From ae833b2765c7c8086bf8e1ea8e8ec8ee9b73e656 Mon Sep 17 00:00:00 2001 From: Claude Date: Tue, 28 Apr 2026 17:10:27 +0000 Subject: feat(api): route elaboration through local LLM when configured MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Phase 2 of "local OSS models as agents" plan. Adds a third elaboration path that calls the local OpenAI-compatible LLM via the internal/llm client, and reorders dispatch so the cheap path is tried first: local → claude → gemini, with each next attempt only on hard failure of the prior. Wiring is opt-out, not opt-in: when [local_model].endpoint is set, elaboration prefers local by default. Users with a slow or low-quality local model can disable just elaboration via: [local_model] endpoint = "..." prefer_for_elaborate = false without giving up the runner or the classifier path. Implementation: - Server gains an optional *llm.Client field via SetLLM (matches the existing SetNotifier/SetWorkspaceRoot setter pattern, no NewServer signature break). - elaborateWithLocal() reuses buildElaboratePrompt verbatim and asks for response_format=json_object so we skip markdown-fence cleanup. - handleElaborateTask reorders try chain; existing Claude-first behavior is preserved exactly when SetLLM is not called. - LocalModel.UseForElaborate() encapsulates the default-true gating with a *bool so explicit-false survives TOML parse. Tests: - elaborateWithLocal: parses valid response, errors on nil client, errors on bad JSON. - handler: local preferred when wired; falls back to claude when local fails; unchanged behavior when no LLM is configured. - config: UseForElaborate gating across empty/default/explicit-true/ explicit-false cases. Pre-existing test failures noted in docs/plans/local-oss-runner.md (post-epic cleanup): TestGeminiLogs_ParsedCorrectly returns 404 for gemini execution log fetch — predates this change. Plan: docs/plans/local-oss-runner.md. https://claude.ai/code/session_017Edeq947TpSm1vQTxMhi1J --- internal/api/server.go | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'internal/api/server.go') diff --git a/internal/api/server.go b/internal/api/server.go index 8a20349..33048e4 100644 --- a/internal/api/server.go +++ b/internal/api/server.go @@ -12,6 +12,7 @@ import ( "github.com/thepeterstone/claudomator/internal/config" "github.com/thepeterstone/claudomator/internal/executor" + "github.com/thepeterstone/claudomator/internal/llm" "github.com/thepeterstone/claudomator/internal/notify" "github.com/thepeterstone/claudomator/internal/storage" "github.com/thepeterstone/claudomator/internal/task" @@ -50,6 +51,7 @@ type Server struct { elaborateLimiter *ipRateLimiter // per-IP rate limiter for elaborate/validate endpoints webhookSecret string // HMAC-SHA256 secret for GitHub webhook validation projects []config.Project // configured projects for webhook routing + llm *llm.Client // optional local LLM client; when set, elaboration prefers it } // SetAPIToken configures a bearer token that must be supplied to access the API. @@ -73,6 +75,13 @@ func (s *Server) SetWorkspaceRoot(path string) { s.workspaceRoot = path } +// SetLLM wires a local OpenAI-compatible LLM client for use by elaboration +// (and future internal helpers). When non-nil, elaboration will prefer it +// over the Claude CLI; on failure it falls back to claude → gemini. +func (s *Server) SetLLM(c *llm.Client) { + s.llm = c +} + func NewServer(store *storage.DB, pool *executor.Pool, logger *slog.Logger, claudeBinPath, geminiBinPath string) *Server { wd, _ := os.Getwd() s := &Server{ -- cgit v1.2.3