Add agent run dashboard and telemetry setup guide

frontend/README.md

@@ -66,7 +66,7 @@ This creates `build.zip` with a top-level `dist/` directory, including `dist/ind
 - Datasets: search, create logs/metrics/traces with an optional custom partition, manage information and ingestion/storage statistics, inspect schema, explore, set/clear retention, configure/disable hot tier when the server enables it, and delete with typed name confirmation. Time partitions cannot be set at creation. Static schema upload, tags/labels, existing partition editing and index management are not supported.
 - Dashboards: server-backed lists and detail routes, search/tags/favourites/sort/pagination, ownership, full-document saves with conflict resolution, SQL and PromQL tiles, six variable types, URL time ranges and selections, classic import/export, and explicit migration of old browser-local dashboards. Demo dashboards use independent in-memory state per client.
 - Team: native users and one-time passwords, role and privilege management, default OIDC role configuration, provider group mappings and role provenance, and API key creation/copy/deletion with configurable expiration from 30 minutes to 90 days or no expiration. New UI-created keys default to 90 days; existing keys keep their original lifetime. Search and 25-row pagination apply to every tab; authorization stays with the backend.
-- Agents: schema-discovered GenAI telemetry datasets, bounded recent records, time ranges, local search, record inspection and trace handoff.
+- Agents: schema-discovered GenAI datasets, related spans grouped into runs, successful/failed/incomplete status, observed duration, models and recorded token usage. Run details include the span tree, model and tool calls, errors, captured conversation and raw fields. Search/status/model filters and captured time bounds survive navigation between Agents, Traces and Logs. Missing telemetry and bounded samples are explicit; evaluations and cost estimates remain deferred.
 - Cluster: registered node reachability and resource metrics with independent request states; read-only.
 - Errors: grouped issues, full-range frequency analytics, and occurrence inspection for OTLP traces and recognized log severity schemas, plus paginated OTLP error spans and trace handoff. Groups match exact service, error type and message values; issue assignment and resolution are not persisted.
 - Workspace setup: `/onboarding` discovers accessible datasets and opens the matching explorer; `/new` explains server scope and provides connection/setup actions. Hosted workspace creation is not exposed by this server.

frontend/docs/api-contracts.md

@@ -215,7 +215,7 @@ See [observability validation](observability-validation.md) for bounds, caps, er
 
 ## Native operations and setup screens
 
-Agents uses existing dataset list, schema, metadata and SQL requests. Discovery recognizes flattened `gen_ai.agent.name`, `gen_ai.agent.id`, `gen_ai.operation.name`, `gen_ai.request.model` and `gen_ai.tool.name`; direct dataset links defer the full schema scan until the selector is focused or rescanned. Discovery is limited to four concurrent schema requests and skips forbidden/missing datasets. Queries quote dataset/field identifiers, use the dataset time partition, and return at most 100 recent non-null GenAI records in captured UTC bounds. Search applies only to those loaded records. Run aggregation, evaluations and pricing are not inferred. Unknown demo dataset names cannot return synthetic records.
+Agents uses existing dataset list, schema, metadata and SQL requests. Discovery recognizes flattened `gen_ai.agent.name`, `gen_ai.agent.id`, `gen_ai.operation.name`, `gen_ai.request.model`, `gen_ai.response.model` and `gen_ai.tool.name`; direct dataset links defer the full schema scan until the selector is focused or rescanned. Discovery is limited to four concurrent schema requests and skips forbidden/missing datasets. Queries quote dataset/field identifiers and use the dataset time partition. Up to 100 recent trace IDs containing GenAI telemetry seed a query for related spans, including children without GenAI attributes; the outer response is bounded to 1,000 flattened records. Explicit half-open UTC predicates preserve exact time bounds inside the minute-expanded query envelope. Search, status and model filters apply to the loaded runs. Run normalization deduplicates span identities before counting usage, preserves event content and displays absent values distinctly from zero. A unique outer agent span can certify recovery within its descendants: explicit completed OK permits recovered child errors, which remain visible. Failed or incomplete ancestors and separate roots retain their outcome. Completed UNSET spans are accepted; missing status or completion remains incomplete. Missing identity, parents, clipped time coverage and the separate 100-trace / 1,000-record caps are disclosed. Evaluations and cost estimates remain deferred until telemetry and pricing inputs are reliable. Unknown demo dataset names cannot return synthetic records.
 
 Cluster reads `GET /api/v1/cluster/info` and `/api/v1/cluster/metrics` through the shared authenticated client. The first returns node identity, storage/staging paths, reachability and nullable status/error text. Metrics are independent: a denied metrics request does not hide node health. Nonfinite Rust metric values serialized as null display as unavailable per field. Missing cluster routes (404/405) show a deployment-mode explanation; 403 and 401 retain shared permission/session handling. No node deletion is exposed.
 

frontend/docs/prism-parity.md

@@ -126,15 +126,15 @@ The [observability validation record](observability-validation.md) documents ori
 
 The previously classic-only routes below now resolve to native pages. `classicUi.ts` marks them `limited`, distinguishing a usable native subset or capability explanation from full classic parity. The existing Traces, APM, Add data and telemetry-aware dataset routes retain their behavior.
 
-| Routes                        | Native behavior                                                                                                                                                                                  | Deliberate limits                                                                                                                                                                                                         |
-| ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `/agents`, `/agents/:dataset` | Discover flattened GenAI fields through dataset schemas; query the latest 100 telemetry records in a selected time range; search loaded records; inspect full records; open compatible trace IDs | Individual events/spans, not classic run aggregation, evaluations, pricing or token-cost analytics. Demo uses explicit synthetic fixtures.                                                                                |
-| `/cluster`                    | Show registered distributed nodes, reachability, status, storage/staging locations and resource metrics from the existing cluster endpoints                                                      | Read-only. Standalone servers can report cluster administration unavailable. Node and metrics failures remain separate.                                                                                                   |
-| `/errors`, `/errors/:dataset` | Discover trace and log error datasets; group issues, query full-range frequency, inspect occurrences, sort/page issues and OTLP spans, and open trace or SQL investigations                      | Exact service/type/message grouping with recognized severity schemas; persistent issue resolution, fuzzy grouping and cross-dataset correlation remain unavailable. See [Errors contracts and tests](error-analytics.md). |
-| `/onboarding`                 | Discover accessible datasets, link each to its confirmed explorer, and guide ingestion and team setup                                                                                            | Dataset presence is not presented as proof of event arrival. Existing Add data owns ingestion configuration and verification.                                                                                             |
-| `/new`                        | Explain server workspace scope; open connection settings or native setup                                                                                                                         | No API in this checkout provisions a separate hosted workspace.                                                                                                                                                           |
-| `/keystone`, `/keystone/:id`  | Native availability page and classic investigation handoff where available                                                                                                                       | No supported investigation/conversation API in this checkout. No claim that an ID exists or is accessible.                                                                                                                |
-| `/settings/llm-key`           | Native availability pages and deployment-dependent classic handoff                                                                                                                               | No provider-key management API. No credentials are read, stored or submitted.                                                                                                                                             |
+| Routes                        | Native behavior                                                                                                                                                                                                                | Deliberate limits                                                                                                                                                                                                         |
+| ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `/agents`, `/agents/:dataset` | Discover GenAI datasets; group related spans into runs; inspect status, duration, models, tokens, span trees, calls, errors, captured conversation and raw fields; preserve time/filter context across Agents, Traces and Logs | Bounded telemetry sample, with incomplete/missing fields disclosed. Evaluations and cost estimates are deferred. Demo uses explicit synthetic fixtures.                                                                   |
+| `/cluster`                    | Show registered distributed nodes, reachability, status, storage/staging locations and resource metrics from the existing cluster endpoints                                                                                    | Read-only. Standalone servers can report cluster administration unavailable. Node and metrics failures remain separate.                                                                                                   |
+| `/errors`, `/errors/:dataset` | Discover trace and log error datasets; group issues, query full-range frequency, inspect occurrences, sort/page issues and OTLP spans, and open trace or SQL investigations                                                    | Exact service/type/message grouping with recognized severity schemas; persistent issue resolution, fuzzy grouping and cross-dataset correlation remain unavailable. See [Errors contracts and tests](error-analytics.md). |
+| `/onboarding`                 | Discover accessible datasets, link each to its confirmed explorer, and guide ingestion and team setup                                                                                                                          | Dataset presence is not presented as proof of event arrival. Existing Add data owns ingestion configuration and verification.                                                                                             |
+| `/new`                        | Explain server workspace scope; open connection settings or native setup                                                                                                                                                       | No API in this checkout provisions a separate hosted workspace.                                                                                                                                                           |
+| `/keystone`, `/keystone/:id`  | Native availability page and classic investigation handoff where available                                                                                                                                                     | No supported investigation/conversation API in this checkout. No claim that an ID exists or is accessible.                                                                                                                |
+| `/settings/llm-key`           | Native availability pages and deployment-dependent classic handoff                                                                                                                                                             | No provider-key management API. No credentials are read, stored or submitted.                                                                                                                                             |
 
 Network access (`/settings/network-access`) edits the real outbound alert-target policy via `GET` and `PUT /api/v1/alert-target-policy`. It is distinct from ingress access control. The full policy includes private-IP and invalid-TLS switches plus allowed/denied domains and CIDRs. Backend authorization and validation remain authoritative; failed saves retain the draft. The policy cache is per server node and loaded at startup; cross-node propagation is a backend limitation, not asserted by the UI.