Skip to main content
Unlisted page
This page is unlisted. Search engines will not index it, and only users having a direct link can access it.
Version: 11.3.0

Request Log

The Request Log lists the traffic your agents send through HYPR AgentPass™: every inference call to a language model, and every MCP tool call. Each request is attributed to the agent that made it and to that agent's supervisor. Open it from Oversight → Request Log.

This page is the reference for administrators and operators. For a supervisor's view of the page, and a closer look at one request, see Viewing the Request Log.

The Request Log: the time range, summary cards, the request volume chart and the request stream

Who Sees What​

The Request Log permission decides whose requests a role sees. See Permissions by Role.

RoleRequests shownFilters available
AgentPassAdmin, AgentPassOperatorEvery supervisor's requestsType, classification and supervisor
AgentPassSupervisorRequests from agents the supervisor is responsible forType

A role whose Request Log permission is limited to its own records sees only requests supervised by that user, on every part of the page.

The classification filter appears only for a role that can view Data classification, and only when your organization has classification tiers. The supervisor filter appears only for a role that sees every supervisor's requests, and only when more than one supervisor has traffic in the time range.

The Page Header​

The header sets what the rest of the page covers:

  • Time range. 1h, 24h or 7d. The default is 24h. The range applies to the summary cards, the chart, the stream and the supervisor filter.
  • Refresh. Fetches the latest activity, and returns the stream to its first page. The page does not refresh itself.
  • Updated. How long ago the page last fetched its data.
How far back the log reaches

The time range reaches back up to 7 days. The platform sets how long each category of event is kept. See Data Management. A request older than the time range can still be opened from a policy decision that links to it. See Open a Request from a Policy Decision.

Summary Cards​

Five cards summarize the time range. Hover over a card for its breakdown.

CardShowsOn hover
HealthThe share of requests that succeeded. The label names the time range, such as success last 24hHow many of all requests succeeded
RequestsThe number of requestsInference calls and tool calls, separately
TokensInput and output tokens togetherInput and output tokens, separately
Avg latencyThe average latencyAverage across all requests
Active agentsThe number of distinct agents that sent trafficHow many requests carried no agent identity, or All requests attributed

The cards follow the time range only. The stream filters do not change them.

Request Volume​

Request volume plots the requests in the time range over time. Switch the view between Requests, which separates successes from errors, and Models, which stacks inference calls by model. A model the gateway could not identify shows as Unknown.

Like the summary cards, the chart ignores the stream filters.

Request Stream​

The Request stream lists individual requests, newest first. It loads 50 at a time. Load more, at the end of the list, fetches the next set.

The Request stream header with the supervisor filter, the Any classification filter and the All, Inference and MCP tool tabs

Filter the Stream​

These filters narrow the stream. Each one returns the stream to its first page.

FilterOptions
TypeAll, Inference or MCP tool
ClassificationAny classification, or one of your organization's tiers
SupervisorAll supervisors, or one supervisor. The list is searchable

The classification filter matches the tier a call carried when it was made. See Classifying the Data Your Tools Handle.

Columns​

Each row shows these columns, from left to right.

ColumnWhat it shows
StatusThe status code. A request that did not succeed also shows its category. See the following table
TimeThe time of day for today's requests, otherwise the date and time. Hover for the full timestamp
AgentThe agent's name, or Unattributed. An AWS Bedrock or AWS Bedrock Mantle request adds an icon that opens its AWS caller details. See Connecting AWS Bedrock
Model / MCPThe model, or the MCP tool or method. An inference call that asked for tools adds how many
DataThe classification tier and tags the call carried
SupervisorThe supervisor responsible for the agent
LatencyA bar on a 0 to 12 second scale, with the value. Hover for model and gateway time
SizeThe size of the request
TokensInput and output tokens

The status category tells you how a request ended.

CategoryStatus
Policy403
Rate limit429
Timeout504
ServerAny other 5xx status
ClientAny other 4xx status
RedirectA 3xx status

Request Detail​

Click a row to open Request detail. The row stays highlighted while the panel is open.

The panel opens with how the request ended, such as Succeeded, Blocked by policy or Timed out. It then shows:

  • The latency, time to first byte, gateway time, tokens and payload size
  • A What happened timeline
  • The call's data classification, and what its session had already read, when they apply
  • The coding session the request belongs to, when the agent reported one
  • The tool calls the model requested
  • The captured Request and Response, with their headers and bodies, and the whole body behind a cut one when your deployment keeps it
  • What the upstream returned, when it differs from what the gateway returned
  • The supervisor responsible for the agent, as Supervised by

For what each part shows, and how to read the captured bodies, see Inspect a Single Request.

Open a Request From a Policy Decision​

A policy decision links to the request that caused it. Following that link opens the Request Log with the request's detail panel already open. It opens even when the request falls outside the current time range. Closing the panel returns you to the stream.

See Investigating a Policy Decision.

When Export Files Stop Being Written​

A role that can view Data management sees a banner on this page when a gateway node cannot write its export files. The banner reads Event export files are not being written, and names the cause. It also gives the number of failed writes, how many nodes are affected and when the failures started.

The export files for that period are incomplete

Requests still reach the Request Log while the banner shows. The export files you collect for the same period are missing records. Check the export directory on the affected gateway nodes, including its free disk space and write permissions.

The banner clears once the node writes its export files again. It also appears on the Data Management page.