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/config/config.go | 37 +++++++++++++++++++++++++------------ 1 file changed, 25 insertions(+), 12 deletions(-) (limited to 'internal/config') diff --git a/internal/config/config.go b/internal/config/config.go index ce3b53f..7f87391 100644 --- a/internal/config/config.go +++ b/internal/config/config.go @@ -15,19 +15,32 @@ type Project struct { Dir string `toml:"dir"` } +// LocalModel configures an OpenAI-compatible local LLM endpoint used for +// internal helpers (classifier, future elaboration/summarization) and as the +// backend for the "local" runner. If Endpoint is empty, the LocalRunner is +// not registered and the classifier falls back to the Gemini CLI. +type LocalModel struct { + Endpoint string `toml:"endpoint"` // e.g. "http://localhost:11434/v1" + Model string `toml:"model"` // e.g. "llama3.1:8b" + TimeoutSeconds int `toml:"timeout_seconds"` // default 60 + DefaultTemperature float64 `toml:"default_temperature"` // default 0.2 + APIKey string `toml:"api_key"` // optional bearer token +} + type Config struct { - DataDir string `toml:"data_dir"` - DBPath string `toml:"-"` - LogDir string `toml:"-"` - ClaudeBinaryPath string `toml:"claude_binary_path"` - GeminiBinaryPath string `toml:"gemini_binary_path"` - MaxConcurrent int `toml:"max_concurrent"` - DefaultTimeout string `toml:"default_timeout"` - ServerAddr string `toml:"server_addr"` - WebhookURL string `toml:"webhook_url"` - WorkspaceRoot string `toml:"workspace_root"` - WebhookSecret string `toml:"webhook_secret"` - Projects []Project `toml:"projects"` + DataDir string `toml:"data_dir"` + DBPath string `toml:"-"` + LogDir string `toml:"-"` + ClaudeBinaryPath string `toml:"claude_binary_path"` + GeminiBinaryPath string `toml:"gemini_binary_path"` + MaxConcurrent int `toml:"max_concurrent"` + DefaultTimeout string `toml:"default_timeout"` + ServerAddr string `toml:"server_addr"` + WebhookURL string `toml:"webhook_url"` + WorkspaceRoot string `toml:"workspace_root"` + WebhookSecret string `toml:"webhook_secret"` + Projects []Project `toml:"projects"` + LocalModel LocalModel `toml:"local_model"` } func Default() (*Config, error) { -- cgit v1.2.3