feat(inference): unified provider router (v0.18.2) - #45
Merged
Conversation
…v0.18.2) Adds clawmes/lib/inference.py — a single chat_completion() that selects the OpenAI-compatible backend at call time, so tools stop hardcoding one provider. * Selection: CLAWMES_LLM_PROVIDER (venice|opengateway); unset -> auto (Venice when VENICE_API_KEY set, else OpenGateway). * VeniceError / OpenGatewayError normalized to one InferenceError (.code, .provider). * Routed both existing inference call sites through it: /research narrative summary and /agent --ai intent extractor (and thus clawmes_info op=research). With Venice configured, those now run on Venice. Gate: 4641 passed, 8 skipped; 100% coverage; ruff check + format clean; plugin.yaml byte-identical. Tool count unchanged (53).
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Completes the "wire everything" for inference. Adds
clawmes/lib/inference.py— onechat_completion()that picks the OpenAI-compatible backend at call time, so tools no longer bind to a single provider.Changes
CLAWMES_LLM_PROVIDER(venice|opengateway); unset → auto (Venice whenVENICE_API_KEYis set, else OpenGateway).VeniceError/OpenGatewayError→ oneInferenceError(.code,.provider)./researchnarrative summary and the/agent --aiintent extractor — and thereforeclawmes_info op=research. With Venice configured, those run on Venice.CLAWMES_LLM_PROVIDER.Gate
4641 passed, 8 skipped; 100% coverage; ruff clean; plugin.yaml byte-identical; tool count unchanged (53). The existing research/agent tests stay green via the router's lazy provider resolution; the two import-failure tests retargeted to the router module.