feat(inference): real local Ollama backend for the InferenceGateway adapter - #128
Merged
Conversation
…dapter ollama_backend() serves a model on the local Ollama daemon — no egress, sovereign-local. Injectable HTTP transport so it's testable without a live daemon; any failure (daemon down, malformed reply) raises → the gateway turns it into an audited denial, never a silent success. Consent still gates even with a live backend. scripts/validate-inference-backends.py (9 controls) wired into make validate. Local inference now actually executes.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Local inference now actually runs — the deepen-the-local-side step.
src/agent_machine/inference_backends.py—ollama_backend()serves a model on the local Ollama daemon (/api/generate, no egress, sovereign-local). HTTP transport is injectable, so it's testable without a live daemon; any failure (daemon down, malformed response) raises → the gateway (feat(inference): local InferenceGateway adapter — fail-closed, audits every call #127) turns it into an audited denial, never a silent success. Consent still gates even with a working backend.scripts/validate-inference-backends.py— 9 controls (served output + usage mapping + correct/api/generatepayload; unreachable → denied audit; malformed → denied audit; no-consent-still-refused). Wired intomake validate.Verified:
make validate-inference-backends→ 9/9 pass.