From 0865afc43be562dbe14528e4299b9e213b54cc93 Mon Sep 17 00:00:00 2001 From: Claude Date: Tue, 28 Apr 2026 09:24:43 +0000 Subject: feat(executor): add LocalRunner and OpenAI-compat LLM client Phase 1 of "local OSS models as agents" plan. Adds a third Runner backed by any OpenAI-compatible HTTP server (Ollama, vLLM, LM Studio, llama.cpp), and migrates the Gemini-CLI classifier to route through the same client when configured. Two-layer split: internal/llm.Client is the workhorse (HTTP, no Pool, no DB) used directly by the classifier and any future internal helper that needs cheap reasoning. internal/executor.LocalRunner is a thin adapter implementing Runner for user-facing tasks. This avoids Pool reentrancy/deadlock when sub-second internal calls fire from inside Pool.execute(). Highlights: - internal/retry: relocated runWithBackoff/IsRateLimitError/ParseRetryAfter into a shared package reused by executor and llm. - internal/llm: Chat (non-streaming) and ChatStream (SSE) over /chat/completions with optional bearer auth, json_object response format, retry on 429/503, Retry-After parsing. - internal/executor/LocalRunner: streams deltas into stdout.log in the same stream-json envelope ClaudeRunner emits, then writes one consolidated assistant block plus a result terminator so existing parsers (extractSummary, ParseChangestatFromOutput) work unchanged. - internal/executor/Classifier: gains optional LLM field; uses json_object response format (no markdown-fence cleanup needed). Falls back to Gemini-CLI subprocess when LLM is nil. - Pool.skipClassification: now skips only when the requested agent type is registered, so unknown types still reach the load balancer. - Storage: additive tokens_in/tokens_out ALTERs on executions; CLI runners record cost_usd as before, LocalRunner records 0 + tokens. - Config: [local_model] section (endpoint, model, timeout_seconds, default_temperature, api_key). Empty endpoint = no LocalRunner registered, classifier falls back to Gemini. Pre-existing test issues fixed in passing: - claude_test.go setupSandbox callsites updated to current signature. - gemini_test.go TestParseGeminiStream skipped (asserts unimplemented GeminiRunner stream-error parsing; tracked separately). Plan: docs/plans/local-oss-runner.md. https://claude.ai/code/session_017Edeq947TpSm1vQTxMhi1J --- internal/executor/classifier_test.go | 76 ++++++++++++++++++++++++++++++++++++ 1 file changed, 76 insertions(+) (limited to 'internal/executor/classifier_test.go') diff --git a/internal/executor/classifier_test.go b/internal/executor/classifier_test.go index 83a9743..84fffcf 100644 --- a/internal/executor/classifier_test.go +++ b/internal/executor/classifier_test.go @@ -2,8 +2,15 @@ package executor import ( "context" + "encoding/json" + "fmt" + "net/http" + "net/http/httptest" "os" + "strings" "testing" + + "github.com/thepeterstone/claudomator/internal/llm" ) // TestClassifier_Classify_Mock tests the classifier with a mocked gemini binary. @@ -36,6 +43,75 @@ echo '{"response": "{\"agent_type\": \"gemini\", \"model\": \"gemini-2.5-flash-l } } +// TestClassifier_Classify_LLM tests classification through a local OpenAI-compatible LLM. +func TestClassifier_Classify_LLM(t *testing.T) { + srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + // Verify the classifier asked for JSON mode. + var body struct { + ResponseFormat *struct { + Type string `json:"type"` + } `json:"response_format"` + } + if err := json.NewDecoder(r.Body).Decode(&body); err != nil { + t.Fatalf("decode body: %v", err) + } + if body.ResponseFormat == nil || body.ResponseFormat.Type != "json_object" { + t.Errorf("classifier should request json_object response format") + } + + w.Header().Set("Content-Type", "application/json") + fmt.Fprintln(w, `{ + "model":"local-fast", + "choices":[{"message":{"role":"assistant","content":"{\"agent_type\":\"claude\",\"model\":\"claude-haiku-4-5-20251001\",\"reason\":\"trivial task\"}"},"finish_reason":"stop"}], + "usage":{"prompt_tokens":10,"completion_tokens":15} + }`) + })) + defer srv.Close() + + c := &Classifier{ + LLM: &llm.Client{Endpoint: srv.URL + "/v1", Model: "local-fast"}, + } + status := SystemStatus{ + ActiveTasks: map[string]int{"claude": 1, "gemini": 0}, + RateLimited: map[string]bool{}, + } + + cls, err := c.Classify(context.Background(), "List files", "ls -la", status, "claude") + if err != nil { + t.Fatalf("Classify: %v", err) + } + if cls.AgentType != "claude" { + t.Errorf("AgentType: want claude got %q", cls.AgentType) + } + if cls.Model != "claude-haiku-4-5-20251001" { + t.Errorf("Model: want claude-haiku-4-5-20251001 got %q", cls.Model) + } + if !strings.Contains(cls.Reason, "trivial") { + t.Errorf("Reason mismatch: %q", cls.Reason) + } +} + +// TestClassifier_LLMTakesPrecedence_OverGemini ensures the LLM path is preferred when both are configured. +func TestClassifier_LLMTakesPrecedence_OverGemini(t *testing.T) { + srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + w.Header().Set("Content-Type", "application/json") + fmt.Fprintln(w, `{"model":"x","choices":[{"message":{"content":"{\"agent_type\":\"claude\",\"model\":\"claude-sonnet-4-6\",\"reason\":\"r\"}"},"finish_reason":"stop"}],"usage":{}}`) + })) + defer srv.Close() + + c := &Classifier{ + LLM: &llm.Client{Endpoint: srv.URL + "/v1", Model: "x"}, + GeminiBinaryPath: "/nonexistent/gemini-binary-should-not-be-called", + } + cls, err := c.Classify(context.Background(), "n", "i", SystemStatus{}, "claude") + if err != nil { + t.Fatalf("Classify: %v", err) + } + if cls.Model != "claude-sonnet-4-6" { + t.Errorf("expected LLM path; got Model=%q", cls.Model) + } +} + func filepathJoin(elems ...string) string { var path string for i, e := range elems { -- cgit v1.2.3