Commit Graph

13 Commits

Author SHA1 Message Date
Alex Fournier 14bed44c8c Reapply "feat(observability): integrate NeMo Relay runtime and shared metrics"
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-27 21:10:51 -07:00
Jeffrey Quesnelle 841a5a744a
Revert "feat(observability): integrate NeMo Relay runtime and shared metrics" 2026-07-27 22:28:08 -04:00
Alex Fournier 4fe4b0dca7 Merge origin/main into feat/hermes-relay-shared-metrics
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-27 08:12:37 -07:00
embwl0x e369d6ea3f feat(delegate): expose redacted child tool history 2026-07-26 20:36:47 -07:00
Alex Fournier 6fa96916a8 docs(relay): disclose managed data boundary
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-23 14:05:11 -07:00
Alex Fournier 43d994986e fix(telemetry): keep consent profile-owned
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-23 14:04:07 -07:00
Alex Fournier bba63d8786 fix(telemetry): prune expired local metrics
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-23 14:01:41 -07:00
Alex Fournier e1a6becf86 docs(telemetry): disclose local profile identity
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-23 13:58:22 -07:00
Alex Fournier 6efc5fe0af fix(runtime): preserve provider payloads through Relay
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-21 09:25:22 -07:00
Alex Fournier 9bc521b138 refactor(runtime): manage Relay LLM tool and subagent execution
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-19 08:57:38 -04:00
Alex Fournier 056e7df0e0 fix(observability): harden Relay metrics isolation and aggregation
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-19 08:55:07 -04:00
Alex Fournier 64faff6768 refactor(observability): move Relay runtime ownership into core
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-19 08:54:49 -04:00
Bryan Bednarski 0d9b7132ff feat(observability): observer-grade telemetry hooks + NeMo-Relay plugin
Adds backend-neutral observer hooks for plugins: session, turn, API
request, tool, approval, and subagent lifecycle events with stable
correlation IDs (session_id, task_id, turn_id, api_request_id,
tool_call_id, parent/child subagent ids). Extends VALID_HOOKS with
api_request_error and subagent_start.

Hot path is zero-cost when no plugin subscribes: has_hook()/presence
checks gate all payload construction, request payloads are returned
by reference when no middleware rewrites, and the sanitized response
payload no longer embeds raw response objects.

Bundles the optional NeMo-Relay observability plugin
(plugins/observability/nemo_relay) as an in-repo consumer of the new
hooks, peer to the existing langfuse plugin. Fails open when the
optional nemo-relay package is not installed.

Authored-by: Bryan Bednarski <bbednarski@nvidia.com>
Salvaged from #29722 onto current main.
2026-06-03 06:36:46 -07:00