mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-18 21:58:58 -04:00
3fa7b2955c
Squashed feat/pii-ner-tier-engine rebased onto master (was 45 commits; see backup/pii-ner-tier-engine-prerebase). Net change: - privacy-filter.cpp: standalone GGML engine for the openai-privacy-filter PII/NER token classifier, wired as a LocalAI gRPC backend (CPU/CUDA/Vulkan). TokenClassify moves off the patched llama.cpp path onto this backend. - PII filter reworked to be NER-centric (encoder/NER detection tier scanning whole conversations as one document), with a recreated bounded restricted- regex secret-matching pattern detector tier alongside it (per-model pii_detection.builtins / .patterns + core/services/routing/piipattern). - Detection labelled by source (ner vs pattern); backend trace / confidence / debug observability; analyze/redact exposed as a synchronous API. - Instance-wide default detector policy + per-usecase default-on; request filtering extended to completions, embeddings, edits & Ollama. - React UI: NER-centric PII editor, detector-models table, pattern/builtins editor, middleware default-policy UI. - Gallery: privacy-filter-multilingual token-classify model + NER install filter; token_classify known_usecase; batch sized to context for NER models. privacy-filter backend registered in the backend gallery (cpu/vulkan/cuda-13 meta + image entries with a capabilities map) matching its CI matrix jobs, and an /import-model auto-detect importer (PrivacyFilterImporter, narrow privacy-filter GGUF detection) replacing the prior pref-only registration. Reconciled against master's independent evolution: - Dropped master's PIIPatternOverrides feature (global-pattern runtime overrides + /api/pii/patterns API + runtime_settings.json persistence). The per-model NER + pattern-detector design supersedes it; it was built on the global redactor pattern set this branch replaced. - Reverted the llama.cpp Score carry-patch (0006-server-task-type-score): removed the patch and restored master's grpc-server.cpp Score RPC (direct llama_decode, slot-loop bypass) and LLAMA_VERSION pin, plus master's model_config validation forbidding score + chat/completion/embeddings on llama-cpp. token_classify is unaffected (it runs on the privacy-filter backend, not llama-cpp). Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com>
44 lines
2.0 KiB
Go
44 lines
2.0 KiB
Go
package localaitools
|
|
|
|
import (
|
|
"context"
|
|
|
|
"github.com/modelcontextprotocol/go-sdk/mcp"
|
|
)
|
|
|
|
// registerMiddlewareTools wires the routing-module admin surface for the
|
|
// MCP server, mirroring what the React /app/middleware page exposes:
|
|
//
|
|
// - get_middleware_status: read-only aggregator. The agent can ask
|
|
// "what's filtering my requests?" and get back the per-model PII
|
|
// enabled state + the detector models each references, recent event
|
|
// count, plus the active router models and their classifier configs.
|
|
// - get_router_decisions: read-only routing-decision log.
|
|
//
|
|
// PII detection policy lives on each detector model's pii_detection
|
|
// block, edited via the model-config tools — there is no global pattern
|
|
// set to mutate here anymore.
|
|
func registerMiddlewareTools(s *mcp.Server, client LocalAIClient, _ Options) {
|
|
mcp.AddTool(s, &mcp.Tool{
|
|
Name: ToolGetMiddlewareStatus,
|
|
Description: "Aggregated routing-module status: per-model resolved PII state and the NER detector models each one references, recent event count, plus the active router models and their classifier configs. Read-only.",
|
|
}, func(ctx context.Context, _ *mcp.CallToolRequest, _ struct{}) (*mcp.CallToolResult, any, error) {
|
|
status, err := client.GetMiddlewareStatus(ctx)
|
|
if err != nil {
|
|
return errorResult(err), nil, nil
|
|
}
|
|
return jsonResult(status), nil, nil
|
|
})
|
|
|
|
mcp.AddTool(s, &mcp.Tool{
|
|
Name: ToolGetRouterDecisions,
|
|
Description: "Recent intelligent-routing decisions. Each row records which router model the client called, which candidate the classifier picked, the classifier's score and latency, and a correlation id that joins back to the usage record. Filter by correlation_id, user_id, or router_model. Read-only.",
|
|
}, func(ctx context.Context, _ *mcp.CallToolRequest, args RouterDecisionsQuery) (*mcp.CallToolResult, any, error) {
|
|
decisions, err := client.GetRouterDecisions(ctx, args)
|
|
if err != nil {
|
|
return errorResult(err), nil, nil
|
|
}
|
|
return jsonResult(decisions), nil, nil
|
|
})
|
|
}
|