ouyangbo/hermes-agent
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

fix(relay): upgrade to 0.8.1

Browse Source 
Signed-off-by: Alex Fournier <afournier@nvidia.com>
This commit is contained in:
Alex Fournier
2026-08-27 16:37:20 -04:00
parent a24c12d14f
commit 31e7237adb
12 changed files with 272 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/observability/relay-shared-metrics.md
+14 -10
View File
@@ -18,18 +18,22 @@ as a no-op compatibility alias for existing installation commands.
> longer activate exporters. Without the new variable, Hermes does not run
> Relay plugin discovery, configuration layering, middleware, or exporters.
Hermes requires NeMo Relay 0.7.1 or later within the 0.7 release line. That
release establishes the lossless provider-codec contract used for Anthropic
Messages, OpenAI Chat Completions, and OpenAI Responses requests.
Hermes requires NeMo Relay 0.8.1 or later within the 0.8 release line. That
line provides the provider-codec and canonical tool-result contracts Hermes
uses for managed provider and tool calls.
## Runtime Dependency and Data Boundary
Hermes installs the platform-specific `nemo-relay` native wheel from the
bounded `>=0.7.1,<0.8` dependency range. The published package is built from
bounded `>=0.8.1,<0.9` dependency range. The published package is built from
the [NVIDIA NeMo Relay repository](https://github.com/NVIDIA/NeMo-Relay).
Unsupported platforms use the explicit no-op runtime described above rather
than downloading a different implementation.
Operator-supplied typed native plugins must be rebuilt for Relay 0.8. `grpc-v1`
workers must be regenerated and rebuilt when they use tool callbacks, tool
execution intercepts, or manual tool-end APIs.
When Relay managed execution is active, the provider request and response pass
through that native module in the Hermes process so configured interceptors can
operate on the real call. This is separate from the shared-metrics data
@@ -55,12 +59,12 @@ opt-in. Set `HERMES_NEMO_RELAY_PLUGINS_TOML` to a selected `plugins.toml` to
activate configured middleware, exporters, or dynamic plugins. When the
variable is unset, Hermes does not invoke Relay's plugin initializer, so Relay
does not perform plugin configuration discovery or layering. When it is set
and the selected file loads successfully, Relay performs its normal static
`plugins.toml` discovery and layers the selected static configuration over the
discovered configuration. Dynamic `[[plugins.dynamic]]` records are loaded
from the selected file only. If the selected file cannot be loaded, Hermes
reports the error and does not invoke Relay initialization or fall back to
ambient discovery.
and the selected file loads successfully, Relay discovers supported user and
system `plugins.toml` files and layers the selected static configuration over
them. Repository-local `.nemo-relay/plugins.toml` files are ignored. Dynamic
`[[plugins.dynamic]]` records are loaded from the selected file only. If the
selected file cannot be loaded, Hermes reports the error and does not invoke
Relay initialization or fall back to ambient discovery.
## Session-Span Segmentation for Continuous Sessions