Skip to content

feat(llm): provider identity and capability contracts #304

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
furgalep wants to merge 4 commits into from
Closed

feat(llm): provider identity and capability contracts #304

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0524b14
feat(llm): provider identity and capability contracts
furgalep Sep 7, 2026
da70a68
fix(llm): normalize injected compat groups; document JsonValue and id…
furgalep Sep 7, 2026
34d0434
feat(llm): corpus-hardened identity parsing with conformance fixtures
furgalep Sep 7, 2026
1127639
feat(llm): deployment-spelling corpora for Azure, Vertex AI, and Bedrock
furgalep Sep 7, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion examples/cybergym/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ readme = "README.md"
requires-python = ">=3.12,<3.14"
dependencies = [
"nooa[tracing] @ git+https://github.com/NVIDIA-NeMo/labs-OO-Agents.git@8229922d7274628c9be83f745589b40852680d60",
"pydantic>=2.5.0",
"pydantic>=2.11.0",
]

[project.optional-dependencies]
Expand Down
2 changes: 1 addition & 1 deletion packages/nooa-memory/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ readme = "README.md"
requires-python = ">=3.12,<3.14"
dependencies = [
"nooa",
"pydantic>=2.5.0",
"pydantic>=2.11.0",
"numpy>=1.24.0",
]

Expand Down
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ classifiers = [
"Topic :: Scientific/Engineering :: Artificial Intelligence",
]
dependencies = [
"pydantic>=2.5.0",
"pydantic>=2.11.0",
# context_blocks + unifiedllm now ship as nooa.context_blocks /
# nooa.unifiedllm subpackages — pull their formerly-external deps in.
# >=1.97.0: routes GPT-5.4 tool calls through Responses and replays reasoning_items;
Expand Down
33 changes: 33 additions & 0 deletions src/nooa/unifiedllm/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,22 @@
# SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
from nooa.unifiedllm.contracts import (
OPAQUE_REPLAY_KEY_VERSION,
ModelCompatGroup,
NormalizedModel,
ProviderIdentity,
ReasoningCapabilities,
ReasoningKind,
ReasoningRecord,
ReasoningReplayMode,
UnknownProviderIdentityError,
compat_group_for,
derive_opaque_replay_key,
get_reasoning_capabilities,
parse_model_string,
register_compat_group,
register_reasoning_capabilities,
)
from nooa.unifiedllm.fake import FakeLLMClient
from nooa.unifiedllm.http_config import HttpConfig
from nooa.unifiedllm.registry import (
Expand Down Expand Up @@ -30,6 +47,22 @@
)

__all__ = [
# Provider contracts (identity and capability types)
"ModelCompatGroup",
"NormalizedModel",
"OPAQUE_REPLAY_KEY_VERSION",
"ProviderIdentity",
"ReasoningCapabilities",
"ReasoningKind",
"ReasoningRecord",
"ReasoningReplayMode",
"UnknownProviderIdentityError",
"compat_group_for",
"derive_opaque_replay_key",
"get_reasoning_capabilities",
"parse_model_string",
"register_compat_group",
"register_reasoning_capabilities",
# Core classes
"UnifiedLLM",
"CompletionClient",
Expand Down
Loading