feat(memory_manager): add OrcaRouter as a named memory-manager backend - #76
Open
XiaoHuo888-hue wants to merge 1 commit into
Open
feat(memory_manager): add OrcaRouter as a named memory-manager backend#76XiaoHuo888-hue wants to merge 1 commit into
XiaoHuo888-hue wants to merge 1 commit into
Conversation
Add an OpenAI-compatible OrcaRouter provider, mirroring the existing DeepSeek backend. OrcaRouter exposes an OpenAI-compatible endpoint at https://api.orcarouter.ai/v1 with sk-orca- prefixed keys. - Register `orcarouter` in MemoryManagerConfig._model_list - Add `orcarouter_base_url` config slot in BaseMemoryManagerConfig - Add OrcaRouterManager (subclasses DeepseekManager) + factory mapping - Add unit tests + README docs Co-Authored-By: Claude <noreply@anthropic.com> Signed-off-by: XiaoHuo888-hue <jinhao.song@myflashcloud.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add OrcaRouter as a named memory-manager backend
OrcaRouter is an OpenAI-compatible LLM gateway (API base
https://api.orcarouter.ai/v1, keys prefixedsk-orca-). It also runs gateway-level, zero-trust security for AI agents on the same endpoint — screening every prompt/response and governing every tool call on a default-deny basis, with no application code changes.This PR registers OrcaRouter as a first-class named backend for
MemoryManagerConfig, mirroring the existing DeepSeek provider — so users can select it viamodel_name: "orcarouter"instead of manually pointing a generic OpenAI-compatible endpoint.Changes
src/lightmem/configs/memory_manager/base_config.py: addorcarouter_base_urlconfig slot (defaults tohttps://api.orcarouter.ai/v1)src/lightmem/configs/memory_manager/base.py: registerorcarouterinMemoryManagerConfig._model_listsrc/lightmem/factory/memory_manager/orcarouter.py: newOrcaRouterManager(subclassesDeepseekManager; OpenAI client, default modelorcarouter/auto, key fromORCAROUTER_API_KEYorconfig.api_key)src/lightmem/factory/memory_manager/factory.py: maporcarouter→OrcaRouterManagertests/test_orcarouter.py: unit tests for config acceptance, factory instantiation, defaults, custom base URL, and missing-key errorREADME.md: news entry + supported-backends table + config exampleExample
Validation
pytest tests/— 7 passed (2 existing + 5 new)flake8/isortclean on new files;py_compileOKOrcaRouterManagerpath returnedORCA-LIVE-OKwith valid token usage (HTTP 200)Disclosure: I'm an engineer on the OrcaRouter team.