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/ratelimit_test.go | 170 ------------------------------------ 1 file changed, 170 deletions(-) delete mode 100644 internal/executor/ratelimit_test.go (limited to 'internal/executor/ratelimit_test.go') diff --git a/internal/executor/ratelimit_test.go b/internal/executor/ratelimit_test.go deleted file mode 100644 index f45216f..0000000 --- a/internal/executor/ratelimit_test.go +++ /dev/null @@ -1,170 +0,0 @@ -package executor - -import ( - "context" - "errors" - "fmt" - "testing" - "time" -) - -// --- isRateLimitError tests --- - -func TestIsRateLimitError_RateLimitMessage(t *testing.T) { - err := errors.New("claude exited with error: rate limit exceeded") - if !isRateLimitError(err) { - t.Error("want true for 'rate limit exceeded', got false") - } -} - -func TestIsRateLimitError_TooManyRequests(t *testing.T) { - err := errors.New("too many requests to the API") - if !isRateLimitError(err) { - t.Error("want true for 'too many requests', got false") - } -} - -func TestIsRateLimitError_HTTP429(t *testing.T) { - err := errors.New("API returned status 429") - if !isRateLimitError(err) { - t.Error("want true for '429', got false") - } -} - -func TestIsRateLimitError_Overloaded(t *testing.T) { - err := errors.New("API overloaded, please retry later") - if !isRateLimitError(err) { - t.Error("want true for 'overloaded', got false") - } -} - -func TestIsRateLimitError_NonRateLimitError(t *testing.T) { - err := errors.New("claude exited with error: exit status 1") - if isRateLimitError(err) { - t.Error("want false for non-rate-limit error, got true") - } -} - -func TestIsRateLimitError_NilError(t *testing.T) { - if isRateLimitError(nil) { - t.Error("want false for nil error, got true") - } -} - -// --- parseRetryAfter tests --- - -func TestParseRetryAfter_RetryAfterSeconds(t *testing.T) { - msg := "rate limit exceeded, retry after 30 seconds" - d := parseRetryAfter(msg) - if d != 30*time.Second { - t.Errorf("want 30s, got %v", d) - } -} - -func TestParseRetryAfter_RetryAfterHeader(t *testing.T) { - msg := "rate_limit_error: retry-after: 60" - d := parseRetryAfter(msg) - if d != 60*time.Second { - t.Errorf("want 60s, got %v", d) - } -} - -func TestParseRetryAfter_NoRetryInfo(t *testing.T) { - msg := "rate limit exceeded" - d := parseRetryAfter(msg) - if d != 0 { - t.Errorf("want 0, got %v", d) - } -} - -// --- runWithBackoff tests --- - -func TestRunWithBackoff_SuccessOnFirstTry(t *testing.T) { - calls := 0 - fn := func() error { - calls++ - return nil - } - err := runWithBackoff(context.Background(), 3, time.Millisecond, fn) - if err != nil { - t.Errorf("want nil error, got %v", err) - } - if calls != 1 { - t.Errorf("want 1 call, got %d", calls) - } -} - -func TestRunWithBackoff_RetriesOnRateLimit(t *testing.T) { - calls := 0 - fn := func() error { - calls++ - if calls < 3 { - return fmt.Errorf("rate limit exceeded") - } - return nil - } - err := runWithBackoff(context.Background(), 3, time.Millisecond, fn) - if err != nil { - t.Errorf("want nil error, got %v", err) - } - if calls != 3 { - t.Errorf("want 3 calls, got %d", calls) - } -} - -func TestRunWithBackoff_GivesUpAfterMaxRetries(t *testing.T) { - calls := 0 - rateLimitErr := fmt.Errorf("rate limit exceeded") - fn := func() error { - calls++ - return rateLimitErr - } - err := runWithBackoff(context.Background(), 3, time.Millisecond, fn) - if err == nil { - t.Fatal("want error after max retries, got nil") - } - // maxRetries=3: 1 initial call + 3 retries = 4 total calls - if calls != 4 { - t.Errorf("want 4 calls (1 initial + 3 retries), got %d", calls) - } -} - -func TestRunWithBackoff_DoesNotRetryNonRateLimitError(t *testing.T) { - calls := 0 - fn := func() error { - calls++ - return fmt.Errorf("permission denied") - } - err := runWithBackoff(context.Background(), 3, time.Millisecond, fn) - if err == nil { - t.Fatal("want error, got nil") - } - if calls != 1 { - t.Errorf("want 1 call (no retry for non-rate-limit), got %d", calls) - } -} - -func TestRunWithBackoff_ContextCancellation(t *testing.T) { - ctx, cancel := context.WithCancel(context.Background()) - calls := 0 - - fn := func() error { - calls++ - cancel() // cancel immediately after first call - return fmt.Errorf("rate limit exceeded") - } - - start := time.Now() - err := runWithBackoff(ctx, 3, time.Second, fn) // large delay confirms ctx preempts wait - elapsed := time.Since(start) - - if err == nil { - t.Fatal("want error on context cancellation, got nil") - } - if elapsed > 500*time.Millisecond { - t.Errorf("context cancellation too slow: %v (want < 500ms)", elapsed) - } - if calls != 1 { - t.Errorf("want 1 call before cancellation, got %d", calls) - } -} -- cgit v1.2.3