a97abcd55a
Merge upstream main into model metrics
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
# Conflicts:
# tests/agent/test_auxiliary_relay.py
2026-08-02 20:10:47 -07:00
fdfddb55cb
fix(moa): carry completed responses through the managed Relay path
...
Under managed Relay execution the provider factory runs lazily inside
provider_stream() on the Relay session's event loop. The MoA facade's
auxiliary call_llm(stream=True) is invoked from that callback, so the
eager final_response check added for the non-managed path never fires:
the inner ManagedLlmStream is returned to the outer stream, which then
synchronously iterates it on the same loop thread and dies with
RuntimeError: Cannot run the event loop while another loop is running
(the completed response effectively trapped one level deeper).
stream_current() now detects a running event loop and returns the raw
factory result instead of nesting a ManagedLlmStream: the outer managed
stream already provides Relay tracking for the enclosing attempt, and
its own completed_response_predicate traps the completed response as
final_response — the same contract the main streaming worker consumes
(chat_completion_helpers reads stream.final_response after the chunk
loop). Nested managed streams remain supported for genuinely streaming
providers via the outer stream's own iteration.
Adds managed-execution regressions using the retained relay_turn
fixture: direct completed-response trapping, and the nested
facade-shaped stream_current call.
2026-07-31 22:30:33 -07:00
ada3663ce7
fix(moa): unwrap completed responses in the auxiliary streaming path
2026-07-31 22:30:33 -07:00
43d29a37c8
fix(observability): include auxiliary model routes
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-31 06:58:41 -07:00
5e34fa2d5c
fix(relay): preserve provider stream errors
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-28 09:58:43 -07:00
b1a5d67e71
Merge upstream main into fix/hermes-relay-anthropic-context
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-28 08:10:58 -07:00
eda54775e2
fix(relay): isolate streaming callback contexts
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-27 21:11:04 -07:00
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
841a5a744a
Revert "feat(observability): integrate NeMo Relay runtime and shared metrics"
2026-07-27 22:28:08 -04:00
3be8a2f5f9
refactor(relay): serialize provider objects by capability
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-27 08:18:41 -07:00
bfae9c2572
fix(relay): ignore rewrites after codec baseline failure
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-27 08:17:21 -07:00
ec6c881453
fix(relay): preserve buffered provider stream chunks
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-27 08:16:16 -07:00
a3ef27ab70
fix(relay): preserve intentional request removals
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-23 14:22:49 -07:00
06ed41aa1f
fix(relay): preserve managed cancellation signals
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-23 14:21:37 -07:00
ad6fb26681
fix(relay): fence bypassed stream chunks
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-23 14:09:33 -07:00
4788994bd2
fix(relay): preserve managed callback context
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-23 13:53:59 -07:00
1500ce163c
fix(relay): normalize rewritten LLM responses
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-23 13:44:27 -07:00
e862099dff
fix(relay): merge Anthropic stream usage
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-23 13:32:44 -07:00
c789bdd38a
fix(relay): close managed provider streams
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-23 13:32:03 -07:00
9dfe690125
fix(relay): preserve provider request extensions
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-23 13:24:19 -07:00
1c6a96032c
fix(relay): preserve successful managed results
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-23 13:12:50 -07:00
afd0b3ecd4
fix(observability): keep Relay session headers local
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-22 14:35:55 -07:00
537425ebe4
fix(runtime): close abandoned Relay streams
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-22 10:32:49 -07:00
27c7c877c5
fix(runtime): close failed auxiliary Relay streams
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-21 14:40:19 -07:00
6efc5fe0af
fix(runtime): preserve provider payloads through Relay
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-21 09:25:22 -07:00
774bcac352
fix(runtime): preserve native streaming responses
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-19 09:23:03 -04:00
2c8fd38f2e
fix(observability): defer logical LLM completion until validation
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-19 09:00:27 -04:00
55b7903cf7
fix(observability): harden Relay terminal lifecycle metrics
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-19 08:59:42 -04:00
4dedaa4237
refactor(runtime): consolidate Relay lifecycle ownership
...
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-19 08:59:06 -04:00
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
AKAZIK-py
Jeffrey Quesnelle