From 0865afc43be562dbe14528e4299b9e213b54cc93 Mon Sep 17 00:00:00 2001
From: Claude <noreply@anthropic.com>
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/cli/llm.go | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)
 create mode 100644 internal/cli/llm.go

(limited to 'internal/cli/llm.go')

diff --git a/internal/cli/llm.go b/internal/cli/llm.go
new file mode 100644
index 0000000..04fe902
--- /dev/null
+++ b/internal/cli/llm.go
@@ -0,0 +1,31 @@
+package cli
+
+import (
+	"log/slog"
+	"net/http"
+	"time"
+
+	"github.com/thepeterstone/claudomator/internal/config"
+	"github.com/thepeterstone/claudomator/internal/llm"
+)
+
+// buildLocalLLMClient returns an *llm.Client when a local model endpoint is
+// configured. Returns nil when LocalModel.Endpoint is empty so callers can
+// gate on `if c != nil` to skip registering LocalRunner / using the LLM
+// classifier path.
+func buildLocalLLMClient(cfg config.LocalModel, logger *slog.Logger) *llm.Client {
+	if cfg.Endpoint == "" {
+		return nil
+	}
+	timeout := 60 * time.Second
+	if cfg.TimeoutSeconds > 0 {
+		timeout = time.Duration(cfg.TimeoutSeconds) * time.Second
+	}
+	return &llm.Client{
+		Endpoint:   cfg.Endpoint,
+		Model:      cfg.Model,
+		APIKey:     cfg.APIKey,
+		HTTPClient: &http.Client{Timeout: timeout},
+		Logger:     logger,
+	}
+}
-- 
cgit v1.2.3