has no price in the ModelDescriptor catalog.

TraconProviderUnavailableException

Thrown when the circuit breaker has temporarily taken a model provider out of service.

TraconQuotaOptions

Defines options for the quota subsystem.

TraconRateLimitOptions

Rate-limit settings applied to Tracon endpoints.

TraconRetentionOptions

Defines data retention and archival options.

TraconRoleMeta

Reports which role levels the current request’s caller satisfies.

TraconRunBudgetExceededException

Thrown when a run tree’s token or cost budget runs out mid-run, between two model turns.

TraconRunContext

Carries the identity, tree position, and budget of the running run to the helper components inside the run path.

TraconRunContinuationOptions

Interrupted-run continuation settings.

TraconRunOptions

Run options that let the caller determine a run’s identifier, its place in the tree, and its budget.

TraconRunRecordingOptions

Defines how much detail run recording retains.

TraconSchedulingOptions

Batch and scheduled run settings.

TraconServiceCollectionExtensions

Extensions that register Tracon with dependency injection.

TraconSessionConflictException

Thrown for the losing request when two concurrent first requests arrive for the same new session id.

TraconSessionOwnerRequiredException

Thrown when session ownership is on, a session write needs an owner, and no authenticated identity could be resolved to be that owner.

TraconSessionOwnershipOptions

Turns per-user session ownership on, a second boundary drawn UNDER the tenant.

TraconSessionStateKeys

The stable keys Tracon uses in an AgentSession state bag.

TraconSkillOptions

Defines limits for skill content and agent attachment.

TraconSkillScriptBuilderExtensions

Configuration extensions that enable skill script execution.

TraconSkillScriptOptions

Defines options that control server-side skill script execution.

TraconSqlServerBuilderExtensions

Extensions that add SQL Server persistence to the Tracon chain.

TraconSqlServerOptions

Settings for Tracon’s SQL Server persistence layer.

TraconSqliteBuilderExtensions

Extensions that add SQLite persistence to the Tracon chain.

TraconSqliteOptions

Settings for Tracon’s SQLite persistence layer.

TraconStorageMeta

Reports which storage implementations are active.

TraconStructuredResponseException

Thrown when a run’s response fails structured output validation.

TraconStructuredResponseOptions

Structured response validation settings.

TraconTenancyBuilderExtensions

Extensions that connect multi-tenancy to the HTTP request.

TraconTenancyOptions

Settings that determine how the tenant is resolved from the request.

TraconTenantProviderOptions

Options that constrain per-tenant model provider bindings (BYOK).

TraconToolApprovalPolicyExtensions

Chain extension that registers a code-defined approval policy for a tool.

TraconToolAttribute

Marks a method as a tool. AddToolsFrom<T> registers only methods carrying this attribute.

TraconToolOptions

Defines tool execution options.

TraconToolRegistration

A single tool registered with dependency injection. Tracon builds the tool registry from these registrations.

TraconToolTimeoutException

Thrown when a tool call does not settle within its configured timeout.

TraconToolUsage

Lets a tool report non-token usage from its own body.

TraconUiBuilderExtensions

Provides extensions that register the embedded management UI.

TraconValidationOptions

Defines options for the POST /api/agents/validate endpoint.

TraconWebhookOptions

Event publishing (webhook) settings.

TraconWorkflowFunctionExtensions

Extensions that register a code function as a workflow node.

TraconWorkflowOptions

Settings that control workflow execution.

TraconWorkflowsBuilderExtensions

Extensions that register workflow execution.

TruncatingAIFunction

Wraps an AI.AIFunction so a result over a byte limit is trimmed and handed to the model inside an envelope that states how many bytes were dropped, instead of running unbounded.

UploadDocumentChunk

A single ready-made chunk in an upload request.

UploadDocumentRequest

Request to upload a document.

UploadDocumentResponse

Result of a document upload request.

ValidatingAIFunction

Wraps an AI.AIFunction with an IToolArgumentsValidator check that runs before every call.

ValidationMessage

A single finding produced by the validation of an agent definition.

VectorChunk

A single chunk to write.

VectorSearchHit

A single search result.

VectorSearchRequest

A semantic search request.

VoiceAttributeNames

Names for well-known VoiceDescriptor.Attributes keys. Not exhaustive: a provider may report other safe scalar labels under their own key.

VoiceAudioFormats

The audio formats that the client can send.

VoiceBuilderExtensions

Adds the voice tools to the Tracon chain.

VoiceConnectionLease

Represents a reserved voice connection slot.

VoiceConnectionLimiter

Limits concurrent voice connections per tenant.

VoiceConversationBuilderExtensions

Extensions that enable the real-time voice conversation layer.

VoiceConversationOptions

Options of the real-time voice conversation layer.

VoiceConversationProtocol

The frame names and the audio formats of the conversation WebSocket.

VoiceConversationRequest

The immutable facts of a conversation connection.

VoiceDescriptor

The definition of an available voice.

VoiceHealth

The voice provider’s reachability status.

VoiceLiveOptions

Options of the provider-hosted live voice layer.

VoiceOptions

Settings for the voice tools.

VoicePriceOverride

Defines the configured price for one voice model.

VoiceProviderNames

Names of known voice providers.

VoiceSessionCost

What one voice conversation cost.

VoiceSessionQuery

The filter for listing voice session records.

VoiceSessionRecord

The summary record of a real-time voice connection.

WebhookApprovalSummary

A pending approval or human-input request’s webhook summary.

WebhookDelivery

A single delivery record.

WebhookDeliveryQuery

A filter for querying delivery history.

WebhookDeliveryResult

The result of a delivery attempt.

WebhookEventPayload

The JSON body of a webhook request.

WebhookEventPayloadJsonContext

The source-generated JSON context for WebhookEventPayloadJsonContext.WebhookEventPayload and its subtypes.

WebhookEvents

The event types Tracon can publish.

WebhookHttpClient

Provides the HttpClient used for webhook delivery, with built-in SSRF protection.

WebhookJobSummary

A job’s webhook summary.

WebhookQuotaSummary

An exceeded quota threshold’s webhook summary.

WebhookRunSummary

A run’s webhook summary.

WebhookSaveRequest

The request body for saving a webhook subscription.

WebhookScoreSummary

A score window threshold’s webhook summary.

WebhookSigner

Produces and verifies the HMAC-SHA256 signature of webhook requests.

WebhookSubscription

An external system’s event subscription.

WebhookTestResponse

The response for the test event.

WebhookUrlValidator

Validates webhook target addresses against SSRF.

WorkflowAgentBinding

Binds catalog agents to a workflow graph defined in code.

WorkflowCheckpointRecord

Represents a single checkpoint of a workflow run.

WorkflowCheckpointState

Provides shared constants for checkpoint state.

WorkflowDefinition

Represents the full definition of a workflow, whether defined through the UI or in code.

WorkflowDefinitionValidator

Validates the structural validity of a workflow definition.

WorkflowDescriptor

Represents a summary view of a workflow listed in the catalog.

WorkflowFunctionDescriptor

Describes a function node registered in code.

WorkflowFunctionResponse

Wire-safe view of a registered function node.

WorkflowGraph

Represents a workflow’s compiled graph: nodes, edges, and external request ports.

WorkflowGraphEdge

Represents the connection between two nodes.

WorkflowGraphNode

Represents a node in the graph.

WorkflowNodeReference

Points to a single node entering a workflow’s graph: an agent from the catalog, or a function registered in code.

WorkflowNodeRetryPolicy

Retries a single workflow function node on a transient provider error instead of failing the whole run.

WorkflowPendingRequest

Represents human input awaited by a workflow run.

WorkflowRespondHttpRequest

Response to a pending human input request.

WorkflowRespondRequest

Represents a response to a pending request.

WorkflowResumeHttpRequest

Request to resume a workflow from a checkpoint.

WorkflowResumeRequest

The information needed to resume a workflow from a checkpoint.

WorkflowRunHttpRequest

Request to run a workflow.

WorkflowRunRequest

The information needed to run a workflow.

WorkflowSaveRequest

Request to save a workflow definition.

AgentCallGraphProblem

The machine-readable result of a call graph validation.

AttachmentValidationResult

The result of validating an attachment.

CallableAgentInfo

The summary of a callable sub-agent, reported to the model.

ConversationBranch

A conversation branch’s store-level result.

DocumentAttachmentSummary

A document attachment’s identifying information, without its content.

EgressAddressPolicy

The address rules one outbound surface applies to its targets.

EgressAddressVerdict

The result of validating an outbound target address.

McpRefreshOutcome

The result of an IMcpToolRefresher.RefreshAsync call.

ResolvedCallableAgents

The resolved set of sub-agents a definition may call, and its cache fingerprint.

RunEventDraft

Represents the information an event carries before its sequence number and timestamp are assigned.

WebhookUrlVerdict

The result reporting whether a webhook target is safe.

IAgentCatalog

The catalog that joins every agent source into a single view. The user interface and the HTTP layer reach agents only through this interface.

IAgentDecorator

A decorator applied to every agent resolved from the catalog. Tracon adds run recording through this mechanism; a consumer can register its own decorator the same way.

IAgentDefinitionStore

The store for agent definitions kept in the database. Versioning and rollback support are required: every save produces a new version, and old versions are not deleted.

IAgentSkillStore

The store for a tenant’s run-time skill definitions.

IAgentSource

A source the catalog collects agents from. Tracon joins sources declared in code, stored in the database, and registered by the application.

IApiKeyStore

The store for per-tenant API keys.

IArchiveSink

The cold-storage extension point rows are written to before deletion.

IAttachmentStorage

The extension point that stores attachment content in an external store (S3, Blob).

IAttachmentStore

The contract for attachment metadata and for the default (database) content storage.

IAuditActorResolver

Resolves the actor (the who) of the current call.

IAuditDecorated

Exposes the real store implementation an audit trail decorator wraps.

IAuditLog

The audit trail log.

IContentGuard

The extension point that inspects content going to and coming from the model.

IContentProtector

Extension point for at-rest encryption of stored content.

IConversationBranchStore

The store that branches a conversation by copying it.

IDataSubjectResolver

Maps a data subject (an end user, in the consumer’s own identity system) to the sessions, runs, and conversations that belong to them.

IDataSubjectStore

The data plane that counts, exports, and erases one data subject’s content across the schema.

IEvalEvaluatorFactory

The extension point that builds the AI.IAgentEvaluator an eval suite is graded with.

IEvalStore

The store for evaluation (eval) suites, cases, and runs.

IExperimentStore

Defines the store for A/B experiments.

IIdempotencyStore

The store for idempotency records.

IInboundTriggerStore

The store for inbound trigger definitions.

IJobDispatcher

Queues a job for a registered IJobHandler.

IJobHandler

The extension point that provides job execution logic for one handler key.

IJobScheduleStore

The store for schedule definitions.

IJobStore

The store for queued jobs and their items.

ILiveVoiceProvider

Creates and supervises a provider-hosted live voice session.

ILiveVoiceSideband

The server-side control connection of a live voice session.

IMcpOAuthCoordinator

The coordinator that manages the OAuth Mode 1 (authorization code) flow for MCP servers.

IMcpPromptClient

The client that lists an MCP server’s prompts and resolves their content.

IMcpResourceClient

The client that lists and reads an MCP server’s resources.

IMcpResourceContextProviderFactory

The factory that builds an AI.AIContextProvider for AgentDefinition.McpResourceUris (Mode A).

IMcpServerStore

The store for registered MCP servers.

IMcpToolRefresher

Refreshes the tool list of remote MCP servers on demand.

IMigrationApplier

Applies the pending migrations of the active SQL persistence provider.

IModelProvider

A model provider. Each provider is implemented in its own package (for example, Tracon.OpenAI) and registered with DI.

IModelProviderConfigurationDiagnostics

Defines optional configuration diagnostics for a model provider.

IModelProviderHealthCheck

The optional health-check contract for a model provider.

IModelProviderRegistry

The registry that keeps registered model providers by name.

IPendingApprovalStore

The store for pending approval requests.

IProviderRetryClassifier

Decides whether a model-provider failure is retryable on the next fallback link.

IQuotaStore

The store for quota rules and consumption counters.

IRetentionPolicyStore

The control-plane store for retention policies and run history.

IRetentionStore

The data plane that counts, batch-deletes, and reads-for-archive over the actual retention data.

IRunAttributionContext

Resolves who a run belongs to and what work it was made for.

IRunAuthorizationHandler

Decides whether a caller may start a run or read/write a session.

IRunCancellationRegistry

The in-memory registry of runs in progress on this instance; binds an incoming cancellation request to the running run’s CancellationTokenSource.

IRunErrorClassifier

Converts a raw run error into a class and a clustering fingerprint.

IRunEventSink

Receives run events as they are written, in addition to IRunStore.

IRunInputStore

Stores a run’s input messages. The source of replay.

IRunJudge

The extension point that scores a completed production run.

IRunPricingResolver

Computes the cost from a model+usage pair. Pricing order: the model catalog, then the Tracon:Pricing configuration.

IRunScoreStore

The store for run and message scores (RunScore).

IRunStore

Store for run records and the event stream.

ISessionStore

The store for serialized agent sessions.

ISingletonLeaseStore

The lease store that keeps a named job running on a single instance across the cluster.

ISkillScriptGrantStore

The store for skill script execution grants.

ISpeechSynthesizer

A provider that generates speech from text.

ISpeechTranscriber

A provider that transcribes speech to text.

ISqlPersistenceDiagnostics

Defines optional diagnostics for the active SQL persistence provider.

IStatePreflightReader

Reads the stored state generations WITHOUT writing anything, so an operator can ask “can this build still read my data” BEFORE upgrading.

IStructuredResponseValidator

Validates a run’s response against the agent’s requested AgentResponseFormat before the run closes.

ITenantContext

Resolves the current request’s tenant. In a single-tenant setup, returns a fixed value and requires no additional configuration.

ITenantCredentialModelProvider

A model provider that can build clients from resolved per-tenant credentials.

ITenantEgressPolicyStore

The store for per-tenant model provider egress policies.

ITenantProviderBindingStore

The store for per-tenant model provider bindings (BYOK).

ITenantStore

The store for tenant registrations.

IToolApprovalPresenter

Resolves a human-readable presentation for a tool call that is about to publish an approval request — turning, for example, { "orderId": "ORD-1001" } into “Cancel order for Priya Shah”.

IToolApprovalRuleStore

The store for persistent approval rules.

IToolArgumentsValidator

Validates a tool call’s arguments before the call runs.

IToolAuthorizationHandler

Decides whether a tenant/user may call a specific tool.

IToolRegistry

The registry of tools registered in code.

ITraceStore

The store for persisted spans.

ITraconBuilder

The fluent chain that configures Tracon. Returned from the AddTracon call.

ITraconDrainState

Reports whether the process has begun a graceful shutdown drain.

ITraconUiProvider

Source that serves the management UI’s static assets.

IVectorSearchStore

The embedding-based semantic search store.

IVersionedAgentSource

An IAgentSource that can resolve a specific definition version. Only sources that keep a version history implement it. A source without version history need not implement this interface.

IVoiceHealthCheck

Checks the voice provider’s reachability.

IVoicePricingReader

Reads the configured voice model’s pricing.

IVoiceSessionStore

Stores the summary record of real-time voice connections.

IWebhookPublisher

The component that publishes an event to its subscriptions.

IWebhookStore

The store for webhook subscriptions and delivery history.

IWorkflowCheckpointStore

The store for workflow checkpoints.

IWorkflowDefinitionStore

The store for workflow definitions stored in the database.

IWorkflowFunctionCatalog

The registry of workflow function nodes registered in code.

IWorkflowRunner

Reads the workflow catalog and runs workflows.

AgentDefinitionOrigin

Tells where an agent definition came from.

AgentParameterKind

The data kind of an AgentParameter.

AgentResponseFormatKind

The requested format of an agent response.

ApiKeyScope

An authority scope an API key may open.

ApprovalStatus

The status of a pending approval request.

AuditChainStatus

The result of walking a tenant’s audit trail hash chain.

CanaryDecisionKind

Defines the outcome of a canary evaluation.

CompactionStrategyKind

The kind of context compaction strategy that can be bound to an agent definition.

ContentGuardAction

The decision a guard can make.

ContentGuardDirection

The direction of a content guard check.

ContentGuardSource

Where the text handed to an IContentGuard came from.

EvalCaseDiffKind

The bucket an aligned case falls into within an EvalRunDiff.

EvalCaseSource

The reason an EvalCase was promoted from a production run.

EvalRunDiffUnavailableReason

Why two eval runs cannot be compared.

EvalRunStatus

The status of an eval run.

ExperimentStatus

Defines the lifecycle status of an A/B experiment.

IdempotencyState

The four possible states of an idempotency key.

InboundTriggerOutcome

The outcome of validating an inbound trigger request.

InboundTriggerPayloadMode

How an inbound trigger’s request body becomes the agent/workflow message.

InboundTriggerTargetKind

What kind of target an inbound trigger fires.

JobItemStatus

The status of a batch job item.

JobStatus

The status of a queued job.

LiveVoiceAppendChannel

The channel a live append is written to.

LiveVoiceDelegationMode

How a live model hands heavier work back.

LiveVoiceEventKind

What a live voice sideband event says.

McpOAuthAuthorizationMode

The MCP OAuth authorization flow.

McpOAuthOperationStatus

The result status of an OAuth authorization request.

McpOperationStatus

The result status of an MCP request.

McpTransportMode

The way a connection to an MCP server is made.

ModelProviderHealthStatus

A provider’s checked reachability status.

OpenAIApiSurface

Selects which of the two OpenAI chat APIs is used.

PiiPatterns

The built-in pattern families for Tracon.PatternContentGuard.

PricingSource

Reports where a run’s cost pricing came from.

ProtectedColumn

A database column IContentProtector can be applied to.

ProviderRetryDecision

Whether a provider failure should move to the next fallback link.

QuotaMetric

The metric a quota is exceeded by.

QuotaPeriod

The interval at which a quota’s counter resets.

RateLimitPartitionKind

Which key the rate limit is partitioned by.

ReplayToolMode

How tools are handled during replay.

RunAccess

The kind of access a RunAuthorizationRequest asks about.

RunErrorClass

A run error’s class.

RunEventType

Event types produced during a run. The user interface maps these directly onto visual elements, so the values must stay stable.

RunKind

Reports what a runs row records.

RunPromotionStatus

Defines the outcome of RunToCasePromoter.PromoteAsync.

RunReplayOutcome

Represents the outcome of a replay preparation.

RunScoreBucket

A closed, low-cardinality set of time buckets for a score trend series.

RunScoreKind

The shape of the value a RunScore carries.

RunScoreTarget

Which target a score belongs to — the filter RunScoreQuery.Target narrows to.

RunStatus

Status of a run.

SessionAccess

The kind of access a SessionAuthorizationRequest asks about.

SessionBranchStatus

The outcome of a branching attempt.

SpeechUsageSource

The source of a speech measurement.

StatePreflightTarget

Names a table a state preflight can read.

TimeSeriesBucket

The bucket width for a time-series query.

ToolApprovalPolicyDecision

The outcome of a code-defined approval policy (ToolApprovalContext).

ToolArgumentOperator

A comparison operator for a ToolArgumentCondition.

ToolEffect

Classifies the blast radius of a tool call.

TraceSpanKind

A span’s OpenTelemetry kind. Values are stored in the database as smallint; the numbers are stable.

TraceSpanStatus

A span’s result status. smallint in the database.

ValidationSeverity

The severity of a ValidationMessage.

VoiceSessionEndReason

The reason a voice connection closed.

WebhookDeliveryStatus

The status of a webhook delivery attempt.

WorkflowEdgeKind

Represents the kind of an edge.

WorkflowKind

Represents the built-in workflow patterns that can be defined through the UI.

WorkflowNodeKind

Represents the role of a graph node.

WorkflowRequestForm

Defines how the UI presents a pending request.